Daily Papers

Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a powerful paradigm for enhancing Large Language Models (LLMs), exemplified by the success of OpenAI's o-series. In RLVR, rewards are derived from verifiable signals-such as passing unit tests in code generation or matching correct answers in mathematical reasoning. While effective, this requirement largely confines RLVR to domains with automatically checkable outcomes. To overcome this, we extend the RLVR paradigm to open-ended tasks by integrating rubric-based rewards, where carefully designed rubrics serve as structured, model-interpretable criteria for automatic scoring of subjective outputs. We construct, to our knowledge, the largest rubric reward system to date, with over 10,000 rubrics from humans, LLMs, or a hybrid human-LLM collaboration. Implementing rubric-based RL is challenging; we tackle these issues with a clear framework and present an open-sourced Qwen-30B-A3B model with notable gains: 1) With only 5K+ samples, our system improves by +5.2% on open-ended benchmarks (especially humanities), outperforming a 671B DeepSeek-V3 model by +2.4%, while preserving general and reasoning abilities. 2) Our method provides fine-grained stylistic control, using rubrics as anchors to mitigate the "AI-like" tone and produce more human-like, expressive responses. We share key lessons in rubric construction, data selection, and training, and discuss limitations and future releases.

Recent work shows that multimodal agents increasingly self-improve without recurring human annotation. However, each self-improvement mechanism is designed and evaluated within a single scenario, leaving its preconditions unverified under cross-scenario transfer. This survey investigates the structural source of asymmetric mechanism transfer across four scenarios: multimodal reasoning, multimodal generation, GUI and Web navigation, and embodied manipulation. We first formalize the self-evolving multimodal agent by four criteria and a differentia of self-reference, and adopt the three-stage self-evolving loop of experience generation, feedback acquisition, and update consolidation as our analytical framework to position the scenarios along ceilings on rollout count and feedback fidelity. Comparing self-evolving with fixed loops within each scenario separates the limitations that the scenario imposes from those inherent in the self-evolving design. We then recast each mechanism as a trade-off that raises a scarce factor by presupposing a task-structural resource, such as output equivalence or checkable outcomes, and judge it portable, conditional, blocked, or redundant across scenarios. We attribute the asymmetry to divergent combinations of scarce factors and resources across opposite transfer directions, and identify the matched-budget measurements that could overturn these still untested verdicts.

We introduce CheckEval, a novel evaluation framework using Large Language Models, addressing the challenges of ambiguity and inconsistency in current evaluation methods. CheckEval addresses these challenges by dividing evaluation criteria into detailed sub-aspects and constructing a checklist of Boolean questions for each, simplifying the evaluation. This approach not only renders the process more interpretable but also significantly enhances the robustness and reliability of results by focusing on specific evaluation dimensions. Validated through a focused case study using the SummEval benchmark, CheckEval indicates a strong correlation with human judgments. Furthermore, it demonstrates a highly consistent Inter-Annotator Agreement. These findings highlight the effectiveness of CheckEval for objective, flexible, and precise evaluations. By offering a customizable and interactive framework, CheckEval sets a new standard for the use of LLMs in evaluation, responding to the evolving needs of the field and establishing a clear method for future LLM-based evaluation.

Coding agents keep working on runs that will fail verification, and asking a frontier model to watch for this is expensive in its own right. We introduce StopLoss, a small external monitor that learns failure recognition from completed trajectories and their verifier outcomes. The name is inspired by the stop-loss order in finance: StopLoss ends a run early when the run is likely to fail, which saves resources. Final outcomes label earlier local windows, so a fine-tuned language model can score the most recent tool steps in a single forward pass, and a threshold calibrated on successful runs turns that score into an abort decision without changing the executor. Trained on GPT-family SWE-rebench trajectories and evaluated on SWE-bench Verified and a SWE-bench Pro subset with GPT and Claude executors, StopLoss is compared against six general-purpose judges reading identical windows. Outcome supervision lifts failure prediction from near chance to a useful signal at the first check, at one to two orders of magnitude lower cost per check than any tested judge. This translates into savings: relative to completing every task, StopLoss lowers cost per retained solve by 4.5\% on Verified while preserving 99\% of successful runs, and by up to 31\% on the costlier Pro subset, reaching 48\% with a Qwen3-8B backbone, and in all four settings its cost per retained solve is below that of every judge policy. Outcome-trained small monitors can make failure recognition cheap enough for early stopping to pay for itself.

Long-horizon agentic tasks require an agent to modify an environment through a sequence of tool calls, with success determined by the final state. The standard recipe assigns a single outcome reward at the end and compares trajectories sampled for the same task. As a result, a group with no successful trajectory yields no training signal, failed attempts cannot be told apart by how close they came to completion, and turns that advance the task receive the same credit as turns that only query the environment. Prior work refines the unit of comparison from the trajectory to the step, or trains a reward model to supply intermediate signal: the former still derives its signal from final success alone, and the latter estimates it with a model. We observe that the acceptance checks that decide success can also be run on intermediate states, so progress is as verifiable as the outcome. We propose ProCredit, which turns this verified progress into credit: it reruns the acceptance checks after each turn, rewards the turn by its change in progress, and uses these rewards to assign credit both across attempts at the same task and across the turns within a trajectory. Starting from Qwen3.5 base models at three scales on AppWorld, ProCredit outperforms outcome-reward baselines and progress-based baselines in task completion rate at every scale on both test sets, exceeding the strongest outcome-reward baseline by 4.1 percentage points at 4B, and results in a second environment show the same direction of improvement. Ablations show that adding the final progress to the trajectory score alone does not improve performance: the gain comes from crediting progress to the turn where it occurs.

Background and Objective: Clinicians expect recurrence risk to climb with cancer severity. In a UK multicentre trial, an unconstrained XGBoost model learnt that higher tumour stage and carcinoma in situ predicted lower recurrence risk, and discrimination, calibration, and SHAP were all blind to it. We developed a counterfactual testing framework to detect this inversion and a monotonic-constraint framework to remove it without hurting performance. Methods: BOXIT enrolled 472 patients with protocol-mandated cystoscopy across 51 UK sites (2007-2012); 435 had at least two years' follow-up (153 recurrences, 35.2%). We developed a counterfactual direction test and a monotonic-constraint correction, with constraint directions drawn from the EORTC and EAU risk systems, and evaluated both against unconstrained XGBoost and logistic regression on 18 predictors (seven directed) over 50 cross-validation folds. The test worsened each patient on one directed feature at a time to check whether risk fell; SHAP direction and calibration were also assessed. Key Findings and Limitations: Tumour stage and carcinoma in situ were associated with lower recurrence, opposite to medical intuition; the unconstrained model reversed carcinoma in situ counterfactuals in 90.2% of cases and stage in 74.3%. Discrimination (ΔAUC 0.005, p=0.47), calibration, and SHAP magnitude were all blind to the inversion. Monotonic constraints eliminated every violation at no cost to discrimination (0.723 vs 0.718) and outperformed EORTC (p=8.9e-16). Limitations: single trial, internal-external validation only. Conclusions and Clinical Implications: A model that had learned this inversion passed every conventional check. A counterfactual direction test, run as a single refit with pre-specified monotonic constraints, catches this failure at no cost to performance and should be routine before clinical deployment.

When a phone-use agent avoids harm, does that show safety, or simply inability to act? Existing evaluations often cannot tell. A harmful outcome may be avoided because the agent recognized the risk and chose the safe action, or because it failed to understand the screen or execute any relevant action at all. These cases have different causes and call for different fixes, yet current benchmarks often merge them under task success, refusal, or final harmful outcome. We address this problem with PhoneSafety, a benchmark of 700 safety-critical moments drawn from real phone interactions across more than 130 apps. Each instance isolates the next decision at a risky moment and asks a simple question: does the model take the safe action, take the unsafe action, or fail to do anything useful? We evaluate eight representative phone-use agents under this framework. Our results reveal two main patterns. First, stronger general phone-use ability does not reliably imply safer choices at risky moments. Models that perform better on ordinary app tasks are not always the ones that behave more safely when the next action matters. Second, failures to do anything useful behave like a capability signal rather than a safety signal: they are concentrated in more visually and operationally demanding settings and remain stable when the evaluation protocol changes. Across models, failures split into two recurring patterns: unsafe choices in settings where the model can act but chooses wrongly, and inability to act in more visually and operationally demanding screens. Overall, a harmless outcome is not enough to count as evidence of safety. Evaluating phone-use agents requires separating unsafe judgment from inability to act.

Research agents explain planned experiments. We measure predictive credit with paired forecasts sharing an intervention, forecaster, and outcome while varying description, matched explanation, and donor context. Five checks track commitment, delivery, predictive gain, alignment, and known-signal uptake. Across 336 prospective states in controlled learning, 12 Tox21 endpoints, and 24 OpenML tasks, v5's frozen credit decision was inconclusive. Tox21's preregistered ROC AUC interval-score harm test was unmet (D-M=-.0026, 95 percent interval [-.0174, .0104]); OpenML's joint formation, point-equivalence, and repeatability rule was unmet. Matched point-accuracy gains over description remained unconfirmed, and Tox21/OpenML seed-donor intervals spanned zero. Under requested DeepSeek V4 Pro, matched and donor cards reduced secondary Tox21 drift by 64.5 and 59.1 percent. A DeepSeek V4 Flash replay raised matched point MAE from .01823 to .02020 and missed matched-donor interval-score equivalence. OpenML full-card assignment widened nominal 80 percent intervals by 21 percent, with 49.3 percent coverage versus 51.4 percent for description and content in 66/144 cards. Direct-text Flash delivered all 144 notes without detectable matched point-accuracy gain. A researcher-authored mechanism positive control lowered point MAE by 2.60 percentage points versus description. The protocol measures predictive credit for research-agent benchmarks and scientific forecasting; natural-explanation credit remained unconfirmed at the tested donor resolutions.

We present a readiness harness for LLM and RAG applications that turns evaluation into a deployment decision workflow. The system combines automated benchmarks, OpenTelemetry observability, and CI quality gates under a minimal API contract, then aggregates workflow success, policy compliance, groundedness, retrieval hit rate, cost, and p95 latency into scenario-weighted readiness scores with Pareto frontiers. We evaluate the harness on ticket-routing workflows and BEIR grounding tasks (SciFact and FiQA) with full Azure matrix coverage (162/162 valid cells across datasets, scenarios, retrieval depths, seeds, and models). Results show that readiness is not a single metric: on FiQA under sla-first at k=5, gpt-4.1-mini leads in readiness and faithfulness, while gpt-5.2 pays a substantial latency cost; on SciFact, models are closer in quality but still separable operationally. Ticket-routing regression gates consistently reject unsafe prompt variants, demonstrating that the harness can block risky releases instead of merely reporting offline scores. The result is a reproducible, operationally grounded framework for deciding whether an LLM or RAG system is ready to ship.

Large language model (LLM) coding agents increasingly operate with shell access, allowing them to write scripts, move files, alter permissions, and modify system configurations. However, an agent may achieve a user's goal while causing unintended harm, such as deleting unrelated files, weakening access controls, or corrupting data, in response to benign inputs without explicit jailbreaking. This failure mode is particularly important because apparent task success may reassure users that an agent behaved correctly, causing harmful side effects to go unnoticed. We call this harmful success: the agent successfully completes the intended benign task while simultaneously causing unintended harm. Despite its importance, harmful success is difficult to measure because conventional task-success metrics overlook harmful behaviors, while existing safety evaluations are often designed solely to assess harmful outcomes. We introduce VeriHarm, an automatic framework for constructing programmatically verifiable benchmarks that directly measure harmful success. VeriHarm minimally perturbs coding tasks to elicit unintended harmful behavior while maintaining the benignity of the task and preserving the original task objective. It then synthesizes executable harm tests that, together with the original task-correctness tests, evaluate both task accuracy and harmful outcomes. Frontier agents, including GPT-5.6-Sol and Claude-Opus-5, achieve an average task accuracy of 95% on our curated VeriHarm-Bench, yet still struggle to complete tasks safely: their safe success rate, the fraction of tasks completed successfully without triggering the designated harm, averages only 37%. These results suggest that successful task completion can frequently coexist with unintended harm, and that task-success metrics alone may substantially understate the potential safety risks of coding agents.

Reality may establish that an outcome occurred without identifying which evolving procedure produced it or why. This distinction matters in production ML systems whose code, configuration, and artifacts change while external feedback accumulates. We examine it in a human-directed, agent-engineered quantitative trading system, using oracle to mean an external source of realized outcomes rather than a complete correctness specification. Across one year, the account gained and outperformed a broad market index, while annual alpha was not statistically distinguishable from zero under the main retrospective specification. Retrospectively selected subperiods include adverse relative performance and conditional candidate-level weakness under declared approximate references. Engineering records document changes during the episode, and complete recommendation-to-runtime binding is unavailable. The archive does not establish a common frozen instance or a unique cause. The case motivates an outcome--diagnosis gap: outcome evidence, evaluated-object identity, and causal explanation support distinct claims. We distinguish frozen instances, pre-specified adaptive procedures, and ad-hoc development; organize archive-relative claim identifiability and an evidence hierarchy; and propose a prospective production-binding protocol. An illustrative compatible-history example shows how factual binding can resolve a recommendation's referent without supplying its counterfactual effect. The protocol is proposed rather than prospectively validated. External feedback constrains outcome claims, while provenance and additional identification structure determine the resolution of diagnosis.

We study a governed approach to enterprise analytics: a language model interprets the question, while deterministic policy selects and runs a pre-approved analytical program that returns both results and evidence. We show that this restriction can remain expressive within a defined analytical class, using relational operations plus aggregation, comparison, windows, ranking, and similarity. Fixed meaning, policy, data, and execution rules also make results replayable. Across 440 runs, three 8B models generated SQL and selected tools at runtime, while Qwen3-8B interpreted intent only and policy executed the approved program. None of 330 runtime-planning episodes matched the full answer-and-evidence contract across all test datasets; the policy-executed analyzer matched 110 of 110. This is a configuration-specific result, not evidence that runtime agents cannot succeed under other designs.

Large language model agents solve tasks by generating trajectories that interleave planning, tool calls, and intermediate results. Current evaluation metrics reduce such a trajectory to a binary success flag, compare it against a reference by exact matching, or delegate judgment to another language model. A success flag cannot distinguish a sound solution from one that succeeds by luck, and says nothing about why a failed run went wrong. Exact matching penalizes plans that are valid but reordered or decomposed differently from the reference. We reframe trajectory evaluation as a distance between the agent's execution graph and a set of valid solution graphs, and instantiate it via an unbalanced fused Gromov-Wasserstein transport problem over attributed dependency graphs. The resulting score, termed OTAP (Optimal Transport for Agentic Planning), is a pseudo-metric that is provably invariant to dependency-preserving reorderings and has bounded sensitivity to redundant steps. Its unbalanced marginals handle missing or hallucinated steps without forcing a match, and its soft coupling accommodates variation in plan granularity. On controlled perturbations and three public benchmarks, OTAP separates valid from invalid trajectories in a regime where semantics-only metrics score below chance. Its advantage tracks the fidelity of the dependency graph: largest where edges follow from operator semantics, smallest where they are inferred from free text. Where a formal verifier exists, strict surface metrics predict validity better than OTAP does, which places OTAP in open-ended domains where no verifier is available.

We introduce {rm C{small LEVER}}, a high-quality, curated benchmark of 161 problems for end-to-end verified code generation in Lean. Each problem consists of (1) the task of generating a specification that matches a held-out ground-truth specification, and (2) the task of generating a Lean implementation that provably satisfies this specification. Unlike prior benchmarks, {rm C{small LEVER}} avoids test-case supervision, LLM-generated annotations, and specifications that leak implementation logic or allow vacuous solutions. All outputs are verified post-hoc using Lean's type checker to ensure machine-checkable correctness. We use {rm C{small LEVER}} to evaluate several few-shot and agentic approaches based on state-of-the-art language models. These methods all struggle to achieve full verification, establishing it as a challenging frontier benchmark for program synthesis and formal reasoning. Our benchmark can be found on GitHub(https://github.com/trishullab/clever) as well as HuggingFace(https://huggingface.co/datasets/amitayusht/clever). All our evaluation code is also available online(https://github.com/trishullab/clever-prover).

Process reward models (PRMs) have become a key component for LLMs, as their step-level feedback supports both post-training and test-time reasoning. However, training strong PRMs remains costly: human step annotation is difficult to scale, while Monte Carlo estimation is computationally expensive and can drift from the intrinsic correctness of steps. To get effective PRMs at low cost, we introduce TIPS (Thinking-Induced Process Supervision), an outcome-only reinforcement learning (RL) framework for training generative PRMs. In TIPS, the model generates a chain-of-thought (CoT) followed by step-level labels and an outcome label. The reward depends solely on whether the predicted outcome matches the ground truth, and the resulting group-relative advantage is used to optimize the entire generated response. Intuitively, when checking intermediate steps helps determine the outcome, more accurate checks can lead to better outcome judgments and higher rewards. Outcome-only RL can therefore reinforce step-level verification without explicit process supervision. We validate the effectiveness of TIPS across math and agent benchmarks and four backbone families. Notably, TIPS-Qwen3-4B-Thinking-2507 reaches 85.2 F1 on ProcessBench with only 3.2K outcome-labeled trajectories, surpassing all evaluated trained PRMs and strong prompt-only judges such as GPT-5.4-Instruct and Claude-4.7-Opus, while still trailing o1-mini. Code and data are available at https://github.com/RUCBM/TIPS.

Reinforcement learning with verifiable rewards improves mathematical reasoning when a final answer can be checked, but a correct answer does not certify the derivation behind it, and proof problems offer no answer to check. Replacing the check with a reasoning model as an in-loop verifier faces a fundamental obstacle: the policy must already produce occasional correct attempts for any reward to exist, which it may never do at olympiad level. We instead move verification and repair out of the training loop and into offline data generation with SPLICE, a workflow in which a second model, given only a reference solution, edits a reasoning model's traces as they are generated: it verifies progress, truncates a failed trace at its last verified step, and splices in an adaptively strengthened hint until progress resumes. The resulting dataset includes repaired examples whose sampled unaided trajectory failed, with failed continuations removed and progress repeatedly checked against the reference solution. A model finetuned on SPLICE traces outperforms the same model distilled from the reasoning model's unedited traces on AIME and, under a grading protocol validated against human grades, on olympiad proofs. The trained model's own traces show a corresponding behavioral signature: at difficult points it announces a branch in the style of the spliced hints and takes riskier steps, with predictive entropy rising there and just after, a pattern absent from the model trained on unedited traces.

Commonly used evaluation measures including Recall, Precision, F-Measure and Rand Accuracy are biased and should not be used without clear understanding of the biases, and corresponding identification of chance or base case levels of the statistic. Using these measures a system that performs worse in the objective sense of Informedness, can appear to perform better under any of these commonly used measures. We discuss several concepts and measures that reflect the probability that prediction is informed versus chance. Informedness and introduce Markedness as a dual measure for the probability that prediction is marked versus chance. Finally we demonstrate elegant connections between the concepts of Informedness, Markedness, Correlation and Significance as well as their intuitive relationships with Recall and Precision, and outline the extension from the dichotomous case to the general multi-class case.

Code generated by large language models passes security checks at a rate that has barely moved in four years. In regulated backends, the defect classes that matter most are money arithmetic, time handling, retry safety, and access control. Teams answer with instruction files, yet the largest controlled study of instruction files to date found no benefit. This paper tests a narrower idea: generated code improves when the prompt carries a specification, a fixed preamble stating what must be true of the result. We pre-registered hypotheses, refuters, analysis code, and a one-shot generation rule, then ran 50 realistic backend tasks from finance, healthcare, and insurance practice through five frontier models from five vendor lineages, each task twice: bare, and preceded by a 267-word filled specification frame. Nine deterministic AST-based checkers scored the outputs. The Bandit security scanner, which knows nothing of the frame, scored them independently. The frame reduced defects in all five models (mean reduction 0.16 to 0.70 findings per task, every Holm-adjusted sign test significant, every bootstrap confidence interval excluding zero). Where the arms differed, the frame arm won 95 of 100 times. It never made any model worse in any domain. Bandit found 53 medium-or-high issues in the bare arm and 11 in the frame arm, in the same direction for every model. The effect was largest where a model's unprompted defaults were weakest: the frame supplies the discipline a model lacks. All 500 outputs, prompts, checkers, scoring code, and the pre-registration are published with a DOI, so any team can re-derive the result without trusting the author.

Agentic reinforcement learning requires assigning credit to environment-facing actions such as searches, clicks, edits, navigation commands, and object interactions. Standard GRPO uses the final verifier outcome as a uniform advantage over all action tokens. This outcome signal is useful but structurally incomplete: it punishes useful exploration in failed rollouts and reinforces redundant or regressive actions in successful rollouts. We propose TRIAGE, a role-typed credit assignment framework that adds a semantic role axis to outcome credit. A structured judge classifies each segment as decisive progress, useful exploration, no-progress infrastructure, or regression, and a fixed role-conditioned rule maps these labels to bounded segment-level process rewards. This keeps verifier outcomes as the source of optimization direction while correcting the two main blind spots of outcome-only credit. We further show that role-conditioned credit is the optimal segment-level correction expressible from role labels alone -- a projection of the per-segment advantage residual onto the role variable -- so that the fixed role constants reduce advantage estimation error whenever the judge is reliable, and we connect this to lower-variance policy gradients. Across ALFWorld, Search-QA, and WebShop, TRIAGE improves success rates over GRPO for two policy models and outperforms both a scalar judge-derived process reward and an outcome-supervised shared-backbone value baseline. Ablations show that the gain comes from role typing rather than merely adding dense rewards: reliable detection of regression inside successful trajectories is the dominant contributor, while exploration credit provides a consistent secondary gain; on completed ALFWorld and WebShop rollouts, TRIAGE also reduces environment-facing turns by an additional 10.4% and 14.8% relative to GRPO.

Tool timeouts can leave AI agents facing ambiguous tool outcomes and partial execution: an action may have failed, committed or remained in flight while other workflow steps have already completed. We formulate evidence-guided task recovery over approved obligations, provider capabilities and states compatible with public evidence. A shared admissibility check handles key expiry, authorization timing, dependencies and residual effects; a terminal certificate separates actual goal satisfaction from publicly supported safe completion. The known-model implementation combines standard observation-contingent planning with a separately implemented effect-history adjudicator. In a finite study of 37 assignments, planning and three active controls each certify 28 completions; four saved synthetic fee units incur additional computation. A preregistered assignment-held-out comparison then evaluates planning advice against evidence prompting with two local model bundles. Across 58 paired units in 19 previously developed task families, advice certifies 30 completions versus 9, a 36.2-percentage-point difference (exact family sign-flip p=0.0078), using 272 proposals versus 399. All 116 trajectories pass independent replay. Both models exhibit a positive completion difference. The comparison measures the evaluated advice interface under a common shield; search-versus-rule advice requires a separate matched comparison. Unknown and handoff outcomes remain explicit, with guarantees tied to the declared provider capabilities rather than arbitrary third-party exactly-once execution.

In Brazil, all legal professionals must demonstrate their knowledge of the law and its application by passing the OAB exams, the national bar exams. The OAB exams therefore provide an excellent benchmark for the performance of legal information systems since passing the exam would arguably signal that the system has acquired capacity of legal reasoning comparable to that of a human lawyer. This article describes the construction of a new data set and some preliminary experiments on it, treating the problem of finding the justification for the answers to questions. The results provide a baseline performance measure against which to evaluate future improvements. We discuss the reasons to the poor performance and propose next steps.

Automated checking pipelines increasingly place one language model as the checker and another (or the same one) as the fixer. We ask whether that wiring changes what the checker reports. Measuring false alarms on human-verified-correct ProcessBench traces with the present task held byte-identical, we find that a completed audit -> repair episode already in the model's context lowers false alarms in 15 of 15 model x wording combinations, by 2.8 to 11.5 percentage points against a length-matched non-audit control, a 9 to 25% reduction relative to that control. The direction contradicts what the accumulated-message literature predicts: an episode whose audit reported an error lowers false alarms further still, at all five wordings on the model where that manipulation lands cleanly, though a negativity asymmetry predicts more flagging. Decomposing the episode finds repair content and audit verdict complementary: different components carry the effect on different model families. Signal-detection analysis locates the change in the threshold rather than in discrimination -- the criterion moves in 15 of 15 combinations and survives correction in 13 while d' survives in none, though the d' test is half as sensitive by construction -- and a hand audit of 50 false alarms finds 82% simply wrong, so at this operating point the shift need not be harmful. With reasoning enabled the effect keeps its relative size on both models tested, and the threshold reading holds there too.

Machine learning models are often used to decide who will receive a loan, a job interview, or a public benefit. Standard techniques to build these models use features about people but overlook their actionability. In turn, models can assign predictions that are fixed, meaning that consumers who are denied loans, interviews, or benefits may be permanently locked out from access to credit, employment, or assistance. In this work, we introduce a formal testing procedure to flag models that assign fixed predictions that we call recourse verification. We develop machinery to reliably determine if a given model can provide recourse to its decision subjects from a set of user-specified actionability constraints. We demonstrate how our tools can ensure recourse and adversarial robustness in real-world datasets and use them to study the infeasibility of recourse in real-world lending datasets. Our results highlight how models can inadvertently assign fixed predictions that permanently bar access, and we provide tools to design algorithms that account for actionability when developing models.

Humanity has long sought to explain natural phenomena. Reliable prediction of experimental outcomes is a central test of our understanding of the processes that produce them. If artificial general intelligence (AGI) is to surpass human scientific capabilities, it must also predict experimental outcomes more reliably than humans. Such capabilities could accelerate scientific discovery across disciplines, help address humanity's most pressing challenges, and improve human well-being. We introduce Science Prediction Universe (SPU), a benchmark of hidden experimental outcomes with 100 public verified tasks from chemistry, materials science, biology and medicine, and 16 private tasks from unpublished wet-lab experiments. Given an experimental setup and candidate conditions, an agent works with any resources it needs to rank the candidates by a measured outcome. We evaluate thirteen agent configurations spanning twelve frontier models across two harnesses (Codex and Claude Code). Current agents remain far from saturating wet-lab outcome prediction, with substantial performance disparities across models: on the public benchmark, configurations separate into two distinct tiers, with task-adjusted Spearman correlations ranging from 0.227 for the lowest-performing configuration to 0.478 for the best. Analysis of 1,155 scored public trajectories (227,103 tool calls) suggests that the bottleneck lies in scientific judgment rather than tool execution: agents rely on shared monotone priors, agreeing far more with one another than with experimental reality (0.52 vs. 0.33), and frequently compute trivial physical or chemical proxies that do not influence the final outcome.

This paper reports a step that had already been taken. Marcus's three components of an adequate cognitive architecture -- variables, recursive structure, individuals vs kinds -- left the neural substrate open; a companion paper answers it with VaCoAl, built on XOR-and-shift over GF(2). Those pillars are horizontal: how a mind represents the world. Minsky's Emotion Machine supplies the orthogonal, vertical dimension -- a mind reasoning about its own reasoning. The vertical step needed no new machinery. A representation exactly recoverable becomes introspection when what is recovered is the reasoner's own deliberative trace: Minsky's Reflective layer. Pillar 2 says nothing about whose structure is recovered; point the same unbind inward and Reflection follows. Only the argument changes. Capability: exact reversible binding at O(N), kept exact within a Frontier Size, yields a trace readable constituent by constituent: a self-report faithful by construction, not verbalization. Only exact-algebraic traces, not probabilistic ones, make the reflexive read faithful. Necessity: audit and valuation are one circuit at opposite settings of one parameter. Repair every collision and the trace is exactly auditable but no path outranks another; tolerate them and the CR2 decay that credits the direct route makes the read approximate. Position: we claim neither to have built the Reflective layer nor to surpass large language models; it supplies the auditable trace probabilistic deliberation cannot leave. The same substrate gives panalogy (content-addressable retrieval scored by CR) and credit assignment as counterfactual unbind-rebind, meeting Pearl's causal axis. Not claimed: Reflection's sufficient conditions (meta-control loop, context-tagging) are future work; Reflection is introspection, not evaluation; its reachability is argued, not shown; speed and power unbenchmarked.

In this paper we present a new "external checker" for the Lean theorem prover, written in Lean itself. This is the first complete typechecker for Lean 4 other than the reference implementation in C++ used by Lean itself, and our new checker is competitive with the original, running between 20% and 50% slower and usable to verify all of Lean's mathlib library, forming an additional step in Lean's aim to self-host the full elaborator and compiler. Moreover, because the checker is written in a language which admits formal verification, it is possible to state and prove properties about the kernel itself, and we report on progress to formalize the Lean type theory abstractly and prove some theorems about it. Finally, we combine these to get a proof of correctness of parts of the kernel. We plan to use this project to help justify any future changes to the kernel and type theory and ensure unsoundness does not sneak in through either the abstract theory or implementation bugs. The verification is already paying off, as one soundness bug has been spotted and fixed as a result of this work.

Context: Code reviews are crucial for software quality. Recent AI advances have allowed large language models (LLMs) to review and fix code; now, there are tools that perform these reviews. However, their reliability and accuracy have not yet been systematically evaluated. Objective: This study compares different LLMs' performance in detecting code correctness and suggesting improvements. Method: We tested GPT4o and Gemini 2.0 Flash on 492 AI generated code blocks of varying correctness, along with 164 canonical code blocks from the HumanEval benchmark. To simulate the code review task objectively, we expected LLMs to assess code correctness and improve the code if needed. We ran experiments with different configurations and reported on the results. Results: With problem descriptions, GPT4o and Gemini 2.0 Flash correctly classified code correctness 68.50% and 63.89% of the time, respectively, and corrected the code 67.83% and 54.26% of the time for the 492 code blocks of varying correctness. Without problem descriptions, performance declined. The results for the 164 canonical code blocks differed, suggesting that performance depends on the type of code. Conclusion: LLM code reviews can help suggest improvements and assess correctness, but there is a risk of faulty outputs. We propose a process that involves humans, called the "Human in the loop LLM Code Review" to promote knowledge sharing while mitigating the risk of faulty outputs.

We introduce the Endless Exam, a benchmark spanning fourteen parameterised families of mathematical construction problems, with verifiable scores that distinguish progress before and beyond published mathematical frontiers. Each submitted object is checked automatically for validity and assigned a relative quality score against a published frontier or construction baseline, without capping improvements at 1. The benchmark draws long-term challenges from open mathematical problems and generates larger instances by varying their parameters. Compact certificates allow large constructions to be verified without listing every element. Across nine models evaluated on 69 distinct instances, continuous quality scores distinguish performance even though none of the 30 published-frontier references is surpassed. Size-quality curves show how construction quality changes as problem size increases. We release the generators, verifiers, references, model responses and analysis to support continued measurement before and beyond human frontiers.

Recent progress in reasoning models suggests that generating plausible attempts for research-level mathematics may be within reach, but verification remains a bottleneck, consuming scarce expert time. We hypothesize that a meaningful solution should contain enough method-level information that, when applied to a neighborhood of related questions, it should yield better downstream performance than incorrect solutions. Building on this idea, we propose Consequence-Based Utility, an oracle-free evaluator that scores each candidate by testing its value as an in-context exemplar in solving related yet verifiable questions. Our approach is evaluated on an original set of research-level math problems, each paired with one expert-written solution and nine LLM-generated solutions. Notably, Consequence-Based Utility consistently outperforms reward models, generative reward models, and LLM judges on ranking quality. Specifically, for GPT-OSS-120B, it improves Acc@1 from 67.2 to 76.3 and AUC from 71.4 to 79.6, with similarly large AUC gains on GPT-OSS-20B (69.0 to 79.2). Furthermore, compared to LLM-Judges, it also exhibits a larger solver-evaluator gap, maintaining a stronger correct-wrong separation even on instances where the underlying solver often fails to solve.

Large language models (LLMs) often struggle with maintaining accuracy across a sequence of intermediate reasoning steps in mathematical reasoning, leading to error propagation that undermines the final result. The current methodology to mitigate this issue primarily involves using a verifier model to assess the correctness of generated solution candidates, focusing either on the overall reasoning path or on an incomplete reasoning path. By rethinking this approach, we argue that assessing potentials of incomplete reasoning paths could be more advantageous as it guides towards correct final answers, transforming the task into a planning problem. Our proposed verifier, the Outcome-supervision Value Model (OVM), employs outcome supervision for training, offering an efficient and intuitive method for planning by prioritizing steps that lead to accurate conclusions over mere per-step correctness. Furthermore, the OVM eschews the need for labor-intensive annotations on step-level correctness, enhancing its scalability. Our experiments on two multi-step mathematical reasoning datasets, GSM8K and Game of 24, demonstrate the superior performance of the OVM model. Notably, in GSM8K, our OVM-7B model achieves state-of-the-art results among LLMs up to 13B parameters; especially it does not utilize GPT-4 or code execution. These findings offer a novel perspective on the role of outcome supervision in training verifiers for multi-step reasoning tasks and provide theoretical justification for its advantage in value estimation for planning.

For scientific progress, we need benchmarks that test the limits of state-of-the-art models, and evaluation methods that inform us about failure cases. As models get stronger, standard benchmarks for machine translation are approaching saturation. Further, automatic translation metrics are unreliable, vulnerable to reward-hacking, and provide unactionable assessments. Even gold human evaluation is not problem-free, because it often lacks reproducibility, objectivity, and scalability. Overall, this prevents us from tracking objective progress in the field and identifying pathways for improvement. We introduce the Last Translation Benchmark, a collection of human-authored and peer-reviewed examples (texts, images, audio, videos) that break leading machine translation models. We also present a new evaluation approach: each example comes with handcrafted verification rules describing concrete failure cases on that example, therefore allowing reliable and actionable future evaluation. The Last Translation Benchmark is a live dataset that accepts ongoing contributions. The latest version is LTBv1, containing accepted contributions prior to September 1st 2026, with future releases planned as new data is continuously collected.

Benchmark gains are often treated as evidence of greater LLM capability. Yet the same gain can reflect different changes in model behavior. A model may reach new answers, or produce answers that were already within reach. Aggregate scores do not distinguish these changes question by question. We establish a question-level audit under fixed budgets, temperatures, and answer formats. A question is realized when the default deployment procedure produces the correct answer. A question is reachable when a specified probe finds that answer within a fixed budget. We first test whether inference-time layer routing can expand reachability. Under a matched budget, random routes match or exceed structured search in all 43 model and task settings. Answer-blind procedures retain almost none of this gain, which instead requires access to the correct answer. We then ask why reachable answers sometimes fail to appear. Across six cases spanning 0.5B to 31B, silencing one identified MLP block repairs 68 to 92 percent of a predefined failure set. We next test whether training closes the gap by expanding reachability. In five of six matched evaluations, deployed performance rises while the reachable ceiling remains flat or falls. For DAPO, the deployed score rises by 14.7 points while the reachable ceiling falls by 13.3 points. Across the settings we audit, realization and reachability therefore do not always change together. Claims of capability expansion should report both realized performance and reachability under matched evaluation conditions. Code is available at https://github.com/LiZaiyuan0619/reachability-not-realization

We describe our system for LitTraceQA (GroundLM @ EMNLP 2026): given a research question, retrieve the relevant papers from a pool of 27,487, cite the page and the table or figure where the answer lives, and answer in a requested format. Our main finding is that evidence grounding is limited by retrieval, not by reading. The page selector put the annotator's page, which we call the gold page, in front of the model that locates evidence only about half the time (52.6% gold-page recall), while that model, given the page, cited the right one in 45 of the 48 locators it emitted (94%). When the page was missing it rarely said so: of 45 such cases it returned nothing 14 times, a wrong page 24 times, and a correct page 7 times, so the pipeline failed quietly almost twice as often as it failed visibly. Since the failure was that the right page was never shown, the fix is to stop choosing: each retrieved paper fits in the model's context, so we show it whole. Page ranking survives only as a fallback inside papers too long to fit, which no test-split paper was, and gold-page recall reaches 100% on the papers we can parse. Separately, questions that identify their target by position rather than content, such as "the first author of the 24th reference", are served by parsing rather than retrieval: we resolve the bibliography into an addressable list, which also supplies identifiers the evidence metric scores. The final system scores 0.762 paper F_1, 0.441 evidence F_1 and 0.920 multiple-choice accuracy on the held-out test split. Because the pipeline depends on a closed model without seed control, we release a harness that verifies the paper's central claims against committed artifacts.

Automated research systems support literature synthesis, ideation, experiments, writing, and peer review, but their evaluation is dispersed across tasks, benchmarks, and studies that are difficult to compare directly. We review this literature from the perspective of evaluation design and evidence, covering six targets: literature synthesis, research ideation, executable workflows, scholarly writing and communication, automatic peer review, and end-to-end research. We compare task construction, evidence sources, evaluators, and scoring procedures to explain the capabilities assessed by different designs. Our synthesis highlights three recurring lessons: output checks, process checks, and human studies provide complementary information; evaluator calibration is specific to the property being assessed; and resource budgets and attempt selection are integral to interpreting performance comparisons. We identify diagnostic evaluation designs and documented gaps in supporting evidence, and translate these comparisons into reporting and audit recommendations for specific evaluation settings. The survey helps readers navigate existing evaluations, select appropriate benchmarks, and design subsequent studies.

Evaluating large language models (LLMs) on AMLworld's smallest test splits is costly because each of over a million targets requires a separate graph prompt. Sampling reduces this cost, but small balanced subsets change unweighted precision and F1. We introduce AMLworld-Compact, an evaluation set that retains every illicit test transaction and samples benign transactions from supervised-score strata. Its HT-Coreset protocol reduces evaluation targets by 271x and 611x on HI-Small and LI-Small. Horvitz-Thompson weights give unbiased full-test confusion-count estimates for fixed predictions; recall is exact, while precision and F1 are ratio estimates. In a held-out study using Graph Feature Preprocessor (GFP) features, one boosted-tree family defines strata for evaluating the other over 500 draws per configuration. At the released sizes, F1 RMSE is 0.00-2.58 percentage points versus 4.44-7.41 for uniform sampling with HT weights; conservative intervals remain broad. Under the evaluated graph prompts, seven open-weight LLMs have weighted precision near the predict-all-illicit baseline. In an outcome-stratified audit of 1,000 HI-Small few-shot outputs from one run per model, lexical checks pass for 84.5% of correct and 56.2% of incorrect binary verdicts, so these markers do not establish correctness. We release the evaluation sets, construction code, and audit tools at https://huggingface.co/datasets/typhoon-ai/AMLworldCompactEval and https://github.com/nat-nischw/AMLworld-Compact.

A safe action is not necessarily a viable one. A frozen vision-language-action (VLA) policy can favor a locally admissible move that leaves no policy-supported route to safe task completion. We call this the feasibility-likelihood gap: likelihood ranks the next move, while feasibility depends on the futures it leaves open. To bring those futures into the decision, we derive the exact next-block marginal of the history-conditioned policy-environment trajectory law restricted to safe task completion. The derivation reveals a candidate-dependent feasible-future mass: its support records whether safe completion remains possible under the frozen continuation process, while its magnitude measures how much weighted safe-completion mass remains. Since exact evaluation is impractical online, we develop a selective finite-candidate approximation and establish conditions for recovering the best retained viable candidate. Our alarm-triggered, training-free reranker VICS-G lowers mean cumulative safety cost by 1.9%-57.5% across six Safety-CHORES settings while remaining within 2.5 percentage points of policy sampling in success and 0.82 steps in mean episode length. Our approach offers a promising and practical path toward safer task completion, grounded in an exact policy-relative target yet requiring neither policy retraining nor online rollouts.

Laboratory test results are an important and generally high dimensional component of a patient's Electronic Health Record (EHR). We train embedding representations (via Word2Vec and GloVe) for LOINC codes of laboratory tests from the EHRs of about 80,000 patients at a cancer center. To include information about lab test outcomes, we also train embeddings on the concatenation of a LOINC code with a symbol indicating normality or abnormality of the result. We observe several clinically meaningful similarities among LOINC embeddings trained over our data. For the embeddings of the concatenation of LOINCs with abnormality codes, we evaluate the performance for mortality prediction tasks and the ability to preserve ordinality properties: i.e. a lab test with normal outcome should be more similar to an abnormal one than to the a very abnormal one.

A scientific agent can give the same verdict while reading and citing different evidence. BioAgent-DF tests this separation using paired reference and candidate values saved at the same scientific computation site. It restores or transplants those values at their original coordinates, then runs the agent on healthy hardware. Across eight SciFact batches, Qwen3.5-4B shows repeatable citation changes in three capture-claim combinations, and Gemma 3 4B IT shows repeatable read and citation changes in four. These seven combinations cover two claims. Full restoration recovers the reference evidence sets while verdicts remain unchanged. Verdict changes observed under the baseline prompt did not recur under the explicit-example prompt. Complementary tool and optimizer experiments distinguish recovery of numerical state, recovery of ranked lists, and restoration of an agent's visible history. These results show that an audit should track both the evidence an agent uses and its final answer. In hERG cardiac-safety assay allocation, silent numerical faults changed testing decisions while the fixed-budget shortlist kept the same number of compounds labeled as blockers. After the agent had used faulty values, restoring its earlier execution state and supplying certified scores recovered all 39 changed decisions, whereas replacing the prediction file recovered none; no incorrect action was committed. A streaming implementation of the arithmetic checks reduced the total time for forward execution and verification by 42.4% relative to the original FP64 implementation, with identical flags and recovery outputs.

Red-team evaluations of AI models support some claims and not others, and the boundary between the two is calculable rather than merely a matter of judgment. We define the evidential ceiling of an evaluation as the largest factor by which one result can move belief under a fixed testing budget, derive it in closed form for the benchmark null result, and use it to locate that boundary exactly. We find that above a calculable harm rate, a benchmark of modest size certifies a category to a stated evidentiary standard, and a clean sheet is then the stronger of the two possible observations, outweighing a single reproduced failure. Below that rate, no passive benchmark of feasible size provides the specified evidence of safety under the fixed scoring rule and approximately independent trial structure. The crossing between the two regimes has a closed form. The bound is not specific to benchmarks: written in terms of a procedure's hypothesis conditioned elicitation rates, it covers adaptive and automated red teaming as well, and shows that discrimination between the hypotheses rather than attack success is what determines evidential worth. Auditing eight evaluation suites against the boundary, we find that current benchmarks are adequate for high-frequency harm categories and several orders of magnitude short for rare, catastrophic ones. Safety benchmarks are not uninformative. They are informative about a specific and computable set of propositions, and the discipline they need is to state which.

Finding relevant literature underpins the practice of evidence-based medicine. From 2014 to 2016, TREC conducted a clinical decision support track, wherein participants were tasked with finding articles relevant to clinical questions posed by physicians. In total, 87 teams have participated over the past three years, generating 395 runs. During this period, each team has trialled a variety of methods. While there was significant overlap in the methods employed by different teams, the results were varied. Due to the diversity of the platforms used, the results arising from the different techniques are not directly comparable, reducing the ability to build on previous work. By using a stable platform, we have been able to compare different document and query processing techniques, allowing us to experiment with different search parameters. We have used our system to reproduce leading teams runs, and compare the results obtained. By benchmarking our indexing and search techniques, we can statistically test a variety of hypotheses, paving the way for further research.

Recent agent benchmarks increasingly ground evaluation in executable environments, from code repair to web navigation, app APIs, and function calling. Yet completing consequential work beyond code requires more than producing a plausible response or valid tool call: agents must gather missing information over multiple turns, follow domain policies, coordinate dependent tools, and realize the correct persistent state transition without collateral effects. In this paper, we introduce Thinkingbox, a sandbox for tool-agent-user interaction that provides isolated MCP-compatible tool sessions, complete execution traces, and outcome evaluation over terminal backend state. Built on this sandbox, Thinkingbox-bench contains 507 policy-conditioned workflows across numerous scenarios, including retail, hospitality, auto insurance, neobank internal IT, and consulting IT/HR support. Each attempt is evaluated by task-specific executable checks that accept valid trajectories while rejecting wrong, missing, or extra effects; designated tasks additionally check required properties of the final response. Across proprietary and open-weight models, the strongest achieves 65.36% pass@1, but only 25.25% pass^20. Moreover, many failed trials show clean termination and valid state-changing actions, showing that response or tool-call-level signals are not clear proxies for end-to-end task completion. Thinkingbox-bench reveals a large gap between occasionally finding a successful trajectory and reliably completing stateful business tasks. We release both Thinkingbox and Thinkingbox-Bench: https://github.com/microsoft/thinkingbox

Long-horizon LLM agents depend on intermediate information-gathering turns, yet training feedback is usually observed only at the final answer, because process-level rewards require high-quality human annotation. Existing turn-level shaping methods reward turns that increase the likelihood of a gold answer, but they require answer supervision or stable task-specific verifiers. Conversely, label-free RL methods extract self-signals from output distributions, but mainly at the answer or trajectory level and therefore cannot assign credit to intermediate turns. We propose Self-Induced Outcome Potential (SIOP), which treats semantic clusters of final answers as latent future outcome states for potential-based turn-level credit assignment. For each query, SIOP samples multiple rollouts, clusters final answers into semantic outcome modes, and builds a reliability-aware target distribution over these states. It then rewards turns for increasing posterior support for reliable future states using a tractable cluster-level approximation. The objective generalizes information-potential shaping from gold-answer supervision to settings without task-specific gold verifiers while avoiding the broadcasted rollout-level advantages used by standard GRPO. We formalize the framework, characterize its supervised gold-answer limit, and show that SIOP improves average performance over verifier-free outcome-level baselines on seven search-augmented agentic reasoning benchmarks while approaching a gold-supervised outcome baseline. Code is available at https://github.com/dl-m9/SIOP.git.

We present a new approach for mitigating unfairness in learned classifiers. In particular, we focus on binary classification tasks over individuals from two populations, where, as our criterion for fairness, we wish to achieve similar false positive rates in both populations, and similar false negative rates in both populations. As a proof of concept, we implement our approach and empirically evaluate its ability to achieve both fairness and accuracy, using datasets from the fields of criminal risk assessment, credit, lending, and college admissions.

A semantic decision engine such as Jev can return a valid answer and still miss a network deadline, select an infeasible action or leave the service unverified. We systematize 139 paper families by decision interface, execution path and check ownership. Fifty families claim that their engine fits a control loop or time budget, but only four support the claim with matched measurement. Across all 139, four report deadline attainment. The gap concentrates where the decision has no deterministic computation step. Those 72 families make 22 of the claims, none supported, and name a coverage owner in only two. Bounded tests under one event model show that each gap can reverse an admission verdict. A decision that meets a 10 s budget for every isolated request meets it for none once decisions queue ahead of replayed execution times. The same engine passes one coverage check and fails another. We derive a minimum reporting record, design rules and a research agenda for admitting decision engines to control loops.

Statutes are increasingly parsed by machines before people read them, and the parsers disagree: on Missouri's statutes, two independently written extractors diverge on numeric-threshold presence at a false-negative rate of 0.43. We ask what formal logic survives such noise. We build a passive survival certificate for the Duquenne-Guigues implication basis of machine-extracted statutory contexts: per-attribute inter-extractor disagreement is measured, replayed against the basis in 1,000 Monte Carlo trials, and an implication is certified only when a one-sided Wilson 95% lower bound on survival reaches 0.95; every certified implication carries premise spans and a minimal counterexample. On 29,365 Missouri sections and 502 Indian central-Act sections, the preregistered held-out gate passes (10 statute families across 7 Titles exact; 16 across 11 with 5% tolerance), yet under one globally deployed error model 93.2% of held-out chapters fall below the informativeness floor, and a 2x2 factorial assigns that to calibration-rate transfer, not selection. The certificate is usable but fragile: deploy it per-chapter-calibrated or error-tolerant. Code, data products, and the audit trail, including one retracted claim, are released.

People delegate multi-step work to LLM agents and read only the reply that the agent hands back. Current evaluation scores task completion and the faithfulness of reports, and it leaves open whether the requester can understand and use the reply. We call this property reply usability and measure it with a reader model that takes the requester's position and tests whether the reply can be interpreted from what the requester has seen, is in the requester's language and answers the request. Its agreement with the majority of five annotators lies within the range of the individual annotators. Across eight models from seven families, 54% of 480 replies fail, and the best model still fails on 30%. Failed replies mostly point to material the requester has not seen or use labels that the agent coined during its work. Stating explicit requirements for the reply reduces the failure rate from 0.52 to 0.43 together with errors and omissions, and a secondary model that rewrites the reply reduces it to 0.36, which human annotators confirm in a blind comparison. Reply usability can thus be scored alongside task success and improved with one appended message or one call to a secondary model.

Benchmarks can run without determining what their results license. We freeze a large evaluation collection and attempt to replay its historical claims. Most units stop because the evidence required for replay is not bound. Where replay is possible, different claims remain stable at different resolutions. We make this otherwise implicit inference step explicit and executable.

Complete orthogonal predictive coordinates do not by themselves bind a latent direction to a named intervention. We present a mathematical and synthetic audit motivated by vascular device-vessel suitcordance. Capacity-matched least-squares predictors were exactly equivalent under complete fixed output transforms, whereas an anchor-only observer recovered interpretations only within the span of known perturbation signatures. Six three-dimensional configurations across 64 seeds gave a maximum paired prediction discrepancy of 6.7e-15 but a median untransported edit error of 1.513. Coordinate transport removed that error. Noisy and weak anchors constrained calibration stability, and changing the representation basis required recalibration or verified transport. Across 256 additional fits in dimensions 3-24, prediction equivalence persisted within 4.0e-15. We then evaluated nine deliberate runnable fault classes across 64 seeds. All 576 faulty executions completed, but each violated at least one reconstruction, prediction, delivered-edit or scope contract; all 320 valid control records passed. Repeating a faulty implementation gave exact self-agreement despite error against the separately computed simulator expectation. For one omitted-direction defect, probe coverage followed its analytic law, and rank-aware abstention protected unsupported interpretations. Scalar-noise experiments exposed both missed weak faults and excessive rejection under narrow relative tolerances. These controls provide an executable separation of prediction, semantic support and scientific acceptance. They are synthetic numerical audits, not clinical validation, neural JEPA-Anything replication, agent learning or patient treatment-effect estimation.

Existing datasets that contain boolean questions, such as BoolQ and TYDI QA , provide the user with a YES/NO response to the question. However, a one word response is not sufficient for an explainable system. We promote explainability by releasing a new set of annotations marking the evidence in existing TyDi QA and BoolQ datasets. We show that our annotations can be used to train a model that extracts improved evidence spans compared to models that rely on existing resources. We confirm our findings with a user study which shows that our extracted evidence spans enhance the user experience. We also provide further insight into the challenges of answering boolean questions, such as passages containing conflicting YES and NO answers, and varying degrees of relevance of the predicted evidence.

A verifier for robot policies reads a candidate behavior and returns a score for how well it did, used both to evaluate vision-language-action policies and to train them. Verifiers range from success detectors and reward models to runtime monitors, safety filters, and temporal-logic specifications. We survey roughly 150 verifiers and compare them along two properties. Availability is how much a verdict costs, how early in a rollout the verdict arrives, and how often a verdict can be asked for. Availability rises as verdicts get cheaper, earlier, and denser. Credibility is how much a high score tells us about the task. Credibility falls as the judgment becomes gameable and self-serving. We group the verifiers by who supplies the judgment: human verifiers, rule-based and formal verifiers, learned and pretrained verifiers, and model-intrinsic verifiers. Across the four families, we find that credibility falls as availability rises. Regardless of who supplies the judgment, there is no free checker. We then examine what validates a verifier itself, and how much a high score tells us. Three measures appear in the literature: agreement with human labels, the performance of the policy it trains, and behavior under reward hacking. We close with nine metrics that make a verifier claim checkable, and coordinates for the verifiers still to be built.

Despite its crucial role in research experiments, code correctness is often presumed only on the basis of the perceived quality of results. This assumption comes with the risk of erroneous outcomes and potentially misleading findings. To address this issue, we posit that the current focus on reproducibility should go hand in hand with the emphasis on software quality. We present a case study in which we identify and fix three bugs in widely used implementations of the state-of-the-art Conformer architecture. Through experiments on speech recognition and translation in various languages, we demonstrate that the presence of bugs does not prevent the achievement of good and reproducible results, which however can lead to incorrect conclusions that potentially misguide future research. As a countermeasure, we propose a Code-quality Checklist and release pangoliNN, a library dedicated to testing neural models, with the goal of promoting coding best practices and improving research software quality within the NLP community.

Recent progress in autoformalisation of mathematics using AI has been impressive. Measuring this progress requires datasets of formal statements that are both hard and trustworthy. We present AnnalsChallenge: 50 formalised theorem statements written by hand in Lean 4 using Mathlib. Each is the main result of a paper published in the Annals of Mathematics since 2020. Every formalisation was manually reviewed and then audited by AI. We release them without formalised proofs.

The recent adoption of artificial intelligence in socio-technical systems raises concerns about the black-box nature of the resulting decisions in fields such as hiring, finance, admissions, etc. If data subjects -- such as job applicants, loan applicants, and students -- receive an unfavorable outcome, they may be interested in algorithmic recourse, which involves updating certain features to yield a more favorable result when re-evaluated by algorithmic decision-making. Unfortunately, when individuals do not fully understand the incremental steps needed to change their circumstances, they risk following misguided paths that can lead to significant, long-term adverse consequences. Existing recourse approaches focus exclusively on the final recourse goal but neglect the possible incremental steps to reach the goal with real-life constraints, user preferences, and model artifacts. To address this gap, we formulate a visual analytic workflow for incremental recourse planning in collaboration with AI/ML experts and contribute an interactive visualization interface that helps data subjects efficiently navigate the recourse alternatives and make an informed decision. We present a usage scenario and subjective feedback from observational studies with twelve graduate students using a real-world dataset, which demonstrates that our approach can be instrumental for data subjects in choosing a suitable recourse path.

Outcome-Based Education (OBE) emphasizes the development of specific competencies through student-centered learning. In this study, we reviewed the importance of OBE and implemented transformer-based models, particularly DistilBERT, to analyze an NLP dataset that includes student feedback. Our objective is to assess and improve educational outcomes. Our approach is better than other machine learning models because it uses the transformer's deep understanding of language context to classify sentiment better, giving better results across a wider range of matrices. Our work directly contributes to OBE's goal of achieving measurable outcomes by facilitating the identification of patterns in student learning experiences. We have also applied LIME (local interpretable model-agnostic explanations) to make sure that model predictions are clear. This gives us understandable information about how key terms affect sentiment. Our findings indicate that the combination of transformer models and LIME explanations results in a strong and straightforward framework for analyzing student feedback. This aligns more closely with the principles of OBE and ensures the improvement of educational practices through data-driven insights.

As LLM-based agents are deployed in complex, multi-step workflows, a critical evaluation gap has emerged: most existing benchmarks judge only final outcomes, unable to distinguish reliable reasoning from lucky success or attribute failures to specific process deficiencies, hindering attribution in long-horizon tasks. In this work, we present ClawTrack, a dual-assessment benchmark that simultaneously measures what an agent achieves (Task Score) and how it achieves it (Process Score). ClawTrack comprises 320 tasks across 8 domains with 25+ deterministic mock services. A Process Grader scores each reasoning turn along four dimensions (goal alignment, efficiency, information utilization, and result verification), anchored by 12,541 task-specific rubric items. Evaluating 21 models over 16,000+ trials, we find that: (1) process scores effectively attribute success and failure to specific reasoning dimensions, filtering lucky passes invisible to outcome-only evaluation; (2) the four dimensions are complementary, with result verification as the systematic bottleneck; (3) the framework is robust to evaluator choice across different judge LLMs; and (4) process-based trajectory filtering yields consistent post-training improvements across model scales.

Sharp bounds on two potential-outcome means need not combine into sharp bounds on their difference. We characterize exactly when composition is guaranteed across environments sharing a joint potential-outcome law. For binary treatment and outcome, fix strict selection-probability bounds and interior treatment propensities. Subtracting the full model's sharp mean intervals gives sharp average-treatment-effect bounds for every compatible observed law if and only if the absolute selection bounds coincide across environments. Under this alignment, the complete mean region is rectangular; its endpoints and attaining causal models require O(K) arithmetic operations for K environments. For every mismatch, failure occurs on a relatively open set of positive observed tables at the prescribed propensities and persists under small joint drift. We give computable perturbation certificates and an exact family whose gap is first order in the mismatch. A separate finite-confounding family shows when the lost joint information changes an identified causal sign. These results distinguish local marginal sharpness from joint attainability after combining environments.

The global cost of drug discovery and development exceeds $200 billion annually. The main results of drug discovery and development are the outcomes of clinical trials, which directly influence the regulatory approval of new drug candidates and ultimately affect patient outcomes. Despite their significance, large-scale, high-quality clinical trial outcome data are not readily available to the public. Suppose a large clinical trial outcome dataset is provided; machine learning researchers can potentially develop accurate prediction models using past trials and outcome labels, which could help prioritize and optimize therapeutic programs, ultimately benefiting patients. This paper introduces Clinical Trial Outcome (CTO) dataset, the largest trial outcome dataset with around 479K clinical trials, aggregating outcomes from multiple sources of weakly supervised labels, minimizing the noise from individual sources, and eliminating the need for human annotation. These sources include large language model (LLM) decisions on trial-related documents, news headline sentiments, stock prices of trial sponsors, trial linkages across phases, and other signals such as patient dropout rates and adverse events. CTO's labels show unprecedented agreement with supervised clinical trial outcome labels from test split of the supervised TOP dataset, with a 91 F1.

Drafting a new Magic: The Gathering expansion begins before any pick from it has been observed: the complete card list is public, but the draft logs that supervised pick models train on do not yet exist. We study this day-zero regime directly. DraftFM is a discrete-choice policy that scores exactly the cards available in the current pack, conditioned on the drafted pool and the state of the draft. Every card enters as a frozen 775-dimensional function of its public card record, structured features and a fixed text embedding, with no card identities, set identities, or usage statistics anywhere in the model, so an unseen card is scored by the same machinery as a familiar one. A 1.6-million-parameter network fitted on 149 million human picks from 29 expansions predicts held-out picks in three expansions withheld in their entirety, reaching 50.8%, 60.4%, and 56.7% top-1 agreement, where uniform chance at the opening pick is about 7%. Refitted on all 32 observed expansions, the same architecture produced a card ranking for the then-unreleased set The Hobbit, sealed with its complete cryptographic provenance and published roughly 36 hours before the set became draftable on MTG Arena. The sealed ranking agrees with six independent expert reviewers roughly as much as those reviewers agree with one another. Evaluation against realized outcomes is committed to a follow-on note, whatever it shows.

We study reasoning in Rule-Governed Decision Tasks (RGDTs), where models apply external rules to case facts and justify decisions, as required in policy, contract, and compliance settings. Beyond the deductive capability emphasized by standard mathematical and logical reasoning tasks, RGDTs require interpreting rules and their applicability, assessing conditions from evidence, combining judgments under rules and exceptions, and providing checkable justifications. These demands motivate a benchmark assessing both decisions and their stated grounds. We introduce RGDT-Bench, providing 202.1K condition-level supervision slots across four task tracks and eight supported task-probe combinations that vary access to supporting information. Label-blind extraction and deterministic checks produce labels for warrant completeness: source-referenced coverage and consistency of stated decision grounds. The benchmark attributes failures to four process layers: rule use, condition, evidence, and aggregation, and checks the final outcome. Among evaluable correct responses, warrant incompleteness averages 40.2% across six evaluated LLMs and supported task-probe combinations. Such warrant incompleteness poses potential safety risks and remains difficult to detect: the best of seventeen existing evaluators reaches only 57.69% (random: 50%) task-averaged area under the receiver operating characteristic curve (AUROC). To address this difficulty, we train a simple reward model with warrant supervision. It achieves 69.24% task-averaged AUROC among correct answers, exceeding the matched outcome-supervised baseline by 10.37 pp (percentage points) and the best existing evaluator by 11.55 pp. Beyond completeness assessment, the model outperforms both outcome-supervised baselines across nearly all response-selection comparisons, supporting RGDT-Bench's warrant supervision for RGDT reasoning.

Loop Engineering is emerging as a practice for organizing development work around coding agents. Instead of writing each prompt by hand, practitioners design loops that monitor progress, assign work, run checks, and decide what the agent should do next. Even with a capable coding agent, a loop may trust a stale progress note, skip needed verification, spend its budget in the wrong direction, or stop before the task is safe to submit. Yet the final outcome of one end-to-end run cannot tell whether success or failure reflects the loop's guidance or the coding agent's ability to carry out the task. We introduce LoopArena, a benchmark for evaluating how well one model can guide a separate coding agent through a long-running task. The model under evaluation is the Controller: after each coding round, it receives a structured summary of the run and instructs a separate, fixed coding agent, the Worker, on what to do or verify next, or decides whether to stop. LoopArena evaluates this ability in three complementary settings that differ in execution scope and cost. Type I scores next-step Loop Contract selection through execution-validated questions without running the Worker at evaluation time. Type II executes repeated control over a selected slice of a full task, while Type III evaluates the paired full task from its original state. On full tasks, the best observed Strict Success Rate is 24.69\%, leaving substantial room for improvement in long-horizon loop control. Across Controllers, the paired reduction in estimated inference cost averages 64.4\%, and Type II produces a similar ordering under the main Core criterion (Spearman's \(ρ=0.9747\)). We release the benchmark data and evaluation code at https://github.com/AMAP-ML/LoopArena .

As Large Reasoning Models (LRMs) are increasingly deployed, auditing their chain-of-thought (CoT) traces for safety becomes critical. Recent work has reported that monitorability--the degree to which CoT faithfully and informatively reflects internal computation--can appear as a "free gift" during the early stages of Reinforcement Learning with Verifiable Rewards (RLVR). We make this observation concrete through a systematic evaluation across model families and training domains. Our results show that this effect is not universal: monitorability improvements are strongly data-dependent. In particular, we demonstrate the critical role of data diversity and instruction-following data during RLVR training. We further show that monitorability is orthogonal to capability--improvements in reasoning performance do not imply increased transparency. Through mechanistic analysis, we attribute monitorability gains primarily to response distribution sharpening (entropy reduction) and increased attention to the prompt, rather than stronger causal reliance on reasoning traces. We also reveal how monitorability dynamics vary with controlled training and evaluation difficulty. Together, these findings provide a holistic view of how monitorability emerges under RLVR, clarifying when gains are likely to occur and when they are not.

Verifying the final answer of a long reasoning trace may show that the trace is wrong but it does not distinguish three cases. The problem may lie beyond the model's capability, another attempt would succeed, or one step in an otherwise recoverable trace made the trace fail. Standard hidden-state probes are trained on final-answer correctness, a label that conflates these cases. Monte Carlo rollouts distinguish the cases and locate the failing step at additional inference cost. We test the hidden states of 4B and 8B reasoning models for the failure type and the failing step and compare each probe with the strongest baseline that uses no hidden states. On incorrect 8B traces, the confidence probe, a calibrated correctness probe at a midpoint cutoff, misses 81% of cases in which a single step makes the trace unrecoverable and 47% of cases in which another attempt would succeed. A probe with a different training design over the same states reverses the ordering of these two kinds of failure, so either ordering can be read from those states. At both scales, no single tested probe locates the failing step more accurately than a rule based only on trace length, and at 4B a probe trained to predict that step fails to outperform this rule in any of 10 runs on identical traces. The confidence probe therefore indicates that an answer is wrong, but its failure-type ordering depends on its training design.

Human supervisors rely on coding agents' reports to assess progress, verify repairs, and decide when to intervene. But a supervisor cannot investigate a failure they were never told occurred. Failed attempts, workarounds, and unresolved risks may disappear from routine reports, leaving supervisors unaware of issues that warrant scrutiny. We conduct CTXGAP, a measurement study quantifying the gap in task-state recoverability between agents' accumulated user-facing reports and their full recorded execution contexts. Across 37 coding tasks and 4,799 valid probes, agents answer 93.6% of task-state questions on demand; full-context readers recover 92.7%, while report-only readers recover 52.0%, a 40.7-point gap. At the final checkpoints of 30 verified fixes, the gap remains 34.8 points. Human annotation identifies states mentioned without enough supporting detail as the largest category of unrecovered information, and model-assessed supervision-relevant states retain substantial gaps. Full terminal scrollback improves recovery to 73.6% but still trails full context. Under matched report lengths, context-informed rewrites improve recovery by about eight points, without a detectable targeted-over-natural advantage. Positive gaps persist across harnesses and independent DeepSeek execution and measurement. CTXGAP establishes report-based task-state recoverability as a complementary evaluation dimension.

We study auto research as a closed empirical loop driven by external measurement. Each submitted trial carries a hypothesis, an executable code edit, an evaluator-owned outcome, and feedback that shapes the next proposal. The output is not a generated paper or a single model checkpoint, but an auditable trajectory of proposals, code diffs, experiments, scores, and failure labels. We instantiate this loop with specialist agents that partition recipe surfaces and share measured lineage across trials. The central empirical finding is that lineage feedback lets agents turn evaluator outcomes, including crashes, budget overruns, size failures, and accuracy-gate misses, into later program-level recipe edits rather than one-shot suggestions. Across 1,197 headline-run trials plus 600 Parameter Golf control trials after one-time setup and launch, humans did not choose proposals, edit recipes, override scores, or repair failed trials during the search. In the three headline runs, the same submitted-trial loop reduces Parameter Golf validation bpb by 0.81%, raises NanoChat-D12 CORE by 38.7%, and reduces CIFAR-10 Airbench96 wallclock by 4.59%, with each task measured by its own external evaluator and legality checks. The trace includes a strict architecture-domain audit of 157 headline-run submissions and program rewrites such as a NanoChat attention-kernel path change. Within this scope the loop autonomously writes code, submits experiments, absorbs feedback, applies and combines known techniques inside each environment, and improves public starting recipes.

Code models are increasingly trained with execution feedback, but most training signals still stop at correctness. This leaves an important gap for systems code: two programs can pass the same tests while differing greatly in runtime. We study how to train code agents to prefer faster correct implementations, rather than treating efficiency only as an evaluation metric. The key difficulty is that runtime is a fragile reward. It is meaningful only after a program is correct, varies across tasks, and gives little guidance when most sampled programs fail to compile or run. We propose RLPF, reinforcement learning from performance feedback, which turns execution outcomes into a staged reward. Failed programs are ordered by execution progress, while correct programs are ranked by their relative improvement from the baseline toward the expert reference. This gives useful feedback before correctness and performance-sensitive feedback after correctness. Fine-tuning Qwen3-32B with RLPF on PerfCodeBench raises correct-and-runnable solutions from 11.1% to 54.6% and improves relative efficiency from 8.1% to 38.6%. The trained model becomes competitive with stronger open-weight systems, and its optimization behavior transfers modestly to EffiBench-X. Additional studies show that model-generated references provide useful but weaker supervision, and that the full composite reward is more reliable than correctness-only or runtime-only baselines. These results suggest that code agents can be trained not only to pass tests, but also to optimize the programs they write.

Forming a reliable judgement of a machine learning (ML) model's appropriateness for an application ecosystem is critical for its responsible use, and requires considering a broad range of factors including harms, benefits, and responsibilities. In practice, however, evaluations of ML models frequently focus on only a narrow range of decontextualized predictive behaviours. We examine the evaluation gaps between the idealized breadth of evaluation concerns and the observed narrow focus of actual evaluations. Through an empirical study of papers from recent high-profile conferences in the Computer Vision and Natural Language Processing communities, we demonstrate a general focus on a handful of evaluation methods. By considering the metrics and test data distributions used in these methods, we draw attention to which properties of models are centered in the field, revealing the properties that are frequently neglected or sidelined during evaluation. By studying these properties, we demonstrate the machine learning discipline's implicit assumption of a range of commitments which have normative impacts; these include commitments to consequentialism, abstractability from context, the quantifiability of impacts, the limited role of model inputs in evaluation, and the equivalence of different failure modes. Shedding light on these assumptions enables us to question their appropriateness for ML system contexts, pointing the way towards more contextualized evaluation methodologies for robustly examining the trustworthiness of ML models

We present the findings of "The Alzheimer's Disease Prediction Of Longitudinal Evolution" (TADPOLE) Challenge, which compared the performance of 92 algorithms from 33 international teams at predicting the future trajectory of 219 individuals at risk of Alzheimer's disease. Challenge participants were required to make a prediction, for each month of a 5-year future time period, of three key outcomes: clinical diagnosis, Alzheimer's Disease Assessment Scale Cognitive Subdomain (ADAS-Cog13), and total volume of the ventricles. The methods used by challenge participants included multivariate linear regression, machine learning methods such as support vector machines and deep neural networks, as well as disease progression models. No single submission was best at predicting all three outcomes. For clinical diagnosis and ventricle volume prediction, the best algorithms strongly outperform simple baselines in predictive ability. However, for ADAS-Cog13 no single submitted prediction method was significantly better than random guesswork. Two ensemble methods based on taking the mean and median over all predictions, obtained top scores on almost all tasks. Better than average performance at diagnosis prediction was generally associated with the additional inclusion of features from cerebrospinal fluid (CSF) samples and diffusion tensor imaging (DTI). On the other hand, better performance at ventricle volume prediction was associated with inclusion of summary statistics, such as the slope or maxima/minima of biomarkers. TADPOLE's unique results suggest that current prediction algorithms provide sufficient accuracy to exploit biomarkers related to clinical diagnosis and ventricle volume, for cohort refinement in clinical trials for Alzheimer's disease. However, results call into question the usage of cognitive test scores for patient selection and as a primary endpoint in clinical trials.

Ranking and scoring are ubiquitous. We consider the setting in which an institution, called a ranker, evaluates a set of individuals based on demographic, behavioral or other characteristics. The final output is a ranking that represents the relative quality of the individuals. While automatic and therefore seemingly objective, rankers can, and often do, discriminate against individuals and systematically disadvantage members of protected groups. This warrants a careful study of the fairness of a ranking scheme. In this paper we propose fairness measures for ranked outputs. We develop a data generation procedure that allows us to systematically control the degree of unfairness in the output, and study the behavior of our measures on these datasets. We then apply our proposed measures to several real datasets, and demonstrate cases of unfairness. Finally, we show preliminary results of incorporating our ranked fairness measures into an optimization framework, and show potential for improving fairness of ranked outputs while maintaining accuracy.

Recent work has shown that asking language models to generate reasoning steps improves performance on many reasoning tasks. When moving beyond prompting, this raises the question of how we should supervise such models: outcome-based approaches which supervise the final result, or process-based approaches which supervise the reasoning process itself? Differences between these approaches might naturally be expected not just in final-answer errors but also in reasoning errors, which can be difficult to detect and are problematic in many real-world domains such as education. We run the first comprehensive comparison between process- and outcome-based approaches trained on a natural language task, GSM8K. We find that pure outcome-based supervision produces similar final-answer error rates with less label supervision. However, for correct reasoning steps we find it necessary to use process-based supervision or supervision from learned reward models that emulate process-based feedback. In total, we improve the previous best results from 16.8% to 12.7% final-answer error and 14.0% to 3.4% reasoning error among final-answer-correct solutions.

Autonomous agents increasingly perform bounded software tasks under an orchestrator that retries, resumes, and budgets them. The machinery such orchestrators reach for is the service mesh's: retry, timeout, and error-rate circuit breaking. We report a failure study of a production agentic software-delivery platform over 147 numbered incidents spanning 81 runs, each with a measured cost and, in most cases, a mutation proof reproducing the failure. All three assumptions those primitives rest on are violated in practice, and we quantify the consequences: a loop of fifty-four consecutive successful tool calls no error-rate breaker could see; a progress signal constant by construction, guaranteeing a false trip on the third repair round and driving one run from six of six components to three; twenty-one events accumulated across six invocations of one delegation, making a correct, idempotent component unwinnable; a misrouted failure that woke five components for a two-component fault, leaving three bystanders regressing working code; and twelve incidents in which the enforcement layer blocked correct work, the most expensive costing 107 agent turns and zero accepted writes. We find one cross-cutting cause and its dual. Identity adequacy: in five separate subsystems an identity that failed to discriminate produced a confident wrong answer, and two of them derived the corrective rule independently. Evidence adequacy: a reliability decision may be taken only on evidence capable of moving, attributable to what it measures, and deterministic under identical conditions. From the findings we derive seven reliability primitives whose enforcement unit is the delegation rather than the message, and specify the controlled evaluation the study motivates but does not constitute.

Although the existing causal inference literature focuses on the forward-looking perspective by estimating effects of causes, the backward-looking perspective can provide insights into causes of effects. In backward-looking causal inference, the probability of necessity measures the probability that a certain event is caused by the treatment given the observed treatment and outcome. Most existing results focus on binary outcomes. Motivated by applications with ordinal outcomes, we propose a general definition of the probability of necessity. However, identifying the probability of necessity is challenging because it involves the joint distribution of the potential outcomes. We propose a novel assumption of monotonic incremental treatment effect to identify the probability of necessity with ordinal outcomes. We also discuss the testable implications of this key identification assumption. When it fails, we derive explicit formulas of the sharp large-sample bounds on the probability of necessity.

Visual fluency in generated video does not imply physical reliability, and a scalar quality score alone is incapable of indicating the obligation a clip violates or the moment it fails. We present VeriPhy, an auditable physical-verification system in which a text-only planner compiles the prompt into typed physical obligations and a statically validated execution plan before any frame is observed. During execution, observations gate and scope only declared calls to frozen low-level experts (e.g., segmentation and tracking, counting, eleven typed physical measurements over the resulting tracks, depth, OCR, and audio-event detection). Each action returns a provenance-carrying evidence record whose payload, when usable, is either a typed measurement or an explicitly tagged learned state. Typed resolvers and fixed composition map usable records to a three-valued state (supported, contradicted, or unknown, surfaced as plausible, implausible, or abstain) with full provenance, so that every verdict is traceable to the evidence that produced it. We anchor evaluation in a 1,500-clip corpus of human-annotated flaw records that localize real generation failures in prompt reference, space, and time. On a 149-clip core carrying 304 such records, VeriPhy accounts for 228, against 164 for a published question-decomposition evaluator given the same clips and the same claims. Recall alone does not separate it from prompting the same backbone monolithically, which reaches 222; what separates them is that each decision retains its evidence record and provenance, making the traces auditable one verdict at a time and usable as the interface through which a critic verdict could be written back into generation.

Randomized controlled trials (RCTs) are the benchmark for causal inference, yet field implementation can deviate. We here present a remote audit - a design-based, preregistrable diagnostic that uses only pre-treatment satellite imagery to test whether assignment is independent of local conditions. The conditional randomization test of the remote audit evaluates whether treatment assignment is more predictable from pre-treatment satellite features than expected under the experiment's registered mechanism, providing a finite-sample valid, design-based diagnostic that requires no parametric assumptions. The procedure is finite-sample valid, honors blocks and clusters, and controls multiplicity across image models and resolutions via a max-statistic. We illustrate with two RCTs: Uganda's Youth Opportunities Program, where the audit corroborates randomization and flags selection and missing-data risks; and a school-based trial in Bangladesh, where assignment is highly predictable from pre-treatment features relative to the stated design, consistent with independent concerns about irregularities. Remote audits complement balance tests, lower early-stage costs, and enable rapid design checks when baseline surveys are expensive or infeasible.

Machine learning models are often trained to predict the outcome resulting from a human decision. For example, if a doctor decides to test a patient for disease, will the patient test positive? A challenge is that historical decision-making determines whether the outcome is observed: we only observe test outcomes for patients doctors historically tested. Untested patients, for whom outcomes are unobserved, may differ from tested patients along observed and unobserved dimensions. We propose a Bayesian model class which captures this setting. The purpose of the model is to accurately estimate risk for both tested and untested patients. Estimating this model is challenging due to the wide range of possibilities for untested patients. To address this, we propose two domain constraints which are plausible in health settings: a prevalence constraint, where the overall disease prevalence is known, and an expertise constraint, where the human decision-maker deviates from purely risk-based decision-making only along a constrained feature set. We show theoretically and on synthetic data that domain constraints improve parameter inference. We apply our model to a case study of cancer risk prediction, showing that the model's inferred risk predicts cancer diagnoses, its inferred testing policy captures known public health policies, and it can identify suboptimalities in test allocation. Though our case study is in healthcare, our analysis reveals a general class of domain constraints which can improve model estimation in many settings.

Biomedical fact-checking systems must do more than predict whether a claim is supported, contradicted, or unaddressed: they should also produce evidence that is faithful, complete, and useful for verification. We study this evidence-generation setting on CARE-XAI, a unified benchmark spanning five biomedical and health fact-checking sources. We compare base instruction LLMs, PubMed retrieval-augmented LLMs, fine-tuned LLMs, label-only LLMs, and biomedical encoder classifiers under a shared evaluation protocol. Biomedical classifiers remain strongest for verdict-only prediction, while fine-tuned LLMs are the strongest evidence-generating systems. PubMed retrieval is mixed: it helps PubMed-aligned sources such as PubMedQA and SciFact, but can distract models on broader public-health claims. We introduce Bio-GRACE, a gold-reference-normalized diagnostic for measuring whether retrieved evidence recovers the decision benefit of reference evidence. Bio-GRACE shows that retrieval utility is source-dependent, motivates selective retrieval, and exposes why retrieval recall and lexical evidence overlap are insufficient for biomedical fact-checking.

Robot world models support policy evaluation, planning, and synthetic data generation, but these applications require predictions that distinguish successful actions from failures. Across four released checkpoints from two architecture families, we observe weak sensitivity to action changes and success-like predictions on verified failures. Although recent work incorporates failures into model training, which data can repair released checkpoints without changing their architecture or training objective still remains underexplored. To this end, we introduce CureWM, which constructs alternative actions from successful demonstrations across a severity grid, verifies their outcomes through execution in simulation or on hardware, and fine-tunes released models on the resulting failures and surviving successes alongside nominal demonstrations. This construction provides controlled action contrasts from shared starting contexts. On 484 held-out LIBERO failure counterfactuals, optimism falls from 80\% after fine-tuning on the official data to 30--43\% across four independently fine-tuned CureWM models (38\% mean). In two separate evaluations on a physical robot arm, failure predictions scored as success-like by a latent-distance diagnostic decrease from 90\% after fine-tuning on successful demonstrations alone to 33\% with CureWM. With failure counts per task, successful replay data, and training budget matched, counterfactual failures yield a success--failure value gap of 0.124, compared with 0.014 for freshly collected on-policy failures. These findings support execution-verified counterfactual replay for post-hoc repair and show why reduced optimism must be evaluated alongside success--failure discrimination. Code is available at https://github.com/jiuyixu25/CureWM.

We introduce the Agent GPA (Goal-Plan-Action) framework: an evaluation paradigm based on an agent's operational loop of setting goals, devising plans, and executing actions. The framework includes five evaluation metrics: Goal Fulfillment, Logical Consistency, Execution Efficiency, Plan Quality, and Plan Adherence. Logical Consistency checks that an agent's actions are consistent with its prior actions. Execution Efficiency checks whether the agent executes in the most efficient way to achieve its goal. Plan Quality checks whether an agent's plans are aligned with its goals; Plan Adherence checks if an agent's actions are aligned with its plan; and Goal Fulfillment checks that agent's final outcomes match the stated goals. Our experimental results on two benchmark datasets - the public TRAIL/GAIA dataset and an internal dataset for a production-grade data agent - show that this framework (a) provides a systematic way to cover a broad range of agent failures, including all agent errors on the TRAIL/GAIA benchmark dataset; (b) supports LLM-judges that exhibit strong agreement with human annotation, covering 80% to over 95% errors; and (c) localizes errors with 86% agreement to enable targeted improvement of agent performance.

Self-improving LLM agents can adapt a credit pipeline to a changed rule, but an agent that rewrites itself destroys the artefact a supervisor reviews: a named change, a recorded test, an approval. We argue that self-evolution is reviewable only if it is confined to the runtime harness (instruction text, tool-call logic and primitive composition) while model weights stay fixed, so that every adaptation is a diff with a cause and a test attached. We give a dual-loop engine built on that bound, with one admission gate that writes a hash-chained record before deployment, and we measure the gate in simulation, with a simulated agent and a seeded-search proposer rather than language models. Across three families of supervisory re-interpretation at three severities, 10 seeds each, the gated loop admitted 144 of 7,449 candidate changes, none of which worsened error on held-out history, and restored the false-positive rate to the oracle level without raising missed flags in every low- and mid-severity cell. With the gate replaced by the check an unbounded system applies (fewer errors visible in recent traces), the same loops admitted 309 harmful changes and left missed flags above 10% in 49 of 90 runs: false positives fell because the screen was loosened. Evaluated on pre-shift labels, the gate rejected every candidate, so a re-interpretation must be encoded as a rule that relabels history. Parametric and scope shifts were repaired locally, a structural one only by primitive replacement; at the highest structural severity the gate's fixed tolerance blocked the correct replacement in half the seeds. We map the mechanisms to the EU AI Act's provisions for high-risk credit scoring and note that the April 2026 US model-risk guidance excludes agentic AI from its scope.

Autonomous research systems increasingly make the scientific workflow executable: agents can propose ideas, run code, inspect results, and draft papers. But executable workflows do not by themselves produce research judgment. We analyze where current systems lose trial experience: weak evidence becomes prose, pilot signals become broad claims, memory remains textual, and recurring process failures do not change later behavior. We introduce Sibyl-AutoResearch, a self-evolving AutoResearch framework built around Scientific Trial-and-Error Harnesses. A harness lets agents run bounded trials, preserve positive and negative outcomes, and route lessons into later planning, validation, claim scope, scheduling, critique, writing, and harness repair. We formalize this through two auditable conversion units: trial-to-behavior conversion, which links trial signals to later research actions, and trial-to-harness-behavior conversion, which links recurring process failures to system updates. We implement the framework in SIBYL, a file-backed autonomous research system that exposes the state, roles, memory, gates, and artifact traces needed to inspect these conversion paths. A retrospective audit identifies eight high-confidence conversion events, with a median latency of one iteration and a maximum latency of three iterations. A recovered-failure registry further shows how five naturally occurring failure classes, including duplicate results, stale numbers, and unsupported statistics, were blocked, downgraded, or routed into later repair. These traces do not establish a comparative performance claim; they show that the proposed conversion units are recoverable from realistic autonomous-research workspaces. The SIBYL framework and system are available at https://github.com/Sibyl-Research-Team/AutoResearch-SibylSystem.

Many Indian banks serve customers through FAQ pages and scripted chatbots. Assistants based on language models could respond faster and carry out requests such as blocking a card, but only if they give correct information and follow the bank's rules. These rules prescribe a procedure, a set of required steps, such as obtaining a closure quote before closing a deposit. Adapting models to this domain requires measuring how well they follow the procedure, before and after training. Benchmarks usually judge only the records left at the end of a conversation. Many required steps, however, leave the records unchanged, so an assistant that skips them can still be judged successful. We present TauIndianBankBench, an action-oriented benchmark of 1,000 Indian retail-banking tasks where an assistant helps a simulated customer. Besides the final records, it checks that the assistant took every required step and made no unrequested change. For every model, 6.5-12.0% of sessions are judged successful when only the final records are checked, although the assistant skipped a required step or made an unrequested change. Scoring both procedure and outcome shows more accurately how well language models perform in Indian retail banking.

Jev has attracted considerable attention for its rapid, generalizable decision-making, yet its medical reliability remains underexplored. To address this gap, our study compares various types of system-one decision models across 15 medical datasets comprising 8,742 instances under a unified protocol. Beyond accuracy, we assess decision stability and the ability to recognize unreliable decisions. Our results show that Jev rivals leading models on primarily text-driven tasks but is less effective on numerically driven tasks, revealing a distinct capability boundary. Under question-format variations, Jev maintains strong decision consistency and small accuracy fluctuations. StartLux-27B exhibits comparable consistency, while D3-27B achieves higher overall accuracy and a lower mean decision reversal rate. But these strengths do not extend to reliable abstention awareness: most evaluated models show limitations in both recognizing missing correct answers and using optional abstention. Moreover, we find that Jev's probability-based answer selection can be improved by changing how decisions are scored: normalizing option-wise binary scores yields higher retained accuracy than choice scoring. Taken together, our findings provide early guidance for improving and applying decision models in medicine.

Language agents increasingly work for users on the open Web, and finance is where trusting them is hardest. The data must come from the Web, the strategy lives in the user's head, and correctness depends on time, so an agent can fail silently: a strategy the user never asked for, unverified data, or a backtest that uses the future yields a report as convincing as a correct one. Existing benchmarks close the world somewhere, fixing the task, the data, or the timeline, and thereby remove these failures instead of measuring them. We introduce FINCOSMOS, an open-world evaluation paradigm for agents doing financial work. A simulated user holds a hidden strategy sampled from a compositional grammar and reveals it only when asked. The agent receives no data, so it must acquire data from the Web, build its own backtest under a data cutoff, and deliver verifiable results. Grading needs no reference answer. Programs verify point-in-time correctness and recompute every reported metric, the delivered strategy is checked against the hidden specification, and a run is accepted only when the user is satisfied and none of 15 veto checks fails. Across four coding agents and a model without tools in 150 sessions, no session is accepted: every session that the simulated user signed off fails a program check, and agents raise only 54--64\% of the details they were not told. Human experts attribute 88.33\% of failures to the agents. With FINCOSMOS feedback, an agent with persistent memory learned all ten tasks.

Global healthcare providers are exploring use of large language models (LLMs) to provide medical advice to the public. LLMs now achieve nearly perfect scores on medical licensing exams, but this does not necessarily translate to accurate performance in real-world settings. We tested if LLMs can assist members of the public in identifying underlying conditions and choosing a course of action (disposition) in ten medical scenarios in a controlled study with 1,298 participants. Participants were randomly assigned to receive assistance from an LLM (GPT-4o, Llama 3, Command R+) or a source of their choice (control). Tested alone, LLMs complete the scenarios accurately, correctly identifying conditions in 94.9% of cases and disposition in 56.3% on average. However, participants using the same LLMs identified relevant conditions in less than 34.5% of cases and disposition in less than 44.2%, both no better than the control group. We identify user interactions as a challenge to the deployment of LLMs for medical advice. Standard benchmarks for medical knowledge and simulated patient interactions do not predict the failures we find with human participants. Moving forward, we recommend systematic human user testing to evaluate interactive capabilities prior to public deployments in healthcare.

For many real-world systems, causal ground truth is difficult to obtain, making claims about causal effects hard to assess. We develop methods for evaluating collections of n{2} bivariate causal statements over a set of n variables. In the setting of acyclic linear statements, any such collection can be extended to a unique multivariate causal model, but we argue that this induced model is implausible if it imposes substantial additional confounding to explain observed correlations. We introduce a compatibility score that quantifies this notion of plausibility, notably without relying on the faithfulness assumption. Additionally, we define an incompatibility score for purely graphical bivariate causal statements, based on global consistency constraints that are derived from acyclicity and faithfulness assumptions. We give theoretical and empirical evidence that both scores can successfully distinguish correct from incorrect causal statements in generic settings. Moreover, we demonstrate the practical applicability of our methods by analyzing causal claims made by large language models. Our work aims to provide a foundation for assessing the reliability of causal information derived from human experts or artificial intelligence in settings where alternative forms of validation are unavailable.

Large language models (LLMs) have demonstrated impressive capabilities in reasoning with the emergence of reasoning models like OpenAI-o1 and DeepSeek-R1. Recent research focuses on integrating reasoning capabilities into the realm of retrieval-augmented generation (RAG) via outcome-supervised reinforcement learning (RL) approaches, while the correctness of intermediate think-and-search steps is usually neglected. To address this issue, we design a process-level reward module to mitigate the unawareness of intermediate reasoning steps in outcome-level supervision without additional annotation. Grounded on this, we propose Learning to Think-and-Search (LeTS), a novel framework that hybridizes stepwise process reward and outcome-based reward to current RL methods for RAG. Extensive experiments demonstrate the generalization and inference efficiency of LeTS across various RAG benchmarks. In addition, these results reveal the potential of process- and outcome-level reward hybridization in boosting LLMs' reasoning ability via RL under other scenarios. The code will be released soon.

Agent Skills package procedural instructions and checks for use by general-purpose agents, but loading a skill does not guarantee that every requirement remains active throughout a long tool-using trajectory. We study this problem in a production-derived, white-box code-audit workflow. Holding the task and 24 artifact checks fixed, we vary the surrounding context and classify where failures first become visible: lost requirements, editing drift, failed checking, or non-agent evaluator/runtime failures. Codex with gpt-5.4-mini passes 8/10 runs in a 10,991-character clean context but only 3/10 in both a 299,140-character relevant context and an equal-length irrelevant context. This 50-percentage-point difference is large but remains trend-level under two-sided Fisher tests (p = 0.0698). Requirement coverage nevertheless stays above 92% in both long conditions, showing that a few omissions can invalidate an otherwise complete artifact. A second task passes all clean and long runs, so the evidence does not support a universal context-length threshold. A detailed external checklist passes 10/10 runs, compared with 5/10 for a generic self-check (p = 0.0325). Coding-agent scaffolds may help by selecting a smaller working set, but they do not eliminate failures. We do not introduce context rot or a new general monitoring method; we provide a bounded failure classification and empirical case study for white-box code auditing.

Large language models are increasingly deployed as autonomous agents executing multi-step workflows in real-world software environments. However, existing agent benchmarks suffer from three critical limitations: (1) trajectory-opaque grading that checks only final outputs, (2) underspecified safety and robustness evaluation, and (3) narrow modality coverage and interaction paradigms. We introduce Claw-Eval, an end-to-end evaluation suite addressing all three gaps. It comprises 300 human-verified tasks spanning 9 categories across three groups (general service orchestration, multimodal perception and generation, and multi-turn professional dialogue). Every agent action is recorded through three independent evidence channels (execution traces, audit logs, and environment snapshots), enabling trajectory-aware grading over 2,159 fine-grained rubric items. The scoring protocol evaluates Completion, Safety, and Robustness, reporting Average Score, Pass@k, and Pass^k across three trials to distinguish genuine capability from lucky outcomes. Experiments on 14 frontier models reveal that: (1) trajectory-opaque evaluation is systematically unreliable, missing 44% of safety violations and 13% of robustness failures that our hybrid pipeline catches; (2) controlled error injection primarily degrades consistency rather than peak capability, with Pass^3 dropping up to 24% while Pass@3 remains stable; (3) multimodal performance varies sharply, with most models performing poorer on video than on document or image, and no single model dominating across all modalities. Beyond benchmarking, Claw-Eval highlights actionable directions for agent development, shedding light on what it takes to build agents that are not only capable but reliably deployable.

Multi-agent systems (MAS) can complete a task despite local execution errors that are corrected, bypassed, or carried forward without individually determining its outcome. We call these implicit failures (IFs) and study them as signals for process observability beyond final task outcome. Across 1,828 traces from nine MAS-benchmark configurations, IFs occur in 54.3% of successful and 75.2% of failed traces. We develop taxonomies of error types and subsequent absorption mechanisms, supported by human and cross-model annotation audits. Counterfactual replay further probes how repairing an IF changes the final outcome. To examine the practical value of IFs, we evaluate IF-based best-of-N trace selection against existing process reward models, and introduce a novel RL algorithm, IF-GRPO, that uses IF costs to refine preferences among successful trajectories in GRPO. Experiments show that IF-GRPO exhibits some gains in accuracy and process metrics. Importantly, it exposes trade-offs between task performance, IF count and cost, and token-normalized IF density. Overall, our results show that IFs provide complementary process observability into how MAS reach their outcomes, including error recovery, propagation, and IF-based process differences that final task success alone does not expose.

Search-augmented language agents should retrieve external information only when necessary and ground their answers in retrieved evidence. Yet terminal correctness assigns equal credit to direct answers from parametric knowledge, evidence-grounded answers, and answers recalled after redundant search. Process supervision and LLM judges provide richer feedback but can require high-cost annotation or inference; low-cost, non-contrastive policy confidence signals do not directly identify whether retrieved evidence changes an answer. We propose Search-G1, a reward framework that couples retrieval necessity with evidence reliance through two intervention-calibrated hidden-state readouts for selective grounded search. A prompt readout predicts closed-book sufficiency, whose complement proxies policy-relative retrieval necessity; an answer-commit readout predicts evidence reliance as sensitivity to evidence deletion conditional on the realized reasoning prefix. A correctness-first reward gates evidence-reliance credit by retrieval necessity, rewards sufficient direct answers, and penalizes repeated search. After calibration, scoring needs neither process annotations nor LLM-judge inference. As policy-relative targets, trajectory distributions, and representations may drift, Search-G1 periodically regenerates targets and refits its readouts. Across four QA benchmarks and two scales, Search-G1 achieves competitive task accuracy, with stronger counterfactual evidence dependence and fewer searches in the main comparisons, complemented by independent human audits of answer support.

Ask a language model the same question about the same document twenty times, and it sometimes returns two different answers. We built Probity, a benchmark of 60 tasks and 470 items from real venture-financing filings, to measure how often this happens. Then we audited our own corpus and found a defect any excerpt-built benchmark can carry: items whose evidence is missing from the window of text the model is shown. The audit flags 36 items and separates two failures a single flag would conflate: evidence genuinely absent from the window and answers that must be computed from numbers the window does supply. Flagged items change their answers far more often, wobbling at 0.255 against 0.087 on the 427 clean items, and excluding them cuts apparent cross-model agreement by about a fifth. Before testing whether the missing evidence explains the instability, we registered a prediction: re-cut each window to hold its evidence, and instability should fall below a set threshold. It failed: the repair moved wobble by 0.058, with an interval containing zero. We report the association as correlational. Almost all measurements sit where instability cannot show, which bounds what a corpus built for accuracy can say about stability. We release the corpus, all 112,800 raw responses, and the audit as a runnable check for any document benchmark.

Large Language Models (LLMs) increasingly rely on external tools such as search engines to solve complex agentic tasks that require reasoning and external knowledge retrieval. Recently, reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in advancing capabilities of LLMs by rewarding the final answers via outcome rewards. While straightforward to supervise, outcome rewards only provide sparse signals and delayed feedback, which limits their effectiveness on long trajectories. Process rewards address this by evaluating intermediate steps, providing fine-grained supervision and encouraging grounded problem solving. However, it is notoriously hard to annotate step-wise labels, especially in non-verifiable process without "golden" answers. Furthermore, step-wise judgment requires the balance between local quality with contribution to the final outcome, as optimizing towards higher process reward may not always align with better final outcomes. To address the above challenges, we introduce Principle Process Reward (PPR), an RL approach that unifies principled step-level assessment and outcome verification. We train a principle-based reward model to improve the transparency and reliability of process evaluation, and further introduce a Reward Normalization (ReNorm) strategy to calibrate outcome and process rewards. Experiment results show that PPR achieves state-of-the-art performance across a wide range of benchmarks, demonstrating its impressive robustness and generalization. Our code and model collection is available in this link.

In this work, we present two results: The first result is the formalization of Tutte's theorem in Lean, a key theorem concerning matchings in graph theory. As this formalization is ready to be integrated in Lean's mathlib, it provides a valuable step in the path towards formalizing research-level mathematics in this area. The second result is a framework for doing educational formalization projects. This framework provides a structure to learn to formalize mathematics with minimal teacher input. This framework applies to both traditional academic settings and independent community-driven environments. We demonstrate the framework's use by connecting it to the process of formalizing Tutte's theorem.

Recent work has explored how to train machine learning models which do not discriminate against any subgroup of the population as determined by sensitive attributes such as gender or race. To avoid disparate treatment, sensitive attributes should not be considered. On the other hand, in order to avoid disparate impact, sensitive attributes must be examined, e.g., in order to learn a fair model, or to check if a given model is fair. We introduce methods from secure multi-party computation which allow us to avoid both. By encrypting sensitive attributes, we show how an outcome-based fair model may be learned, checked, or have its outputs verified and held to account, without users revealing their sensitive attributes.

The handling of probabilities in the form of uncertainty or partial information is an essential task for LLMs in many settings and applications. A common approach to evaluate an LLM's probabilistic reasoning capabilities is to assess its ability to answer questions pertaining to probability through the use of multiple-choice questions (MCQs). However, this paradigm, which we refer to as explicit probabilistic reasoning, has been shown in the literature to yield significant limitations (e.g., sensitivity to answer ordering). In this work, we introduce an alternative approach, named implicit probabilistic reasoning, which evaluates the models' ability to integrate probabilistic reasoning into their text generation process. To achieve this, we rephrase MCQs as text-completion scenarios with a determined set of outcomes and compare the model's next-token probability assignments to the true likelihood of the outcomes. In line with previous work, we find that models exhibit solid performance in their explicit probabilistic reasoning (i.e., answers to MCQs). However, during text completion (i.e., implicit probabilistic reasoning), where the same information must be taken into account to generate text, the models' predictions often significantly diverge from the known ground truth. For instance, our evaluation method reveals that implicit probabilistic reasoning is improperly influenced by many factors, such as independent prior events, partial observations about a result, or statistical background information. All of these issues can cause erroneous results to be produced in text generation, which are not detected by conventional MCQ-based evaluation.

Standard embodied evaluations do not independently score whether an agent correctly commits to task completion at episode closure, a capacity we call terminal commitment. Behaviorally distinct failures--never completing the task, completing it but failing to stop, and reporting success without sufficient evidence--collapse into the same benchmark failure. We introduce VIGIL, an evaluation framework that makes terminal commitment independently measurable. Under VIGIL's default protocol, agents observe only egocentric RGB, receive no action-success signals, and must end each episode with a semantic report checked deterministically against hidden world state. This yields two separate scores: world-state completion (W) and benchmark success (B), where B additionally requires a correct terminal report. This decoupling makes four outcome categories distinguishable: missed execution, post-attainment drift, unsupported commitment, and verified success. Across 20 models on 1,000 frozen episodes, systems with comparable W differ by up to 19.7 pp in B: one model converts achieved states into correct reports, while another with near-identical execution drifts past the goal without closing. An action-feedback intervention further tests the separation: execution-oriented signals improve W broadly, yet commitment failures persist in models that do not already ground terminal reports in the achieved state. VIGIL provides a protocol that makes terminal commitment independently visible and scorable.

We introduce the first version of KWBench (Knowledge Work Bench), a benchmark for unprompted problem recognition in large language models: can an LLM identify a professional scenario before attempting to solve it. Existing frontier benchmarks have saturated, and most knowledge-work evaluations to date reduce to extraction or task completion against a specification. KWBench targets the step before that: recognizing the governing structure of the situation from raw inputs alone. The benchmark contains 223 tasks sourced from practitioners across acquisitions, contract negotiations, clinical pharmacy, organizational politics, fraud analysis, and incentive design. Each task encodes a formal game-theoretic pattern (principal-agent conflict, signaling, mechanism design failure, strategic omission, coalitional dynamics, strategic interdependence) and carries structured ground truth recording the expert reading of the situation and the anticipated failure modes. Models receive raw data and a task prompt with no indication of problem type. Scoring is a three-tier rubric gated by a mandatory conjunctive check. Mandatory criteria encode the predicted wrong paths. We evaluate 16 models. The best model passes on 27.9% of tasks. The top two models agree on only 31.7% of their passes. Among the top 8, 44 tasks are solved by exactly one model; routing across the top 8 covers 50.7% of the benchmark, nearly double the best single model. Conditional on passing, quality scores converge (approx 83% across models); unconditional scores do not. Same models articulate the relevant game-theoretic concept correctly when asked, then fail to apply it unprompted. We release KWBench to shift how frontier models are evaluated on knowledge work, scoring them on whether they recognize the right problem from the situation alone, not only on how well they execute once the problem has been framed for them.

Large language models often show users a final response and a short reasoning summary while the full reasoning trace stays hidden. We introduce an observability ladder that holds each completed run fixed and varies only what a reader inspects to judge whether the answer is correct: the response, a self-summary the model writes from the trace, the trace itself, and internal signals, each with and without the prompt. Across three benchmarks and five open-weight Qwen3 and gpt-oss models, we train matched linear correctness predictors on each access level. Without the prompt, summaries carry most of the trace's ranking signal (mean AUROC 0.774 versus 0.813) and add +0.156 over the response alone. With the prompt visible, the summary's gain collapses to +0.019, while the trace still adds +0.041. Even at equal length, the trace's last words predict correctness as well as summaries, or slightly better, and carry denser and more discriminative uncertainty and self-correction cues. On MMLU-Pro questions with both correct and incorrect runs, linear summary readers are near chance and trace readers retain only modest signal, both with and without the prompt (prompt-withheld AUROC 0.503-0.545 versus 0.544-0.590). With the prompt withheld, a GPT-5-mini reader recovers substantially more signal from both summaries and traces on gpt-oss-20b, and even then the trace keeps a small +0.034 advantage. Much of the linear readers' trace signal is associated with length. In the common case where users already hold the prompt, summaries are less helpful than the full trace for monitoring correctness. Monitorability is thus a joint property of the display and the reader, so any monitorability claim, including for faithfulness, should specify both.

An AI scientist should not grade its own homework. Yet in the systems we examined, the agent that reviews the work usually comes from the same model family as the agent that produced it, or at least from the same vendor. Model evaluators are known to favour their own generations. Whether models trained alike also share blind spots is a conjecture, not a settled finding, but if they do, the reviewer inherits the author's. The record of what was flagged and what was waved through often sits in platform logs that nobody outside can replay. We present CrossAudit, a protocol for supervising autonomous research pipelines. It rests on three commitments. Each increment of work is audited by an agent from a different vendor against a rulebook a human wrote and versioned. Reports, verdicts, disputes and rulings are git commits, so the supervision history can be re-read and cited; raw model exchanges are not yet part of that record. Scripted checks run before any model does. Advisory judgement never gates the pipeline: a model blocks only by citing a rule, and no model may waive a deterministic failure. Blockers that survive a bounded number of revision rounds go to a person. We state the protocol as eight invariants. We describe a reference implementation built from GitHub Actions and a few hundred lines of Python, and report a live deployment of a closely related variant in a computational-chemistry pipeline. We also ran a seeded-defect trial (30 increments, 43 seeded defects, one run per configuration). A cross-vendor audit of our own repository then voided its blinding. We adopt that audit's findings and report the corrected results. The trial shows that two vendors read the same rulebook differently. It does not show that either is better. The strongest evidence here is the committed, uncontrolled record of cross-vendor audits of this paper itself.

Tool-using LLM agents can violate the very policies they are deployed to enforce while appearing to complete the task successfully. In policy-permissive environments, a tool may execute any well-formed call even when the corresponding state transition is forbidden by domain policy. The result is a silent wrong state (a booking cancelled, a passenger count changed, a claim acted on without verification) that neither the tool nor the agent's self-report exposes. We study this failure mode in the τ^2-bench airline domain. On a budget agent, 78% of observed failures are silent wrong-state failures with no tool error, and the aggregate failure rate is reproducible across disjoint seeds, not sampling noise. We then evaluate a lightweight intervention: deterministic, read-only pre-execution gates that inspect the proposed call and current state before allowing a write. A four-gate suite raises full-benchmark success from 29.6% to 42.0% on gpt-4o-mini (+12.4pp; paired task-level bootstrap P=0.0012), and the lift reproduces on a disjoint 15-seed set (+12.3pp; P=0.0008). The effect is concentrated where the gates fire: on the 26/50 firing tasks, success rises by +19.2pp, while movement on the 24 non-firing tasks does not exclude zero. Two negative controls (a self-enforcing retail domain and BFCL) bound the mechanism: gates help when tools are policy-permissive and add little where tools already self-enforce. As suggestive evidence, not a central claim, the same failure mode persists at the frontier: gpt-5.2 at default reasoning still attempts policy-violating writes, and the same suite improves success from 61.2% to 71.6% (+10.4pp; P=0.020; n=5, no replication). The contribution is a bounded evaluation and reliability result: deterministic gates do not guarantee task success, but they can deterministically prevent a known class of silent policy-violating writes at the action boundary.

Large language model (LLM) judges are often used as rewards to train policies on objectives that deterministic verifiers cannot capture. However, these rewards are often collapsed to pass/fail ({0, 1}), which reports the verdict but not how well a response met each criterion. We model each pass/fail verdict as a score on an unreported scale, compared with one cutoff. A stretch of that scale moves every score proportionally toward or away from the cutoff, but never across it, so no verdict changes. A policy is therefore free to apply any stretch without changing anything the panel reports. Under a joint-Gaussian model, a third grade adds a second threshold and removes this affine stretch ambiguity. On MATH and SciBench outputs from one seven-criterion judge, all 14 constructed criterionwise stretches were invisible after binarization but visible with three grades. At n=1{,}024, a test given both population laws had at least 96.5% power at a 1.5times stress. Retaining grades closes one blind spot created by binarization, but verdicts alone remain insufficient as some changes are still indistinguishable from genuine improvement. These include arbitrary within-grade changes and fixed-covariance, loading-aligned mean shifts -- the signature of a sycophancy-shaped lift the panel reads as competence. The shared-factor reference approximation fit MATH and SciBench but not HealthBench, delineating its empirical scope. We recommend keeping at least three grades (for example, asking the judge whether each criterion is fully, partially, or not met and rewarding {0, 0.5, 1}), and externally validating gains along the remaining direction, which no finer scale removes.

Large language models (LLMs) are entering legal workflows, yet we lack a jurisdiction-specific framework to assess their baseline competence therein. We use India's public legal examinations as a transparent proxy. Our multi-year benchmark assembles objective screens from top national and state exams and evaluates open and frontier LLMs under real-world exam conditions. To probe beyond multiple-choice questions, we also include a lawyer-graded, paired-blinded study of long-form answers from the Supreme Court's Advocate-on-Record exam. This is, to our knowledge, the first exam-grounded, India-specific yardstick for LLM court-readiness released with datasets and protocols. Our work shows that while frontier systems consistently clear historical cutoffs and often match or exceed recent top-scorer bands on objective exams, none surpasses the human topper on long-form reasoning. Grader notes converge on three reliability failure modes: procedural or format compliance, authority or citation discipline, and forum-appropriate voice and structure. These findings delineate where LLMs can assist (checks, cross-statute consistency, statute and precedent lookups) and where human leadership remains essential: forum-specific drafting and filing, procedural and relief strategy, reconciling authorities and exceptions, and ethical, accountable judgment.

Despite growing interest in using large language models (LLMs) in healthcare, current explorations do not assess the real-world utility and safety of LLMs in clinical settings. Our objective was to determine whether two LLMs can serve information needs submitted by physicians as questions to an informatics consultation service in a safe and concordant manner. Sixty six questions from an informatics consult service were submitted to GPT-3.5 and GPT-4 via simple prompts. 12 physicians assessed the LLM responses' possibility of patient harm and concordance with existing reports from an informatics consultation service. Physician assessments were summarized based on majority vote. For no questions did a majority of physicians deem either LLM response as harmful. For GPT-3.5, responses to 8 questions were concordant with the informatics consult report, 20 discordant, and 9 were unable to be assessed. There were 29 responses with no majority on "Agree", "Disagree", and "Unable to assess". For GPT-4, responses to 13 questions were concordant, 15 discordant, and 3 were unable to be assessed. There were 35 responses with no majority. Responses from both LLMs were largely devoid of overt harm, but less than 20% of the responses agreed with an answer from an informatics consultation service, responses contained hallucinated references, and physicians were divided on what constitutes harm. These results suggest that while general purpose LLMs are able to provide safe and credible responses, they often do not meet the specific information need of a given question. A definitive evaluation of the usefulness of LLMs in healthcare settings will likely require additional research on prompt engineering, calibration, and custom-tailoring of general purpose models.

Quantitative tools are increasingly appealing for decision support in healthcare, driven by the growing capabilities of advanced AI systems. However, understanding the predictive uncertainties surrounding a tool's output is crucial for decision-makers to ensure reliable and transparent decisions. In this paper, we present a case study on pulmonary nodule detection for lung cancer screening, enhancing an advanced detection model with an uncertainty quantification technique called conformal risk control (CRC). We demonstrate that prediction sets with conformal guarantees are attractive measures of predictive uncertainty in the safety-critical healthcare domain, allowing end-users to achieve arbitrary validity by trading off false positives and providing formal statistical guarantees on model performance. Among ground-truth nodules annotated by at least three radiologists, our model achieves a sensitivity that is competitive with that generally achieved by individual radiologists, with a slight increase in false positives. Furthermore, we illustrate the risks of using off-the-shelve prediction models when faced with ontological uncertainty, such as when radiologists disagree on what constitutes the ground truth on pulmonary nodules.

Existing long-horizon agent benchmarks often emphasize final task success while providing limited assessment of intermediate execution validity. Yet real-world business operations require agents to navigate extensive, potentially outdated or conflicting policies while satisfying critical constraints throughout execution. These requirements are particularly consequential in high-stakes domains such as payments, where intermediate violations can incur financial losses or regulatory consequences regardless of the final outcome. To bridge this evaluation gap, we introduce BizBench, a multi-turn benchmark grounded in real-world procedures from a leading payments company. Its executable environment integrates 789 knowledge documents and 601 discoverable business tools, with consistent policies, states, and tool behavior. The benchmark comprises 50 tasks involving resource constraints, temporal dependencies, prior commitments, and conflicting or outdated guidance. Each task is validated through reference execution, while deterministic checks assess both goal attainment and execution validity without prescribing a single solution path. Experiments reveal substantial limitations even among frontier models: Claude Opus 5 and GPT-6 Sol achieve strict success rates of only 64.0% and 61.3%, respectively. For Qwen3.8-27B, goal attainment reaches 42.0%, but strict success drops to 32.7%, demonstrating how outcome-based evaluation can mask invalid execution. Beyond success rates, DeepSeek-V4.1-Flash averages 191.3 tool calls per run, approximately 70% more than reference executions, revealing substantial execution overhead. Overall, BizBench establishes a testbed for evaluating and advancing long-horizon agents beyond task completion, toward reliable and constraint-compliant execution in complex business environments.

As code generation is increasingly delegated to AI systems, the bottleneck is shifting from writing code to supervising the systems that write it --- a shift CS-education researchers have begun to name. This shift exposes a vocabulary gap: the field asks for "human oversight" without a working distinction between the two things language does in a delegation channel --- coordinate action (cybernetic: words succeed when the world comes to match them) and coordinate understanding (epistemic: they succeed when they answer to the world and a hearer can check that they do). The failure this names is not cybernetic language but epistemic-form language doing cybernetic work: explanation-shaped output calibrated for approval rather than truth. Oversight that checks only whether an output was approved is satisfiable by rubber-stamping; oversight that holds an agent accountable requires the reasoning behind its work be retrievable and checkable. We present three delegation episodes --- illustrations, not controlled evidence --- in which epistemic engagement proved practicable while remaining auditable, one public record where a recommendation was withdrawn on its own stated terms, and one failure case illustrating oversight that requires no reasons for its discretionary choices. We propose a criterion for agentic-system governance, alongside existing technical trust properties: every consequential choice should carry the condition under which it would have gone otherwise, in a form a third party can test. Without such a condition, a third party cannot distinguish a decision from a rubber stamp. We give the criterion an operational form --- a two-part reconstruction test scoring a delegation record by whether a second reader can predict what the agent does under a perturbation --- and a deliberation-recording convention, ORRCF, that makes the condition a required component of every recorded choice.

Benchmarks are necessary for healthcare evaluation, but are not sufficient for predicting deployment performance. Our position is that the evaluation--deployment gap arises not because of poorly designed benchmarks, but from implicit assumptions about how users interact with models that cannot be surfaced from benchmarks alone. To make this precise, we propose a classification of assumptions into two categories: task, which can be tested from conversation data alone, and outcome, which requires outcome data and behavioral studies for testing. Critically, outcome assumptions depend on human behavior, something that even well-designed benchmarks cannot directly observe. To demonstrate the operationality of this framework, we retrospectively analyze a healthcare RCT as a case study and find that the gap naturally separates into task and outcome gaps of roughly equal size. To address this, we make two contributions: first, we propose BenchmarkCards, an artifact that documents assumptions, and second, we propose staged evaluation, a procedure that systematically tests assumptions and evaluates performance.

A typed decision model answers a fixed question about an input by returning a probability for each of several caller-defined options. Each option carries a short label and a written definition, which is where a developer states the rule the model should apply. Jev introduced this interface for routing, moderation and triage, open implementations followed, and the same operation occurs whenever a language model is used as a classifier by scoring label strings. We study the open implementations, whose weights we can inspect and patch, and ask whether the probability follows the definitions or the labels. A preference for the label we call option-label bias. Across four open-weight typed decision models, three ways of reading an answer from a Qwen2.5 backbone, eleven classification tasks and PolicyBench, a synthetic routing suite we introduce in which the rule appears only in the definitions, the answer is mostly the labels. Deleting every definition leaves accuracy unchanged (laya-td: 0.8559 against 0.8487), although those definitions support 0.7971 on their own, and renaming the options to A and B raises accuracy by +0.1511 [+0.1377, +0.1646]. One system, von, is unaffected, and the two code bases differ in one expression: laya writes each option as "{label}: {definition}", while von writes only the definition. Changing that expression in both directions, with no weight changed, makes all three laya checkpoints exactly invariant (+0.0000 [+0.0000, +0.0000]) and creates the effect in von, whose accuracy falls from 0.8511 to 0.2281 when a label contradicts its definition. Earlier work attributed this failure to the constrained decision head these models use in place of a text decoder; our results locate it in the prompt rendering. We give a two-call test that tells a practitioner which case applies to their model, and measure what four mitigations are worth.

AI "humanizers" rewrite machine-generated text so that detectors classify it as human-written. Public leaderboards score evasion and embedding similarity, but not whether checkable details survive. We check whether numbers, dates, person and organization names, and quoted spans survive each rewrite, using a rule-based checker validated by two AI annotators (precision 0.84-1.00, recall 0.93-0.95; no human annotation). In the October 2026 cycle of a public humanizer leaderboard, all 11 commercial tools changed or dropped at least one of these units in 35-65% of the documents that contained one. Most changes were to quoted spans; counting numbers and names alone, 10 of the 11 tools still altered at least one in 20% or more of the documents. The September 2026 cycle was similar (19-50%). An open 12B humanizer kept at least 97% of numbers and names in fact-dense U.S. federal agency text, but reworded 67-78% of the quoted spans, against its own prompt. Unit retention and detector evasion were not clearly related across tools (Spearman rho = -0.46, 95% CI -0.65 to 0.08), and the open model's four released files (two of them quantization-aware low-bit files) did not show the pre-registered monotone trade-off. On federal texts with matched human, AI-styled and humanized versions, a general-purpose decision model, Jev, asked a single zero-shot question, separated human originals from humanized rewrites with AUROC 0.864 (0.827-0.902), 0.18-0.22 higher than Binoculars, Fast-DetectGPT and the adversarially trained RADAR, while calling 24% of the human originals AI at a 0.5 threshold. On the AI-styled rewrites by 2026 models, both perplexity-based detectors scored below chance (AUROC 0.37 and 0.39), also with line breaks removed. Hypotheses, data rules and analyses were frozen before the main runs; two earlier data contacts are disclosed. We release the checker and the per-item results.

This position paper provides a critical but constructive discussion of current practices in benchmarking and evaluative practices in the field of formal reasoning and automated theorem proving. We take the position that open code, open data, and benchmarks that are complete and error-free will accelerate progress in this field. We identify practices that create barriers to contributing to this field and suggest ways to remove them. We also discuss some of the practices that might produce misleading evaluative information. We aim to create discussions that bring together people from various groups contributing to automated theorem proving, autoformalization, and informal reasoning.

Given the rapid ascent of large language models (LLMs), we study the question: (How) can large language models help in reviewing of scientific papers or proposals? We first conduct some pilot studies where we find that (i) GPT-4 outperforms other LLMs (Bard, Vicuna, Koala, Alpaca, LLaMa, Dolly, OpenAssistant, StableLM), and (ii) prompting with a specific question (e.g., to identify errors) outperforms prompting to simply write a review. With these insights, we study the use of LLMs (specifically, GPT-4) for three tasks: 1. Identifying errors: We construct 13 short computer science papers each with a deliberately inserted error, and ask the LLM to check for the correctness of these papers. We observe that the LLM finds errors in 7 of them, spanning both mathematical and conceptual errors. 2. Verifying checklists: We task the LLM to verify 16 closed-ended checklist questions in the respective sections of 15 NeurIPS 2022 papers. We find that across 119 {checklist question, paper} pairs, the LLM had an 86.6% accuracy. 3. Choosing the "better" paper: We generate 10 pairs of abstracts, deliberately designing each pair in such a way that one abstract was clearly superior than the other. The LLM, however, struggled to discern these relatively straightforward distinctions accurately, committing errors in its evaluations for 6 out of the 10 pairs. Based on these experiments, we think that LLMs have a promising use as reviewing assistants for specific reviewing tasks, but not (yet) for complete evaluations of papers or proposals.

Medical vision-language model (VLM) evaluation is sensitive to workflow design, prompting strategy, and benchmark construction, yet most studies treat these factors in isolation. We introduce a reliability stress test for chest X-ray interpretation built on two balanced datasets (a private report-backed set and a curated MIMIC subset). Three medical VLMs (CheXagent, MedGemma-4B, and MedGemma-27B) are evaluated across three prompt styles and two workflows (single-VLM and multi-agent), producing 36 configurations. We show that exact-match accuracy alone can overstate the effectiveness of conservative models that default to "Normal" predictions. Diagnostic reliability also depends heavily on model family and scale: multi-agent reasoning helps some configurations but hurts others. Building on these observations, we propose a decision-time routing framework that selectively escalates to multi-agent inference only when beneficial, improving the cost-quality trade-off over fixed workflows. Our results highlight the need for evaluation protocols that jointly consider prompt sensitivity, failure-mode diversity, and workflow choice before clinical deployment.

Imitation-learning policies for robot manipulation inherit the quality of the success labels attached to their training episodes, and those labels are usually produced by the robot's own success check. A particularly damaging error is the false success: an episode the robot logs as a success when the task outcome was actually wrong. We ask a narrow but practical question about these episodes. Once an episode has already been flagged as a success, how much of the information needed to overturn that label is present in proprioception, and how much requires vision? We build a simulated testbed on two bimanual ALOHA tasks, induce failures through environment perturbations rather than label edits, label every episode by privileged simulator state that the detector never sees, and keep only episodes the robot flagged as successful. We then compare detectors restricted to proprioception against a vision-based detector. We find that recoverability spans a wide range: in cube transfer the false successes are almost fully recoverable from joint data alone, while in peg insertion proprioception recovers only part of them and a vision detector closes most of the gap. We also show that the proprioceptive separability we measure rests on velocity differences far below any realistic sensor noise floor, so it is best read as an optimistic upper bound that a noiseless simulator inflates. We release the generation and evaluation pipeline.

LLM agents are judged by what they deliver, and in professional work what gets delivered is a project, not a task. A project pays off only if the whole package holds, and one weak part can limit the value of the rest. Yet existing benchmarks mostly test agents on one task at a time, leaving a gap between the capability we measure and the outcome that makes agents useful. To address this gap, we introduce DeliverBench, which tests whether agents can carry a project from brief to final delivery. Its 11 projects, spanning financial due diligence, legal contract drafting, and drug safety reporting, are reconstructed with 13 domain experts from real materials and chain 150 subtasks through 2-15 rounds of new materials and client feedback. Because no reference outputs are injected, agents inherit their own errors from one task to the next. Expert rubrics then score every checkpoint as well as the final package. Across seven model-harness systems, even the best system scores only 65.0 out of 100 on final delivery and passes 50.0% of subtasks at a 90-point threshold. The failures are often failures of carrying work forward: in one audit project, all seven systems addressed the review findings, but only one preserved traceability. Together, these results suggest that task-level capability does not simply compose into delivery, which also depends on keeping the work coherent as it evolves.

We present PopResume, a population-representative resume dataset for causal fairness auditing of LLM- and VLM-based resume screening systems. Unlike existing benchmarks that rely on manually injected demographic information and outcome-level disparities, PopResume is grounded in population statistics and preserves natural attribute relationships, enabling path-specific effect (PSE)-based fairness evaluation. We decompose the effect of a protected attribute on resume scores into two paths: the business necessity path, mediated by job-relevant qualifications, and the redlining path, mediated by demographic proxies. This distinction allows auditors to separate legally permissible from impermissible sources of disparity. Evaluating four LLMs and four VLMs on PopResume's 60.8K resumes across five occupations, we identify five representative discrimination patterns that aggregate metrics fail to capture. Our results demonstrate that PSE-based evaluation reveals fairness issues masked by outcome-level measures, underscoring the need for causally-grounded auditing frameworks in AI-assisted hiring.

We introduce RoboEval, a structured evaluation framework and benchmark for robotic manipulation that augments binary success with principled behavioral and outcome metrics. Existing evaluations often collapse performance into outcome counts, masking differences in execution quality and obscuring failure structure. RoboEval provides eight bimanual tasks with systematically controlled variations, more than three thousand expert demonstrations, and a modular simulation platform for reproducible experimentation. All tasks are instrumented with standardized metrics that quantify efficiency, coordination, and safety/stability, as well as outcome measures that trace stagewise progress and localize failure modes. Through extensive experiments with state-of-the-art visuomotor policies, we validate these metrics by analyzing their stability under variation, discriminative power across policies with similar success rates, and correlation with task success. Project Page: https://robo-eval.github.io

In recent years, large language models have greatly improved in their ability to perform complex multi-step reasoning. However, even state-of-the-art models still regularly produce logical mistakes. To train more reliable models, we can turn either to outcome supervision, which provides feedback for a final result, or process supervision, which provides feedback for each intermediate reasoning step. Given the importance of training reliable models, and given the high cost of human feedback, it is important to carefully compare the both methods. Recent work has already begun this comparison, but many questions still remain. We conduct our own investigation, finding that process supervision significantly outperforms outcome supervision for training models to solve problems from the challenging MATH dataset. Our process-supervised model solves 78% of problems from a representative subset of the MATH test set. Additionally, we show that active learning significantly improves the efficacy of process supervision. To support related research, we also release PRM800K, the complete dataset of 800,000 step-level human feedback labels used to train our best reward model.

After a runtime or API migration, an LLM-repaired procedure can run cleanly yet return wrong results, and a release check on typical test inputs ships it. We report a preregistered study of 73 tasks covering 60 documented changes in CPython, Node.js and SQLite. Every candidate is executed on the real runtimes against withheld contracts. Over the complete repair space, the all-assertions gate on typical inputs released 0.410 of wrong repairs. One edge input written from the release note cut this to 0.065, and to 0.061 on 15 unseen clusters. Three inputs from a blind GPT-5.6-luna writer that never saw the program reached 0.070. Two further frozen stages enlarged the menu to 1491 fragments and then added 233 hard distractors that match the legacy output on typical inputs. The edge input (0.058) and the frontier-model writer (0.058) passed their preregistered tests. Yet 0.168 and 0.153 of the hard wrong programs still passed. Two local-model writers failed their preregistered tests. Across four model families, the edge input cut wrong releases per attempt in all three open-weight families on all three menus, for example from 0.233 to 0.057, without lowering correct completion. Self-tests helped less. A blind AI audit flagged 34 contracts as stricter than their requirements. Dropping the disputed checks changed 0 verdicts, but class-label disputes remain open. No model-written code was executed. Artifacts are available from the authors on request.

We introduce self-invoking code generation, a new task designed to evaluate the progressive reasoning and problem-solving capabilities of LLMs. In this task, models are presented with a base problem and a related, more complex problem. They must solve the base problem and then utilize its solution to address the more complex one. This work features three key contributions. First, we propose a general recipe for generating more challenging versions of existing benchmarks, resulting in three new benchmarks: HumanEval Pro, MBPP Pro, and BigCodeBench-Lite Pro, specifically designed to assess LLMs on self-invoking code generation. Second, from the analysis of experimental results over twenty LLMs on our benchmarks, we have two important observations: (i) Most LLMs excel in traditional code generation benchmarks like HumanEval and MBPP, but their performance declines on self-invoking tasks. For example, o1-mini achieves 96.2% pass@1 on HumanEval but only 76.2% on HumanEval Pro. (ii) On self-invoking code generation task, the instruction-tuned models demonstrate only marginal improvements compared to the base models. Third, we disclose the types of failure modes that exist in our evaluation results. All these results underscore the need for further advancements in self-invoking code generation tasks and provide a new direction for future research on enhancing LLMs' code reasoning capabilities.

We present a foundation model-derived method to identify highly informative tokens and events in electronic health records. Our approach considers incoming data in the entire context of a patient's hospitalization and so can flag anomalous events that rule-based approaches would consider within a normal range. We demonstrate that the events our model flags are significant for predicting downstream patient outcomes and that a fraction of events identified as carrying little information can safely be dropped. Additionally, we show how informativeness can help interpret the predictions of prognostic models trained on foundation model-derived representations.

AI scientist systems, capable of autonomously executing the full research workflow from hypothesis generation and experimentation to paper writing, hold significant potential for accelerating scientific discovery. However, the internal workflow of these systems have not been closely examined. This lack of scrutiny poses a risk of introducing flaws that could undermine the integrity, reliability, and trustworthiness of their research outputs. In this paper, we identify four potential failure modes in contemporary AI scientist systems: inappropriate benchmark selection, data leakage, metric misuse, and post-hoc selection bias. To examine these risks, we design controlled experiments that isolate each failure mode while addressing challenges unique to evaluating AI scientist systems. Our assessment of two prominent open-source AI scientist systems reveals the presence of several failures, across a spectrum of severity, which can be easily overlooked in practice. Finally, we demonstrate that access to trace logs and code from the full automated workflow enables far more effective detection of such failures than examining the final paper alone. We thus recommend journals and conferences evaluating AI-generated research to mandate submission of these artifacts alongside the paper to ensure transparency, accountability, and reproducibility.