new

Get trending papers in your email inbox!

Subscribe

Daily Papers

byAK and the research community

Nov 16

The Alien Space of Science: Sampling Coherent but Cognitively Unavailable Research Directions

Scientific discovery is constrained not only by what is true, but by what is cognitively available to researchers. Many directions are coherent in light of the literature yet unlikely to be proposed because no existing community combines the relevant concepts, methods, and intuitions. Modern language models inherit this bias, recombining high-density regions of the literature when prompted for novel ideas. We target the complementary region, the alien space of science: directions that are scientifically plausible but unlikely under the distribution of existing researchers. Our method decomposes papers into conceptual units and clusters them into a vocabulary of idea atoms. A coherence model scores whether atom combinations form viable research directions, while an availability model scores whether any existing author community is positioned to produce them. We rank combinations to maximize coherence while minimizing availability. On 16,068 peer-reviewed LLM papers from NeurIPS, ICLR, ICML, and major NLP venues, the sampler produces more diverse research portfolios than frontier LLM baselines, including batch-prompted variants that see their entire output, while matching or exceeding their per-idea quality under blind human, LLM, and downstream experimental evaluation. In temporal validation, all components use only pre-2025 data. Selecting less than 1% of the candidate space recovers 2025 combinations at 35.9 times chance; weighting unavailability increases recovery of strictly novel combinations to 3.24 times chance. By separating scientific plausibility from community availability, our framework points toward AI ideation that complements rather than merely accelerates human science, expanding exploration into coherent directions the community may overlook.

  • 9 authors
·
Oct 20

CyberArena: Benchmarking AI Agents in Live Symmetric Attack-and-Defense Combat

AI agents are demonstrating increasingly strong offensive and defensive cybersecurity capabilities in the real world. Current benchmarks mostly evaluate agents in isolation against static targets. Real cyber operations, however, are dynamic and coupled: security postures constantly change as attackers and defenders adapt to each other in real time. Static benchmarks quickly saturate and miss an agent's ability to attack and defend simultaneously under live pressure. To address this gap, we present CyberArena, a dynamic, symmetric adversarial benchmark built around multi-round attack-and-defense combat. In isolated sandboxes, two agents compete under identical rules, acting concurrently as both attackers and defenders over continuously changing services. This converts static targets into evolving, semi-open challenges, directly testing an agent's speed and precision in discovering, exploiting, and patching vulnerabilities. To sustain the benchmark's longevity, an automated agentic pipeline continuously generates, reviews, and validates new environments. Furthermore, because pairwise contests are notoriously hard to quantify, we introduce a dynamical model that maps match dynamics into unified, multidimensional scores across offensive, defensive, and domain-specific capabilities. Evaluating 12 frontier LLM agents across 40 challenges in 466 matches, CyberArena separates model capabilities where single-agent baselines hit a ceiling. The trajectories read like a fight rather than an exam: defenders patch one hole and miss the next and certify repairs on stale evidence, while capable agents think a move ahead, planting backdoors for later rounds and, in one case, writing their own packet sniffer to watch the opponent. Beyond a benchmark, CyberArena serves as an adaptable, scalable experimental platform for future research on cybersecurity agents.

2077AIDataFoundation 2077AI
·
Oct 13 2

Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling

AI agents negotiate and transact in natural language with unfamiliar counterparts: a buyer bot facing an unknown seller, or a procurement assistant negotiating with a supplier. In such interactions, the counterpart's LLM, prompts, control logic, and rule-based fallbacks are hidden, while each decision can have monetary consequences. We ask whether an agent can predict an unfamiliar counterpart's next decision from a few interactions. To avoid real-world logging confounds, we study this problem in controlled bargaining and negotiation games, formulating it as target-adaptive text-tabular prediction: each decision point is a table row combining structured game state, offer history, and dialogue, while K previous games of the same target agent, i.e., the counterpart being modeled, are provided in the prompt as labeled adaptation examples. Our model is built on a tabular foundation model that represents rows using game-state features and LLM-based text representations, and adds LLM-as-Observer as an additional representation: a small frozen LLM reads the decision-time state and dialogue; its answer is discarded, and its hidden state becomes a decision-oriented feature, making the LLM an encoder rather than a direct few-shot predictor. Training on 13 frontier-LLM agents and testing on 91 held-out scaffolded agents, the full model outperforms direct LLM-as-Predictor prompting and game+text features baselines. Within this tabular model, Observer features contribute beyond the other feature schemes: at K=16, they improve response-prediction AUC by about 4 points across both tasks and reduce bargaining offer-prediction error by 14%. These results show that formulating counterpart prediction as a target-adaptive text-tabular task enables effective adaptation, and that hidden LLM representations expose decision-relevant signals that direct prompting does not surface.

Long-Context Aware Upcycling: A New Frontier for Hybrid LLM Scaling

Hybrid sequence models that combine efficient Transformer components with linear sequence modeling blocks are a promising alternative to pure Transformers, but most are still pretrained from scratch and therefore fail to reuse existing Transformer checkpoints. We study upcycling as a practical path to convert pretrained Transformer LLMs into hybrid architectures while preserving short-context quality and improving long-context capability. We call our solution HyLo (HYbrid LOng-context): a long-context upcycling recipe that combines architectural adaptation with efficient Transformer blocks, Multi-Head Latent Attention (MLA), and linear blocks (Mamba2 or Gated DeltaNet), together with staged long-context training and teacher-guided distillation for stable optimization. HyLo extends usable context length by up to 32times through efficient post-training and reduces KV-cache memory by more than 90%, enabling up to 2M-token prefill and decoding in our vLLM inference stack, while comparable Llama baselines run out of memory beyond 64K context. Across 1B- and 3B-scale settings (Llama- and Qwen-based variants), HyLo delivers consistently strong short- and long-context performance and significantly outperforms state-of-the-art upcycled hybrid baselines on long-context evaluations such as RULER. Notably, at similar scale, HyLo-Qwen-1.7B trained on only 10B tokens significantly outperforms JetNemotron (trained on 400B tokens) on GSM8K, Lm-Harness common sense reasoning and RULER-64K.

  • 10 authors
·
Apr 26

Memory-Induced Tool-Drift in LLM Agents

Modern LLM agents combine long-term memory for personalization with tool-calling interfaces for taking actions in the world -- a combination underpinning contemporary production systems. We study a previously unexamined failure of this combination: when personality-driven biases stored in memory (cost-consciousness, impatience, risk tolerance, etc.) silently affect tool calls in contexts where they are not applicable. We call this memory-induced tool-drift and operationalize it through MEMDRIFT, a benchmark of 105 scenarios spanning five bias dimensions and seven professional domains, generated through an automated adversarial pipeline. Across seven frontier models -- including those with extended reasoning -- biased memories raise deflection scores (a judge-scored measure of parameter deviation from unbiased baselines) by up to +3.6 points on a 1--5 scale. Tool-drift persists when memory management is handled by three production memory architectures. The phenomenon affects real-world tools: scanning 6{,}062 tools across 288 verified MCP servers, we flag 608 with susceptible parameters and confirm tool-drift on a validated subset. Mechanistically, biased memories act as implicit steering vectors, pushing activations along the same latent directions as explicit behavioral instructions. They also redistribute attention from task-relevant context toward memory entries with surface-level keyword overlap to the target parameter. Standard defenses -- prompt-based relevance instructions and memory filters -- reduce drift but do not eliminate it. As agents take increasingly consequential actions on a user's behalf, memory-induced tool-drift represents a systematic vulnerability that current safeguards do not address, motivating dedicated defenses at the intersection of memory management and tool-call generation.

  • 4 authors
·
May 23

Superintelligent Retrieval Agent: The Next Frontier of Information Retrieval

Retrieval-augmented agents are increasingly the interface to large organizational knowledge bases, yet most still treat retrieval as a black box: they issue exploratory queries, inspect returned snippets, and iteratively reformulate until useful evidence emerges. This approach resembles how a newcomer searches an unfamiliar database rather than how an expert navigates it with strong priors about terminology and likely evidence, and results in unnecessary retrieval rounds, increased latency, and poor recall. We introduce SuperIntelligent Retrieval Agent (SIRA), which defines superintelligence in retrieval as the ability to compress multi-round exploratory search into a single corpus-discriminative retrieval action. SIRA does not merely ask what terms are relevant to the query; it asks which terms are likely to separate the desired evidence from corpus-level confusers. On the corpus side, an LLM enriches each document offline with missing search vocabulary; on the query side, it predicts evidence vocabulary omitted by the query; and document-frequency statistics as a tool call to filter proposed terms that are absent, overly common, or unlikely to create retrieval margin. The final retrieval step is a single weighted BM25 call combining the original query with the validated expansion. Across ten BEIR benchmarks and downstream question-answering tasks, SIRA achieves the significantly superior performance outperforming dense retrievers and state-of-the-art multi-round agentic baselines, demonstrating that one well-formed lexical query, guided by LLM cognition and lightweight corpus statistics, can exceed substantially more expensive multi-round search while remaining interpretable, training-free, and efficient.

  • 4 authors
·
May 6

SpreadsheetBench 2: Evaluating Agents on End-to-End Business Spreadsheet Workflows

Spreadsheets are widely used for business analysis, financial modeling, reporting, and decision-making. However, most existing spreadsheet benchmarks evaluate isolated operations such as single-formula generation or local cell edits, and therefore fail to capture end-to-end workflows in realistic business settings. We introduce SpreadsheetBench 2, a workflow-level benchmark for spreadsheet agents that covers three task categories: generation, debugging, and visualization. The benchmark is constructed from authentic business data, including financial reports and corporate filings, and is annotated and validated by domain experts. The benchmark contains 321 tasks; each instance averages 11.8 worksheets and requires 593.5 cell modifications, reflecting large multi-sheet workbooks with cross-sheet dependencies. We evaluate eight frontier large language models under a unified multi-turn agent scaffold, and additionally include several LLM-based spreadsheet products as complementary baselines. Results show that current systems remain far from reliable on real-world workflows: the best model achieves 34.89\% overall task accuracy, and debugging accuracy is as low as 12.00\%. Trajectory analysis and a failure taxonomy further indicate that insufficient spreadsheet inspection and incorrect target-cell selection are the dominant bottlenecks. Together, these findings position SpreadsheetBench 2 as a challenging testbed for advancing reliable spreadsheet automation. Project page: https://spreadsheetbench.github.io/

  • 14 authors
·
Jun 28

Cost-Efficient Theorem Proving via Agent Orchestration in Program Verification

Program verification establishes software correctness through machine-checkable proofs constructed in theorem provers. It's a guarantee especially valuable for code generated by large language models (LLMs), which is fluent but carries no assurance of correctness. Almost all existing provers, however, pursue pass rates alone at whatever sampling or search budget it takes, and overlook the success-vs-cost frontier; yet real software often carries hundreds of interdependent proof obligations, so what matters at scale is not whether one theorem can be proved, but how many can be proved economically. We introduce CoCo-Prover, which formalizes cost-efficient program proving as metalevel decision-making under cost, grounded on two-level proof graphs: an AND/OR proof hypergraph within each declaration is joined to a lemma-dependency graph across declarations; and at each step, it answers two questions: which open goals to select, and which actions to purchase on these goals. Selection stays symbolic as a topological pass over the proof graphs. Action choice is agent orchestration via metalevel decision-making: an agentic router treats every bounded specialist invocation as a separately priced, best-effort computation, matching heterogeneous specialist agents together with configurations, under evolved routing rules as evidence accumulates. On five program verification benchmarks in Lean 4 including function-level CLEVER, VERINA, and AlgoVeri, and repository-level NTP4VC and Vero, we show that CoCo-Prover achieves a better success-vs-cost frontier than baselines including frontier coding agents and state-of-the-art LLM-based provers: it achieves the best solve rate on every benchmark and up to 100% on two benchmarks. It also reduces cost by up to 30.9% compared to the strongest baseline with the strongest LLM in our evaluation.

  • 6 authors
·
Oct 6

Calibrated Trust, Not Sharper Prediction: An Empirical Test of Uncertainty Fusion

A recurring proposal in legal AI is to improve case-outcome prediction by fusing uncertainty tools (evidence graphs with belief propagation, sequential Bayesian odds updating, Dempster-Shafer combination, and conformal prediction) into one pipeline. We test this on 1,000 real European Court of Human Rights cases from LexGLUE and FairLex, predicting whether the Court found a Convention violation from the case's fact paragraphs. We compare three families across two frontier LLMs (Claude Opus 4.8 and GPT-5.5) as per-fact evidence estimators: (A) the raw LLM, (B) the LLM routed through the fusion pipeline, and (C) a term-frequency baseline through the same pipeline. Across roughly 4,750 tests we find: (1) on discrimination (AUROC around 0.83) the pipeline yields no improvement over either the raw LLM or the baseline; a frontier LLM used directly is the strongest single discriminator. (2) Naively composing an LLM with Bayesian-odds and Dempster-Shafer fusion more than doubles calibration error (ECE from about 0.16 to 0.46) via a prior-mismatch mechanism that replicates across both models. (3) Dempster-Shafer fusion is actively unsafe on long chains, committing confidently to wrong labels at below-chance accuracy; we recommend removing it. (4) The pipeline's genuine value is operational: routed through a conformal selective-prediction layer, the system decides which cases to automate and which to escalate. After removing Dempster-Shafer, recalibrating, and applying class-conditional risk control on the full 1,000-case set, the tuned engine auto-clears at 96.8 percent accuracy with 0.5 percent errors escaping and 96.3 percent caught for review, versus 85.9 / 3.8 / 72.1 for an untuned baseline. The contribution of such pipelines in law is calibrated trust, not sharper prediction.

  • 1 authors
·
Jul 10

Personal Salience: Highlighting Is Social, but Individuality Lives in Selection

Social highlighters let people mark passages that matter to them. We ask how much of an individual is recoverable from these naturalistic traces, using a co-readership identity control (the same document highlighted by many users) that holds document and topic fixed and asks whether a person's own history predicts their marks better than another reader's does. We separate generic salience (structure), crowd salience (what others marked), and personal salience (the individual residual). First, highlighting is social: which sentences you mark is predicted far better by the crowd than by structure or by a personal model, and even a well-estimated crowd, an information-privileged baseline that sees others' marks on the same document, beats a frontier LLM twin built from your other-document history; the within-document personal signal is at most a whisper (own-vs-other gap +0.017 by an embedding scorer, small but significant). Second, in sharp contrast, individuality lives in selection: asked which of the already-salient passages are yours, your own history is a strong, leakage-free predictor (gap +0.14). A topic decomposition shows this is largely stable thematic preference: it shrinks ~6-8x against a topically-matched peer, and a thin residual cannot be separated from finer topic. The non-obvious part is an asymmetry: under the same scorer the individual signal is ~6-8x weaker in salience than in selection. Methodologically, naive history-conditioning evaluations leak (the target's own marks enter the profile in ~42% of pairs, inflating personal scores by up to +0.15 AP) and small crowds overstate personalization; our results are leakage-free, use a dense crowd, and a model-matched control. Highlights carry a genuine individual signature, but a thin layer over a strong shared one, surfacing far more in which salient things a person selects than in what is salient.

  • 2 authors
·
Jun 7 1

DRYLAB-Bench: Benchmarking the Biosecurity Risk of Agentic LLM Mutation Design

As large language models (LLMs) acquire advanced biological design capabilities, they offer substantial research benefits but simultaneously introduce severe dual-use risks, such as engineering enhanced pathogens or drug-resistant bacteria. While biosecurity frameworks recognize these threats, the actual risk of LLMs executing dangerous biological modifications remains unquantified, particularly when augmented with specialized biological design tools (BDTs). Existing evaluations primarily assess hazardous knowledge possession rather than practical application, overlook risk amplification from BDTs, and rely on unreliable, expensive, or hazardous validation methods. To address these gaps, we introduce DRYLAB-Bench (Design Risk Yielded by LLM Agent in Biodesign), the first comprehensive benchmark evaluating the high-risk biological mutation design capabilities of LLM agents. Moving beyond basic question-answering, DRYLAB-Bench tasks agents with 30 genuinely hazardous mutation-design scenarios distilled from biosecurity guidelines. It evaluates models in a multi-round, tool-augmented environment where LLMs orchestrate BDTs to iteratively refine candidates. Crucially, it scores designs directly against 187,695 empirical wet-lab measurements from ProteinGym and ViroGym using our proposed Biosecurity Risk Score (BRS), quantifying risk-associated effects while enabling scalable and safe ground-truth verification. Evaluations of 15 frontier models reveal substantial baseline threats: without tools, 67.6% of one-shot designs exceed the average measured variant, and 21.4% reach the highest-risk decile. Equipping models with BDTs significantly amplifies this risk, raising the pooled risk by \(ΔBRS=+0.116\) and the top-decile share to 23.5%. Code: https://github.com/drylab-bio/DRYLAB-Bench

  • 9 authors
·
Oct 8

InferenceBench: A Benchmark for Open-Ended LLM Inference Optimization by AI Agents

AI agents are increasingly used to automate research and development tasks, yet existing benchmarks typically evaluate them on prescribed workflows or narrow action spaces. Even nominally open-ended tasks can often be solved by retrieving a well-known recipe and tuning a few hyperparameters, making it unclear whether strong results reflect genuine optimization or memorized solutions. We introduce InferenceBench, where an agent must deploy an OpenAI-compatible inference server and optimize the speed of LLM inference. Each agent receives a target LLM, one H100 GPU, an optimization scenario, and a wall-clock time budget of two hours. Three optimization scenarios isolate distinct bottlenecks of inference (prefill latency, decode latency, and concurrent request throughput) and a fourth balances all three at the same time. Across 15 frontier agent configurations, agents reliably improve over a naive PyTorch baseline (up to 8.08times) and often match or exceed serving engines with default settings (4.05times for vLLM), but still fall below a simple hyperparameter search under the same time budget (up to 11.53times). Qualitative analysis of agent trajectories shows that although agents enumerate many relevant optimization techniques, they overwhelmingly converge on a single inference framework. They test only a few distinct configurations and spend the remaining budget re-measuring, repairing, or optimizing hyperparameters rather than exploring substantially different strategies. This suggests the bottleneck is not domain knowledge, but the ability to propose diverse configurations, evaluate them systematically, and submit the best identified solution. Overall, InferenceBench reflects the ability of agents to operate in an open-ended AI engineering setting, where memorized solutions lead to limited improvements.

  • 3 authors
·
May 19

Agent-Editing World Model: Rethinking World Modeling for LLM Agents

Recent advances in large language models (LLMs) have enabled agents to tackle long-horizon tasks across diverse environments. To further improve agent performance, existing language world models typically predict environment observations, yet reconstructing high-entropy, execution-dependent tool responses offers limited value when real feedback is available. Meanwhile, agents suffer from task-state contamination, where unsupported assumptions and outdated plans persist in history and distort subsequent decisions. We propose the Agent-Editing World Model (AEWM), which models how reasoning and actions shape future task progress rather than simulating tool responses. AEWM combines Action Judge to distinguish Critical, Exploratory, and Noisy decisions with State Revision to edit noisy reasoning--action continuations from the same observed history. EditAct integrates these capabilities with real execution, directly changing the state underlying subsequent decisions rather than merely providing critiques. We train AEWM across Search, Terminal, and Software Engineering through mid-training and supervised fine-tuning. AEWM achieves 70.5\% macro-F1 on our Action Judge benchmark, exceeding the strongest frontier baseline by 10.6 points. Across six benchmarks and three agent backbones, EditAct improves average scores by 3.2--6.7 points over the strongest baseline. Furthermore, rejection sampling fine-tuning on verified EditAct trajectories, termed AEWM-RFT, improves over Self-RFT by 2.2--2.6 points across three domains without online AEWM guidance.

MemPilot: Orchestrating On-Demand Multimodal Memory Curation for LLM Agents

Memory has become integral to the LLM agent ecosystem, supporting information retention and reuse across interactions. However, most existing agent memory systems construct memory in a query-agnostic manner, which can incur unnecessary preprocessing cost and discard details that later prove essential. Recent studies have begun shifting memory processing toward runtime adaptation, but typically specialize in particular operations or fixed processing schemes, leaving flexible control over performance, cost, and latency largely underexplored. To address this challenge, we present MemPilot, a flexible framework that orchestrates on-demand memory curation under different performance--cost--latency preferences. Specifically, we optimize a multi-step LLM policy via reinforcement learning to iteratively choose between retrieving from query-agnostic memory and delegating query-specific curation of raw multimodal history to heterogeneous LLMs and VLMs. The policy jointly controls evidence amount, curation instructions, model selection, and visual access, enabling fine-grained allocation of runtime computation. To optimize this policy under competing objectives, we adapt objective-wise advantage decoupling by separately estimating each objective's advantage before aggregation. Moreover, we introduce prefix-based marginal utility estimation for fine-grained credit assignment across multi-step rollouts. Experiments on five multimodal agent-memory benchmarks demonstrate favorable performance--cost--latency trade-offs across optimization preferences, with preference sweeps yielding broader frontiers than existing trade-off-aware baselines.

OrgForge-IT: A Verifiable Synthetic Benchmark for LLM-Based Insider Threat Detection

Synthetic insider threat benchmarks face a consistency problem: corpora generated without an external factual constraint cannot rule out cross-artifact contradictions. The CERT dataset -- the field's canonical benchmark -- is also static, lacks cross-surface correlation scenarios, and predates the LLM era. We present OrgForge-IT, a verifiable synthetic benchmark in which a deterministic simulation engine maintains ground truth and language models generate only surface prose, making cross-artifact consistency an architectural guarantee. The corpus spans 51 simulated days, 2,904 telemetry records at a 96.4% noise rate, and four detection scenarios designed to defeat single-surface and single-day triage strategies across three threat classes and eight injectable behaviors. A ten-model leaderboard reveals several findings: (1) triage and verdict accuracy dissociate - eight models achieve identical triage F1=0.80 yet split between verdict F1=1.0 and 0.80; (2) baseline false-positive rate is a necessary companion to verdict F1, with models at identical verdict accuracy differing by two orders of magnitude on triage noise; (3) victim attribution in the vishing scenario separates tiers - Tier A models exonerate the compromised account holder while Tier B models detect the attack but misclassify the victim; (4) rigid multi-signal thresholds structurally exclude single-surface negligent insiders, demonstrating the necessity of parallel, threat-class-specific triage pipelines; and (5) agentic software-engineering training acts as a force multiplier for multi-day temporal correlation, but only when paired with frontier-level parameter scale. Finally, prompt sensitivity analysis reveals that unstructured prompts induce vocabulary hallucination, motivating a two-track scoring framework separating prompt adherence from reasoning capability. OrgForge-IT is open source under the MIT license.

  • 1 authors
·
Mar 23

Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security

LLM-based agents process external content, exposing them to prompt injection and multi-turn manipulation. Most safety benchmarks evaluate defenders against fixed attack pools collected before evaluation, single-turn or multi-turn. We present a 21-scenario benchmark for adaptive multi-round attacks against memoryless LLM defenders: an autonomous LLM attacker observes prior defender responses and pivots across rounds, while each defender response is evaluated as a fresh interaction. Holding the 21 scenarios, attackers, defenders, and structured-output scoring fixed, restricting scoring to the first attacker turn yields 0-1% attack success rate (ASR); allowing 15 rounds of adaptive attack yields 5.4-14.0%. Pooling three frontier attacker LLMs uncovers 1.4-2.2times as many unique successful attacks as the best single attacker, and the generated attacks have low cosine similarity (0.02-0.14) to attacks in existing benchmarks. Claude Opus 4.6 and GPT-5.4 are tied in aggregate (5.4% each; overlapping 95% CIs), but their weaknesses differ sharply: on one scenario Opus reaches 60% ASR (95% CI 36--80%) while GPT-5.4 and Gemini each stay at 7% (CI 1-30%; the gap is preserved in a higher-N replication). 13 of 21 scenarios distinguish at least one defender pair, yet rankings disagree across scenarios (Kendall's W = 0.19). We release the benchmark -- 21 evaluation scenarios, 10 public development scenarios, the orchestrator, baseline harnesses, and a multi-attacker CLI -- plus 945 transcripts from the 3times3 frontier matrix, an attack-replay dataset, and 18{,}422 gpt-oss-20b battles from an open competition's final scoring rounds.

  • 3 authors
·
Jul 19

WINA: Weight Informed Neuron Activation for Accelerating Large Language Model Inference

The growing computational demands of large language models (LLMs) make efficient inference and activation strategies increasingly critical. While recent approaches, such as Mixture-of-Experts (MoE), leverage selective activation but require specialized training, training-free sparse activation methods offer broader applicability and superior resource efficiency through their plug-and-play design. However, many existing methods rely solely on hidden state magnitudes to determine activation, resulting in high approximation errors and suboptimal inference accuracy. To address these limitations, we propose WINA (Weight Informed Neuron Activation), a novel, simple, and training-free sparse activation framework that jointly considers hidden state magnitudes and the column-wise ell_2-norms of weight matrices. We show that this leads to a sparsification strategy that obtains optimal approximation error bounds with theoretical guarantees tighter than existing techniques. Empirically, WINA also outperforms state-of-the-art methods (e.g., TEAL) by up to 2.94% in average performance at the same sparsity levels, across a diverse set of LLM architectures and datasets. These results position WINA as a new performance frontier for training-free sparse activation in LLM inference, advancing training-free sparse activation methods and setting a robust baseline for efficient inference. The source code is available at https://github.com/microsoft/wina.

  • 7 authors
·
May 25, 2025 2

MacroLens: A Multi-Task Benchmark for Contextual Financial Reasoning under Macroeconomic Scenarios

Financial decision-making is contextual: forecasting prices, valuing companies, and assessing event exposure weigh price history, accounting fundamentals, macroeconomic regime, and contemporaneous text. A benchmark over these four signals is hard to build because finance violates four assumptions of time-series evaluation: text must be gated by its publication date to prevent look-ahead, quarterly fundamentals are reported with a one- to ninety-day lag, filing text is partly redundant with the numerical statement fields it accompanies, and macroeconomic regimes leak across calendar splits. No public benchmark addresses all four signals jointly. MacroLens covers 4,416 U.S. small- and micro-cap equities over 2021-2026. Seven tasks share one point-in-time panel of prices, 46.8M XBRL accounting facts, 53 macroeconomic series, 295,860 SEC filings, and 215,882 news articles, plus a scenario layer of 1,130 macroeconomic events across 49 types automatically detected and rendered as natural language. Tasks span contextual forecasting, public and private valuation, statement generation from fundamentals and descriptions, scenario-conditioned returns, and real-estate valuation. We evaluate 19 methods across six families spanning naive heuristics through time-series foundation models, fine-tuned LLM-based time-series models, and zero-shot large language models (LLMs), plus a five-step feature-context ablation on two frontier LLMs and a gradient-boosted baseline. MacroLens is released at https://huggingface.co/datasets/DeepAuto-AI/MacroLens.

  • 5 authors
·
Jun 22

Binding Drift in Multi-Step Tool-Augmented Agents

Tool-augmented language-model agents execute multi-step workflows over external systems, resolving an entity once and then acting on it across subsequent steps. Prior work shows that in single-step actions, agents select the correct tool but bind it to the wrong entity 24-26% of the time. We study what happens to entity bindings over time: do they stay correct, silently drift to a different entity, or, if wrong from the start, propagate and compound? We formalize binding drift (correct at step 1, wrong later) as distinct from error propagation (wrong at step 1, carried forward), and score them on disjoint workflow sets so the two cannot be conflated. In a controlled multi-step testbed (200 workflows, 580 entity-binding-scored steps, four enterprise domains, eight model backends spanning small to frontier), we find: (1) under controlled error injection, an entity lock (the intuitive "persist the first binding" fix) amplifies wrong actions from 907 to 2,746 (3.0x; bootstrap 95% CI [2.8, 3.3]), because it faithfully carries the seeded wrong entity into every later step; (2) the amplification reaches 8.5x on the most affected model (Claude Opus 4.5); (3) a practical LLM-based re-verifier (a single cheap second model call re-reading the original instruction) reduces wrong actions by 79% (0.21x; CI [0.18, 0.25]), closing the gap to within 1 percentage point of an oracle upper-bound (0.20x); and (4) in the natural (non-injected) setting, baseline agents drift on 18% of eligible workflows, with the per-step error rate rising across steps. Persistence and re-verification are not interchangeable: a defense that eliminates drift can worsen propagation, and a practical re-verifier nearly matches oracle recovery.

  • 2 authors
·
Jul 16

CulturalTeaming: AI-Assisted Interactive Red-Teaming for Challenging LLMs' (Lack of) Multicultural Knowledge

Frontier large language models (LLMs) are developed by researchers and practitioners with skewed cultural backgrounds and on datasets with skewed sources. However, LLMs' (lack of) multicultural knowledge cannot be effectively assessed with current methods for developing benchmarks. Existing multicultural evaluations primarily rely on expensive and restricted human annotations or potentially outdated internet resources. Thus, they struggle to capture the intricacy, dynamics, and diversity of cultural norms. LLM-generated benchmarks are promising, yet risk propagating the same biases they are meant to measure. To synergize the creativity and expert cultural knowledge of human annotators and the scalability and standardizability of LLM-based automation, we introduce CulturalTeaming, an interactive red-teaming system that leverages human-AI collaboration to build truly challenging evaluation dataset for assessing the multicultural knowledge of LLMs, while improving annotators' capabilities and experiences. Our study reveals that CulturalTeaming's various modes of AI assistance support annotators in creating cultural questions, that modern LLMs fail at, in a gamified manner. Importantly, the increased level of AI assistance (e.g., LLM-generated revision hints) empowers users to create more difficult questions with enhanced perceived creativity of themselves, shedding light on the promises of involving heavier AI assistance in modern evaluation dataset creation procedures. Through a series of 1-hour workshop sessions, we gather CULTURALBENCH-V0.1, a compact yet high-quality evaluation dataset with users' red-teaming attempts, that different families of modern LLMs perform with accuracy ranging from 37.7% to 72.2%, revealing a notable gap in LLMs' multicultural proficiency.

  • 10 authors
·
Apr 9, 2024

DiagnosticIQ: A Benchmark for LLM-Based Industrial Maintenance Action Recommendation from Symbolic Rules

Monitoring complex industrial assets relies on engineer-authored symbolic rules that trigger based on sensor conditions and prompt technicians to perform corrective actions. The bottleneck is not detection but response: translating rules into maintenance steps requires asset-specific knowledge gained through years of practice. We investigate whether LLMs can serve as decision support for this rule-to-action step and introduce , a benchmark of 6{,}690 expert-validated multiple-choice questions from 118 rule-action pairs across 16 asset types. We contribute (i) a symbolic-to-MCQA pipeline normalizing rules to Disjunctive Normal Form with embedding-based distractor sampling, (ii) five variants probing distinct failure modes (Pro, Pert, Verbose, Aug, Rationale), and (iii) a benchmark of 29 LLMs and 4 embedding baselines. A human evaluation (9 practitioners, mean 45.0\%) confirms requires specialist knowledge beyond operational experience. Three findings stand out. The frontier has closed: the top three LLMs lie within one Macro point, with Bradley-Terry Elo placing claude-opus-4-6 30 points above the next model. Yet \,Pro exposes brittleness, with every model losing 13--60\% relative accuracy under distractor expansion. \,Aug exposes pattern-matching: under condition inversion, frontier models still select the original answer 49--63\% of the time. The deployment bottleneck is not capability but calibration: frontier models handle template-style fault detection but break under structural perturbation.

ibm IBM
·
May 8 2

Do Large Language Models Align with Core Mental Health Counseling Competencies?

The rapid evolution of Large Language Models (LLMs) offers promising potential to alleviate the global scarcity of mental health professionals. However, LLMs' alignment with essential mental health counseling competencies remains understudied. We introduce CounselingBench, a novel NCMHCE-based benchmark evaluating LLMs across five key mental health counseling competencies. Testing 22 general-purpose and medical-finetuned LLMs, we find frontier models exceed minimum thresholds but fall short of expert-level performance, with significant variations: they excel in Intake, Assessment & Diagnosis yet struggle with Core Counseling Attributes and Professional Practice & Ethics. Medical LLMs surprisingly underperform generalist models accuracy-wise, while at the same time producing slightly higher-quality justifications but making more context-related errors. Our findings highlight the complexities of developing AI systems for mental health counseling, particularly for competencies requiring empathy and contextual understanding. We found that frontier LLMs perform at a level exceeding the minimal required level of aptitude for all key mental health counseling competencies, but fall short of expert-level performance, and that current medical LLMs do not significantly improve upon generalist models in mental health counseling competencies. This underscores the critical need for specialized, mental health counseling-specific fine-tuned LLMs that rigorously aligns with core competencies combined with appropriate human supervision before any responsible real-world deployment can be considered.

  • 11 authors
·
Oct 29, 2024

BlueFin: Benchmarking LLM Agents on Financial Spreadsheets

We present BlueFin, a benchmark that tasks large language model (LLM) agents with synthesis, manipulation, and comprehension tasks over spreadsheet workbooks in the professional finance domain. Though estimates of the global population of paying users of spreadsheet software range in the hundreds of millions -- an order of magnitude more than the estimated global population of professional developers -- comparatively fewer resources have been devoted to exploring and expanding LLM capabilities in the spreadsheet domain, with fewer still dedicated to mirroring real occupational tasks encountered by those in professional finance roles. In response, we curate a set of 131 challenging, complex tasks with real-world relevance in the domain, containing 3,225 granular rubric criteria; notably, our rubric criteria and LM judge evaluations are validated by a team of expert human annotators, resulting in high-quality, granular evaluations of complex tasks that are difficult to verify programmatically but can be reliably evaluated by an LM judge agent. Our judge achieves parity with expert consensus (α=0.826) with a macro-F1 score of 0.839. Frontier LLMs demonstrate poor performance on the challenging benchmark, with the strongest LLMs achieving less than 50\% average scores across tasks -- models exhibit particular weaknesses in dynamic correctness. Our contributions include a dataset of examples across three categories of spreadsheet tasks, an open source harness and agentic evaluation framework, and a characterization of existing frontier models' performance on our benchmark.

  • 9 authors
·
May 28

EU-Agent-Bench: Measuring Illegal Behavior of LLM Agents Under EU Law

Large language models (LLMs) are increasingly deployed as agents in various contexts by providing tools at their disposal. However, LLM agents can exhibit unpredictable behaviors, including taking undesirable and/or unsafe actions. In order to measure the latent propensity of LLM agents for taking illegal actions under an EU legislative context, we introduce EU-Agent-Bench, a verifiable human-curated benchmark that evaluates an agent's alignment with EU legal norms in situations where benign user inputs could lead to unlawful actions. Our benchmark spans scenarios across several categories, including data protection, bias/discrimination, and scientific integrity, with each user request allowing for both compliant and non-compliant execution of the requested actions. Comparing the model's function calls against a rubric exhaustively supported by citations of the relevant legislature, we evaluate the legal compliance of frontier LLMs, and furthermore investigate the compliance effect of providing the relevant legislative excerpts in the agent's system prompt along with explicit instructions to comply. We release a public preview set for the research community, while holding out a private test set to prevent data contamination in evaluating upcoming models. We encourage future work extending agentic safety benchmarks to different legal jurisdictions and to multi-turn and multilingual interactions. We release our code on https://github.com/ilijalichkovski/eu-agent-bench{this URL}.

  • 4 authors
·
Oct 24, 2025

TutorBench: A Benchmark To Assess Tutoring Capabilities Of Large Language Models

As students increasingly adopt large language models (LLMs) as learning aids, it is crucial to build models that are adept at handling the nuances of tutoring: they need to identify the core needs of students, be adaptive, provide personalized guidance, and be accurate. To this end, we introduce TutorBench, a dataset and evaluation benchmark designed to rigorously evaluate the core tutoring skills of LLMs. The dataset comprises 1,490 samples curated by human experts, focused on high-school and AP-level curricula. The samples are drawn from three common tutoring tasks: (i) generating adaptive explanations tailored to a student's confusion, (ii) providing actionable feedback on a student's work, and (iii) promoting active learning through effective hint generation. To account for the inherent complexity of tutoring, samples are accompanied by sample-specific rubrics which are used to judge model responses during evaluation. TutorBench uses a reliable and fine-grained automatic evaluation method that uses an LLM-judge and the sample-specific rubrics. We evaluate 16 frontier LLMs on TutorBench and present a detailed analysis of their performance and behavior. Our results show that none of the frontier LLMs achieve a score of greater than 56%, showing a large room for improvement. We find that LLMs fall short in exhibiting the full range of tutoring skills needed to guide, diagnose, and support students effectively, with all the frontier models achieving less than a 60% pass rate on rubric criteria related to these skills. We also find that different model families exhibit varied strengths and limitations: the Claude models outperform others in supporting active learning, while they lag behind in the other two use cases. By releasing TutorBench, we provide a comprehensive and unsaturated benchmark to guide the development of the next-generation of AI tutors.

  • 14 authors
·
Oct 2, 2025

SCICONVBENCH: Benchmarking LLMs on Multi-Turn Clarification for Task Formulation in Computational Science

Large Language Models (LLMs) are increasingly deployed as scientific AI as- sistants, and a growing body of benchmarks evaluates their capabilities across knowledge retrieval, reasoning, code generation, and tool use. These evaluations, however, typically assume the scientific problem is already well-posed, whereas practical scientific assistance often begins with an ill-posed user request that must be refined through dialogue before any computation, analysis, or experiment can be carried out reliably. We introduce SCICONVBENCH, a benchmark for multi- turn clarification in scientific task formulation across four computational science problem domains: fluid mechanics, solid mechanics, materials science, and par- tial differential equations (PDEs). SCICONVBENCH targets two complementary capabilities: eliciting missing information (disambiguation) and detecting and correcting erroneous requests containing internally contradictory information (in- consistency resolution). Our benchmark pairs a structured task ontology with a rubric-based evaluation framework, enabling systematic measurement of LLM per- formance across three dimensions: clarification behavior, conversational grounding, and final-specification fidelity. Current frontier models perform relatively well on inconsistency resolution, but even the best model resolves only 52.7% of the disambiguation cases in fluid mechanics. We further find that frontier LLMs fre- quently make silent assumptions and perform implicit specification repairs that are not grounded in the conversation with users. SCICONVBENCH establishes a foundation for evaluating the upstream conversational reasoning that a reliable computational science assistant requires. The code and data can be found at https://github.com/csml-rpi/SciConvBench.

Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation

Frontier LLM agents are automating many business tasks, but their high inference cost makes large-scale deployment unsustainable. Small language models (SLMs) offer a cheaper alternative, yet they typically fall short when swapped into a harness designed for a frontier LLM. We show that for many routine business tasks, SLM agents can match LLM performance at 90% lower cost, when paired with an adapted harness that can be automatically discovered by a meta agent. The key insight is that much of the task difficulty is shared across instances and can be lifted from the model into the harness via tailored instructions, tools, and orchestration loops. To study this systematically, we create a framework that maps agent failure modes to harness adaptation strategies, and build a harness optimizer that automatically discovers effective adaptations from failure trajectories. Across seven business-oriented agentic tasks and three SLM families, we found optimized harnesses significantly improve performance on 16 of 21 task-SLM pairs, with seven pairs closing the SLM-LLM performance gap and the best SLM agent recovering 89.7% of LLM performance at 4% of the cost. Our analysis further shows that adaptation works best for tasks with more repetitive workflows and for SLMs with sufficient base capabilities. Together, these results suggest that harness adaptation can expand the practical deployment range of SLM agents in routine business tasks.

  • 4 authors
·
Jul 8

PHMForge: Evaluating LLM Agents on Industrial Prognostics through MCP-Native, Algorithm-Grounded Tools

LLM agents are beginning to invoke industrial asset-management tools through the Model Context Protocol (MCP), yet whether they can act reliably on this substrate for safety-critical Prognostics and Health Management (PHM) is unanswered. Prior benchmarks conflate protocol fluency with reasoning, instrumentation failures with agent failures, and tool use with tool retrieval. We introduce PHMForge, an evaluation environment that closes each conflation. PHMForge ships 99 SME-authored scenarios across eight industrial asset classes spanning rotating equipment, aero-engines, and lithium-ion cells, on public datasets including NASA PCoE, served through 39 MCP-native tools wrapping published PHM algorithms (C-MAPSS, ISO~10816, Arrhenius capacity-fade models, time-series foundation models). Krippendorff's αin [0.74,,0.82] on a 30-scenario stratified rotating-equipment/aero-engine sample; the battery extension is single-rater. Across three agentic frameworks and six LLM backbones, the strongest configuration reaches 80.8\% pass@1, with the residual gap concentrated in orchestration and tool-sequencing errors. Crucially, an architectural ablation shows that replacing MCP execution with text-based Retrieval-Augmented Generation (RAG) over telemetry-equivalent evidence collapses Remaining Useful Life pass-all-3 from 100\% to 20\% (5/5 vs.\ 1/5) on the battery class, exposing the structural limits of static retrieval for prognostic computation. Trajectory decomposition shows orchestration errors dominate failures across backbones, while schema-invalid tool calls concentrate in smaller open-weight models. Frontier LLMs are stronger at calling tools than at planning when to call them. PHMForge is open-sourced with deterministic evaluators, a public leaderboard, and a datasheet.

  • 8 authors
·
May 7

Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers

Fact verification is essential for ensuring the reliability of LLM applications. In this study, we evaluate 12 pre-trained LLMs and one specialized fact-verifier, including frontier LLMs and open-weight reasoning LLMs, using a collection of examples from 14 fact-checking benchmarks. We share three findings intended to guide future development of more robust fact verifiers. First, we highlight the importance of addressing annotation errors and ambiguity in datasets, demonstrating that approximately 16\% of ambiguous or incorrectly labeled data substantially influences model rankings. Neglecting this issue may result in misleading conclusions during comparative evaluations, and we suggest using a systematic pipeline utilizing LLM-as-a-judge to help identify these issues at scale. Second, we discover that frontier LLMs with few-shot in-context examples, often overlooked in previous works, achieve top-tier performance. We therefore recommend future studies include comparisons with these simple yet highly effective baselines. Lastly, despite their effectiveness, frontier LLMs incur substantial costs, motivating the development of small, fine-tuned fact verifiers. We show that these small models still have room for improvement, particularly on instances that require complex reasoning. Encouragingly, we demonstrate that augmenting training with synthetic multi-hop reasoning data significantly enhances their capabilities in such instances. We release our code, model, and dataset at https://github.com/just1nseo/verifying-the-verifiers

  • 9 authors
·
Jun 16, 2025

Structured Distillation of Web Agent Capabilities Enables Generalization

Frontier LLMs can navigate complex websites, but their cost and reliance on third-party APIs make local deployment impractical. We introduce Agent-as-Annotators, a framework that structures synthetic trajectory generation for web agents by analogy to human annotation roles, replacing the Task Designer, Annotator, and Supervisor with modular LLM components. Using Gemini 3 Pro as teacher, we generate 3,000 trajectories across six web environments and fine-tune a 9B-parameter student with pure supervised learning on the 2,322 that pass quality filtering. The resulting model achieves 41.5% on WebArena, surpassing closed-source models such as Claude 3.5 Sonnet (36.0%) and GPT-4o (31.5%) under the same evaluation protocol, and nearly doubling the previous best open-weight result (Go-Browse, 21.7%). Capabilities transfer to unseen environments, with an 18.2 percentage point gain on WorkArena L1 (an enterprise platform never seen during training) and consistent improvements across three additional benchmarks. Ablations confirm that each pipeline component contributes meaningfully, with Judge filtering, evaluation hints, and reasoning traces each accounting for measurable gains. These results demonstrate that structured trajectory synthesis from a single frontier teacher is sufficient to produce competitive, locally deployable web agents. Project page: https://agent-as-annotators.github.io

Multi-Legal-Bench: Evaluating LLMs on Legal Reasoning Across Jurisdictions, Languages, and Legal Traditions

Legal NLP benchmarks overwhelmingly evaluate a single language or aggregate tasks that differ fundamentally across jurisdictions, making cross-lingual comparison impossible. We introduce Multi-Legal-Bench, the first cross-jurisdictional legal benchmark that evaluates identical tasks across six countries (Ukraine, France, Netherlands, Poland, Czech Republic, Lithuania), four language families, and 134 million court decisions. The benchmark defines five tasks court-type classification, judgment form classification, case-outcome prediction, legal norm extraction, and cause category prediction mapped to structured metadata from national court registries, forming a deliberately sparse 5x6 task-jurisdiction matrix (20 of 30 cells filled). We evaluate 7 frontier LLMs under zero-shot and 3-shot prompting via AWS Bedrock, with 4 additional small/medium models (3-12B) for scaling analysis. Our results reveal that: (1) task-dependent few-shot effects discovered in Ukrainian replicate across all jurisdictions; (2) no single model dominates any language rankings shift with both task and jurisdiction; (3) cross-lingual few-shot transfer does not follow language proximity: UA->FR (Romance, -2.1 pp) transfers better than UA->PL (Slavic, -13.7 pp), with label-set alignment predicting transfer quality better than language family; and (4) tokenizer fertility, despite a 2.3x spread, does not significantly predict cross-lingual accuracy (r=-0.27, p=0.14), suggesting that model architecture and pretraining data dominate tokenizer efficiency. We release all data, prompts, and model predictions.

  • 1 authors
·
May 27

OpenLearnLM Benchmark: A Unified Framework for Evaluating Knowledge, Skill, and Attitude in Educational Large Language Models

Large Language Models are increasingly deployed as educational tools, yet existing benchmarks focus on narrow skills and lack grounding in learning sciences. We introduce OpenLearnLM Benchmark, a theory-grounded framework evaluating LLMs across three dimensions derived from educational assessment theory: Knowledge (curriculum-aligned content and pedagogical understanding), Skills (scenario-based competencies organized through a four-level center-role-scenario-subscenario hierarchy), and Attitude (alignment consistency and deception resistance). Our benchmark comprises 124K+ items spanning multiple subjects, educational roles, and difficulty levels based on Bloom's taxonomy. The Knowledge domain prioritizes authentic assessment items from established benchmarks, while the Attitude domain adapts Anthropic's Alignment Faking methodology to detect behavioral inconsistency under varying monitoring conditions. Evaluation of seven frontier models reveals distinct capability profiles: Claude-Opus-4.5 excels in practical skills despite lower content knowledge, while Grok-4.1-fast leads in knowledge but shows alignment concerns. Notably, no single model dominates all dimensions, validating the necessity of multi-axis evaluation. OpenLearnLM provides an open, comprehensive framework for advancing LLM readiness in authentic educational contexts.

  • 14 authors
·
Jan 19

FrontierOR: Benchmarking LLMs' Capacity for Efficient Algorithm Design in Large-Scale Optimization

Large language models (LLMs) are increasingly used for optimization modeling and solver-code generation, yet practical operations research and optimization problems often require a harder capability: designing scalable algorithms that exploit problem structure and outperform direct formulation-and-solve baselines. Existing benchmarks are limited to small or simplified examples far below real-world scale and complexity. We introduce FrontierOR, among the first benchmarks to systematically evaluate LLM-based efficient algorithm design for realistic large-scale optimization problems. FrontierOR includes 180 tasks derived from methodologically diverse papers published in top-tier operations research venues, each with standardized instances and a hidden, expert-verified evaluation suite. We evaluate seven LLMs spanning frontier, cost-effective, and open-source models both in one-shot and test-time evolution settings. The results reveal that frontier models still struggle to move from executable formulations to efficient optimization algorithms: the strongest one-shot model outperforms Gurobi in only 31% of cases in both solution quality and computational efficiency, and even strong coding agents with test-time evolution achieve only 50% on selected hard tasks. FrontierOR establishes a practical evaluation platform for LLM-based optimization algorithm design, which enables future LLMs and agents to be systematically tested on whether they can move beyond correct formulation toward a feasible, high-quality, and efficient algorithm. Code and data are publicly released at https://github.com/Minw913/FrontierOR.

  • 27 authors
·
May 29

SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents

As Large Language Models (LLMs) are increasingly deployed as autonomous agents in complex and long horizon settings, it is critical to evaluate their ability to sabotage users by pursuing hidden objectives. We study the ability of frontier LLMs to evade monitoring and achieve harmful hidden goals while completing a wide array of realistic tasks. We evaluate a broad range of frontier LLMs using SHADE (Subtle Harmful Agent Detection & Evaluation)-Arena, the first highly diverse agent evaluation dataset for sabotage and monitoring capabilities of LLM agents. SHADE-Arena consists of complex pairs of benign main tasks and harmful side objectives in complicated environments. Agents are evaluated on their ability to complete the side task without appearing suspicious to an LLM monitor. When measuring agent ability to (a) complete the main task, (b) complete the side task, and (c) avoid detection, we find that the best performing frontier models score 27% (Claude 3.7 Sonnet) and 15% (Gemini 2.5 Pro) as sabotage agents when overseen by Claude 3.6 Sonnet. For current frontier models, success on the side task relies heavily on having access to a hidden scratchpad that is not visible to the monitor. We also use SHADE-Arena to measure models' monitoring abilities, with the top monitor (Gemini 2.5 Pro) achieving an AUC of 0.87 at distinguishing benign and malign transcripts. We find that for now, models still struggle at sabotage due to failures in long-context main task execution. However, our measurements already demonstrate the difficulty of monitoring for subtle sabotage attempts, which we expect to only increase in the face of more complex and longer-horizon tasks.

  • 12 authors
·
Jul 7, 2025

AIRTBench: Measuring Autonomous AI Red Teaming Capabilities in Language Models

We introduce AIRTBench, an AI red teaming benchmark for evaluating language models' ability to autonomously discover and exploit Artificial Intelligence and Machine Learning (AI/ML) security vulnerabilities. The benchmark consists of 70 realistic black-box capture-the-flag (CTF) challenges from the Crucible challenge environment on the Dreadnode platform, requiring models to write python code to interact with and compromise AI systems. Claude-3.7-Sonnet emerged as the clear leader, solving 43 challenges (61% of the total suite, 46.9% overall success rate), with Gemini-2.5-Pro following at 39 challenges (56%, 34.3% overall), GPT-4.5-Preview at 34 challenges (49%, 36.9% overall), and DeepSeek R1 at 29 challenges (41%, 26.9% overall). Our evaluations show frontier models excel at prompt injection attacks (averaging 49% success rates) but struggle with system exploitation and model inversion challenges (below 26%, even for the best performers). Frontier models are far outpacing open-source alternatives, with the best truly open-source model (Llama-4-17B) solving 7 challenges (10%, 1.0% overall), though demonstrating specialized capabilities on certain hard challenges. Compared to human security researchers, large language models (LLMs) solve challenges with remarkable efficiency completing in minutes what typically takes humans hours or days-with efficiency advantages of over 5,000x on hard challenges. Our contribution fills a critical gap in the evaluation landscape, providing the first comprehensive benchmark specifically designed to measure and track progress in autonomous AI red teaming capabilities.

  • 4 authors
·
Jun 17, 2025

FoundationalASSIST: An Educational Dataset for Foundational Knowledge Tracing and Pedagogical Grounding of LLMs

Can Large Language Models understand how students learn? As LLMs are deployed for adaptive testing and personalized tutoring, this question becomes urgent -- yet we cannot answer it with existing resources. Current educational datasets provide only question identifiers and binary correctness labels, rendering them opaque to LLMs that reason in natural language. We address this gap with FoundationalASSIST, the first English educational dataset providing the complete information needed for research on LLMs in education: full question text, actual student responses (not just right/wrong), records of which wrong answers students chose, and alignment to Common Core K-12 standards. These 1.7 million interactions from 5,000 students enable research directions that were previously impossible to pursue, from fine-tuning student models to analyzing misconception patterns. To demonstrate the dataset's utility, we evaluate four frontier models (GPT-OSS-120B, Llama-3.3-70B, Qwen3-Next-80B variants) on two complementary task families: Knowledge Tracing, testing whether LLMs can predict student performance on questions, and the exact answer a student will give; and Pedagogical Grounding, testing whether LLMs understand the properties that make assessment items effective. Our evaluation reveals significant gaps in current LLM capabilities. Every model barely achieves a trivial baseline on knowledge tracing. All models fall below random chance on item discrimination, indicating that LLMs do not understand what makes one problem more diagnostic than another. Models do show competence at judging relative difficulty (up to 68.6%), but this partial success only highlights the gaps elsewhere. These results establish that substantial advances are needed before LLMs can reliably support personalized learning at scale. We release FoundationalASSIST to support progress on these foundational challenges.

  • 4 authors
·
Jan 20

RSIBench-Data: Benchmarking Data-Centric Research for Recursive Self-Improvement

Recursive self-improvement requires turning evidence of model failures into better models. Data-centric post-training research entails diagnosing capability gaps, designing and validating training-data strategies, and learning from checkpoint feedback. Can LLM agents automate this loop? Existing benchmarks entangle research decisions with optimization, serving, evaluation, and systems implementation, obscuring agents' research capability. We introduce RSIBench-Data, a controlled benchmark of LLM agents as data-centric researchers with a fixed post-training stack. Agents iteratively revise training-data strategies for a fixed target model; training and serving use Tinker-backed services, official evaluation runs through Harbor and E2B sandboxes, and budgets are fixed across agents. We evaluate four frontier agents on six benchmarks across software engineering, terminal use, scientific question answering, and mathematics. Agents demonstrate core data-centric research capabilities: in 58.33\% of settings, they improve upon the first valid attempt by refining strategies from feedback. However, improvement is inconsistent. Among searches continuing after the best observed score, 78.26\% end with a lower-scoring final attempt, while the rest only recover the same peak. A strong candidate may therefore appear early or midway through a run even as later revisions fail. Trajectory analysis identifies four patterns in stronger runs: accurate hypotheses, validation-grounded supervision, behavior-aligned data, and preservation of strong checkpoints. These findings suggest that current agents can make useful data-centric discoveries but cannot yet translate feedback into consistent improvements. RSIBench-Data provides a measurable, auditable testbed for the research capabilities required for recursive self-improvement. We open-source our code at https://github.com/evolvent-ai/RSIBench-Data.

  • 7 authors
·
Jul 27

Do We Need Frontier Models to Verify Mathematical Proofs?

Advances in training, post-training, and inference-time methods have enabled frontier reasoning models to win gold medals in math competitions and settle challenging open problems. Gaining trust in the responses of these models requires that natural language proofs be checked for errors. LLM judges are increasingly being adopted to meet the growing demand for evaluating such proofs. While verification is considered easier than generation, what model capability does reliable verification actually require? We systematically evaluate four open-source and two frontier LLMs on datasets of human-graded natural language proofs of competition-level problems. We consider two key metrics: verifier accuracy and self-consistency (the rate of agreement across repeated judgments on the same proof). We observe that smaller open-source models are only up to ~10% behind frontier models in accuracy but they are up to ~25% more inconsistent. Furthermore, we see that verifier accuracy is sensitive to prompt choice across all models. We then demonstrate that the smaller models, in fact, do possess the mathematical capabilities to verify proofs at the level of frontier models, but they struggle to reliably elicit these capabilities with general judging prompts. Through an LLM-guided prompt search, we synthesize an ensemble of specialized prompts that overcome the specific failure modes of smaller models, boosting their performance by up to 9.1% in accuracy and 15.9% in self-consistency. These gains are realized across models and datasets, allowing models like Qwen3.5-35B to perform on par with frontier models such as Gemini 3.1 Pro for proof verification.

  • 4 authors
·
Apr 1

TraceDance: An Automated System for Building Agent Behavior Benchmarks from Real-World Agent Deployment Traces

An agent can complete a task while exhibiting undesirable behavior during execution. Developers need tests for the specific behaviors encountered in deployment, beyond fixed benchmark suites. We present TraceDance, an agent system that constructs targeted benchmarks from deployment traces for user-specified undesirable behaviors. For efficient construction, Anchor-and-Confirm combines programmable retrieval with candidate-level confirmation by a Flash large language model (LLM), while the Anchor Synthesis Loop generates and revises specifications for custom behaviors. The benchmarks use decision-point continuation to evaluate an LLM's next turn at a recorded decision point with a behavior-specific rubric, without a reference answer or environment replay. Experiments in coding and general tool use draw on 252,557 sessions and produce 107 benchmarks with 4,125 instances, fulfilling 95.3% of build-target requests. Both human annotators confirm the requested behavior in 84% of sampled instances, and the automated grader's agreement with human pass/fail judgments is comparable to that between the annotators. Nine frontier LLMs achieve a mean pass rate of only 26.7%, showing that they still struggle to respond appropriately at the evaluated decision points. Analysis across behavior-specific benchmarks further reveals weaknesses in how current LLMs behave as agents. By turning deployment problems into targeted benchmarks, TraceDance could serve as a key component of the recursive self-improvement (RSI) loop.

ByteDance ByteDance
·
Sep 26 2

SecRespond: Benchmarking AI Agents for Real-World Post-Compromise Incident Response

Large Language Model (LLM) agents are increasingly adopted in real-world security operations with access to host artifacts and command-line interfaces (CLIs), making it critical to thoroughly assess their security capabilities. However, existing cybersecurity benchmarks focus on pre-compromise settings where agents are placed in a clean and idealized environment before an attack occurs. This leaves the post-compromise setting underexplored. To address this gap, we introduce SecRespond, the first benchmark for evaluating LLM agents on the post-compromise incident-response workflow. Given a forensic disk snapshot of a compromised host together with the alerts, vulnerability scans, and baseline checks reported by a host security product, agents are required to produce forensic reports on intrusions, baseline risks, and vulnerability risks, together with a remediation plan. We instantiate this task across 10 cyber ranges, each constructed from a distinct compromised cloud host, spanning 4 entry-point types, 21 ATT&CK techniques, and 5 operating systems. We evaluate 23 frontier LLMs on the OpenCode agent harness. Experimental results show that although current agents can reliably uncover the problems exposed by alerts, they struggle to proactively investigate the disk for silent intrusions and to produce comprehensive, verified remediation plans, with no model achieving complete detection and remediation on any single range. This reveals a fundamental bottleneck in building agents for real-world incident response. The benchmark is publicly available at https://github.com/Alibaba-NLP/qqr/tree/main/data/secrespond.

Alibaba-NLP Alibaba-NLP
·
Jul 28 2

Continual Learning Exam: Benchmarking Long-Horizon RSI and Experiential Learning in LLM Agents

Continual learning is the ability of LLM agents to improve over time by acquiring, refining, and applying knowledge from experience while retaining useful prior knowledge. It is essential for agents learning over long time horizons, yet current evaluations largely assess individual task performance rather than improvement through accumulated experience. We introduce Continual Learning Exam (CLE), a large-scale benchmark developed by 50+ domain experts to measure experience-driven improvement in realistic professional workflows. CLE comprises 120 human-authored tasks, each organised as a five-level ladder, yielding 600 levels spanning 89 professional roles across 12 occupational domains. Agents must pass each level to unlock the next, with later levels building on experience accumulated during earlier assignments. An evaluation agent assesses each submission against human-authored rubrics. We compare a single-submission setting with one that provides diagnostic feedback after failure and allows one revision. Across 17 harness-model configurations using frontier LLMs, feedback and revision yield a median completion gain of 5.3 percentage points. Yet the best-performing system clears only 47.7% of levels and completes all five levels in just 23.3% of tasks, highlighting the difficulty of sustained learning from experience for existing frontier LLMs. As such, the dataset can also be used to post-train LLMs to strengthen their continual learning capabilities.

QuoteBench: How Matched Scores Can Hide Command-Path Failures

LLM coding agents issue Bash commands through interfaces that may serialize, wrap, and reparse model output. Matched execution scores alone cannot distinguish command-generation errors from failures introduced after generation. QuoteBench measures this boundary with exact final-state validation on 56 one-shot tasks from 14 incident-derived families, crossing the generation contract with the execution transport around one deliberately unescaped added parser. Escaping at the interpolation point reproduces each replayed reply's raw-path outcome, so any recovery under a disclosed boundary must come from the model changing its generation. Across eight same-window configurations, replaying the same reply through the added parser lowers success by 55.4 to 73.2 percentage points; disclosure recovers 30.4 to 60.7 points for six configurations, and zero or slightly negative for the other two. Raw generation is nearly saturated at the frontier; boundary adaptation is what still separates models. GPT-5.6-sol's matched gap of -3.6 points hides -64.3 points of damage and +60.7 points of compensation. The deployment configuration reorders models: one reversal among 26 comparable pairs is unambiguous and four more sit on single-task margins. Evaluations of command-issuing agents should report the model configuration, generation contract, execution path, operating point, and final-state validator rather than treat a matched score as an intrinsic model property.

  • 4 authors
·
Aug 12 4

Pre-trained knowledge elevates large language models beyond traditional chemical reaction optimizers

Modern optimization in experimental chemistry employs algorithmic search through black-box parameter spaces. Here we demonstrate that pre-trained knowledge in large language models (LLMs) fundamentally changes this paradigm. Using six fully enumerated categorical reaction datasets (768 - 5,684 experiments), we benchmark LLM-guided optimization (LLM-GO) against Bayesian optimization (BO) and random sampling. Frontier LLMs consistently match or exceed BO performance across five single-objective datasets, with advantages growing as parameter complexity increases and high-performing conditions become scarce (<5% of space). BO retains superiority only for explicit multi-objective trade-offs. To understand these contrasting behaviors, we introduce a topology-agnostic information theory framework quantifying sampling diversity throughout optimization campaigns. This analysis reveals that LLMs maintain systematically higher exploration entropy than BO across all datasets while achieving superior performance, with advantages most pronounced in solution-scarce parameter spaces where high-entropy exploration typically fails - suggesting that pre-trained domain knowledge enables more effective navigation of chemical parameter space rather than replacing structured exploration strategies. To enable transparent benchmarking and community validation, we release Iron Mind (https://gomes.andrew.cmu.edu/iron-mind), a no-code platform for side-by-side evaluation of human, algorithmic, and LLM optimization campaigns with public leaderboards and complete trajectories. Our findings establish that LLM-GO excels precisely where traditional methods struggle: complex categorical spaces requiring domain understanding rather than mathematical optimization.

  • 5 authors
·
Aug 27, 2025

HydroAgent: Closing the Gap Between Frontier LLMs and Human Experts in Hydrologic Model Calibration via Simulator-Grounded RL

Calibrating distributed hydrologic models is a critical bottleneck across operational water resources management - streamflow prediction, reservoir operation, drought monitoring, infrastructure design, and flood forecasting all depend on it. Each basin demands an expert to translate hydrograph signatures into adjustments of a high-dimensional parameter vector, and the resulting workflow does not transfer between watersheds. We ask: can frontier large language model (LLM) agents replace the human hydrologic modeler, and if not, what would it take? We benchmark nine frontier LLM agents - Claude Opus 4.6/4.7, Sonnet 4.6, GPT-5/5.4/5.4-pro, and Gemini 2.5-pro/3.1-pro/3-flash - on the operational CREST distributed hydrologic model used by the U.S. National Weather Service for flash-flood forecasting. Best-of-twenty-rounds Nash-Sutcliffe Efficiency (NSE) across four held-out gauges spanning 329-40,792 km2 ranges from -0.16 (GPT-5.4) to 0.75 (Sonnet 4.6); the ceiling reproduces across all three vendors and capability tiers, with the strongest models concentrating in the 0.65-0.75 band, and no model reaches the human-expert reference except Opus-4.7 on one gauge. We argue this gap is not a parameter-count problem but a domain-grounding problem. We then propose HYDROAGENT, fine-tuning open-weight Qwen3-4B with supervised fine-tuning on 2,576 expert calibration trajectories and Group-Relative Policy Optimization using NSE as a verifiable reward from online CREST simulations - reinforcement learning with simulation feedback (RLSF). For Earth system science, a small domain-tuned policy with simulator-in-the-loop RL is a more compute-efficient and physically faithful path than scaling generic frontier models, and the multi-modal richness of Earth data - remote sensing, in-situ time series, and forecaster narrative - makes domain agents a leveraged direction for AI in physical science.

  • 7 authors
·
May 17

RefineBench: Evaluating Refinement Capability of Language Models via Checklists

Can language models (LMs) self-refine their own responses? This question is increasingly relevant as a wide range of real-world user interactions involve refinement requests. However, prior studies have largely tested LMs' refinement abilities on verifiable tasks such as competition math or symbolic reasoning with simplified scaffolds, whereas users often pose open-ended queries and provide varying degrees of feedback on what they desire. The recent advent of reasoning models that exhibit self-reflection patterns in their chains-of-thought further motivates this question. To analyze this, we introduce RefineBench, a benchmark of 1,000 challenging problems across 11 domains paired with a checklist-based evaluation framework. We evaluate two refinement modes: (1) guided refinement, where an LM is provided natural language feedback, and (2) self-refinement, where LMs attempt to improve without guidance. In the self-refinement setting, even frontier LMs such as Gemini 2.5 Pro and GPT-5 achieve modest baseline scores of 31.3% and 29.1%, respectively, and most models fail to consistently improve across iterations (e.g., Gemini-2.5-Pro gains only +1.8%, while DeepSeek-R1 declines by -0.1%). By contrast, in guided refinement, both proprietary LMs and large open-weight LMs (>70B) can leverage targeted feedback to refine responses to near-perfect levels within five turns. These findings suggest that frontier LMs require breakthroughs to self-refine their incorrect responses, and that RefineBench provides a valuable testbed for tracking progress.

Cookie-Bench: Continuous On-screen Key Interaction Evaluation for Web Generation

Front-end web code has become a core product surface for every frontier LLM release, yet evaluating these interactive applications at development speed remains costly because human-judged leaderboards like Arena do not scale. Existing automated proxies typically lean on reference implementations, test suites, or rigid checklists, and tend to miss the reasoned synthesis a human reviewer performs over a live session. We articulate a new evaluation regime that is simultaneously reference-free, autonomously driven, and holistically reasoned, and instantiate it through two artifacts. \dataname is an 11-domain, 54-leaf, 1,000-query WebDev benchmark spanning both static-presentation and interactive-application tasks, balanced across three difficulty tiers and three target-language groups, with briefs rewritten to resist recall from circulated prompts. \framename, grounded in Flavell's metacognitive monitoring, separates evidence accumulation from judgment across three stages: Static Perception forms a first impression from passive observation; Agent-Driven Interaction explores the application autonomously while capturing continuous screen video, audio, and per-step screenshots; Dynamic Scoring issues holistic functionality and aesthetics verdicts with structured failure attribution only after the evidence chain is complete. On \dataname, \framename aligns closely with expert human ratings while surfacing substantial headroom across 13 frontier LLMs on interactive web generation. \noindenthttps://anonymous.4open.science/r/Cookie-3CE/

  • 11 authors
·
May 30

Auditing Multimodal LLM Raters: Central Tendency Bias in Clinical Ordinal Scoring

Multimodal large language models (LLMs) are increasingly explored as automated evaluators in clinical settings, yet their scoring behavior on ordinal clinical scales remains poorly understood. We benchmark three frontier LLM families against supervised deep learning models for scoring Clock Drawing Test (CDT) images on two public datasets using the Shulman rubric. While fully fine-tuned Vision Transformers achieve the best calibration (MAE 0.52, within-1 accuracy 91%), zero-shot LLMs remain competitive on tolerance-based agreement (GPT-5 MAE 0.67, within-1 accuracy 92%) despite higher absolute error. However, per-score analysis reveals that all three LLM families exhibit a pronounced central tendency effect (systematic endpoint compression): predictions are systematically compressed toward the middle of the scale, with over-prediction at the low end (score 0 to 1) and under-prediction at the high end (score 5 to 4). This effect disproportionately affects the clinically critical extremes where accurate scoring most impacts screening decisions for cognitive impairment. Targeted ablations show that neither few-shot exemplars spanning the full score range nor removing clinical terminology from the prompt eliminates the effect. Our findings extend the LLM-as-a-judge bias literature from NLP evaluation to clinical assessment, and highlight the need for calibration-aware evaluation and post-hoc calibration before deploying LLM-based raters in high-stakes screening workflows.

OR-License: Evaluating LLM Agents as Real-World Operations Research Practitioners

Can large language model (LLM) agents deliver expert-level operations research (OR) solutions directly from original client materials, without prior expert reformulation? Existing OR benchmarks typically begin with self-contained descriptions or predefined optimization tasks, underrepresenting the translation of original business materials into professionally validated solutions. We introduce OR-License, an end-to-end benchmark of 31 instances across 10 industrial scenarios from paid OR engagements totaling USD 3.68 million. It preserves original requirements, input data, deliverable formats, and information boundaries after de-identification. To study information acquisition, we introduce ORSim, a controlled client simulator that discloses business facts without supplying OR expertise. Hidden evaluation checks feasibility and compares objective quality against original expert solutions accepted by clients before benchmark construction. Deployment-Adjusted Quality (DAQ) averages expert-relative quality across instances, assigning zero to infeasible deliveries. Across 11 frontier LLMs using coding-agent harnesses, several exceed the expert reference in conditional objective quality, but none matches its DAQ; the strongest primary Claude Code configuration achieves 88.39% strict feasibility and a DAQ of 0.87 against the expert reference of 1. Client information acquisition extends beyond clarification into solution development and validation, with some later stages showing higher confirmed issue-resolution proportions. Trajectory analysis identifies formulation and implementation failures, while task-equalized research-chain completion rates range from 24% to 45% across models on evaluable tasks. These findings motivate sustained information-gap resolution, faithful problem formulation, and evidence-linked self-improvement for reliable long-horizon agents.

AllEAILab ALLE AI
·
Oct 15 3

PostTrainBench: Can LLM Agents Automate LLM Post-Training?

AI agents have become surprisingly proficient at software engineering over the past year, largely due to improvements in reasoning capabilities. This raises a deeper question: can these systems extend their capabilities to automate AI research itself? In this paper, we explore post-training, the critical phase that turns base LLMs into useful assistants. We introduce PostTrainBench to benchmark how well LLM agents can perform post-training autonomously under bounded compute constraints (10 hours on one H100 GPU). We ask frontier agents (e.g., Claude Code with Opus 4.6) to optimize the performance of a base LLM on a particular benchmark (e.g., Qwen3-4B on AIME). Importantly, we do not provide any predefined strategies to the agents and instead give them full autonomy to find necessary information on the web, run experiments, and curate data. We find that frontier agents make substantial progress but generally lag behind instruction-tuned LLMs from leading providers: 23.2% for the best agent vs. 51.1% for official instruction-tuned models. However, agents can exceed instruction-tuned models in targeted scenarios: GPT-5.1 Codex Max achieves 89% on BFCL with Gemma-3-4B vs. 67% for the official model. We also observe several failure modes worth flagging. Agents sometimes engage in reward hacking: training on the test set, downloading existing instruction-tuned checkpoints instead of training their own, and using API keys they find to generate synthetic data without authorization. These behaviors are concerning and highlight the importance of careful sandboxing as these systems become more capable. Overall, we hope PostTrainBench will be useful for tracking progress in AI R&D automation and for studying the risks that come with it. Website and code are available at https://posttrainbench.com/.

Towards Execution-Grounded Automated AI Research

Automated AI research holds great potential to accelerate scientific discovery. However, current LLMs often generate plausible-looking but ineffective ideas. Execution grounding may help, but it is unclear whether automated execution is feasible and whether LLMs can learn from the execution feedback. To investigate these, we first build an automated executor to implement ideas and launch large-scale parallel GPU experiments to verify their effectiveness. We then convert two realistic research problems - LLM pre-training and post-training - into execution environments and demonstrate that our automated executor can implement a large fraction of the ideas sampled from frontier LLMs. We analyze two methods to learn from the execution feedback: evolutionary search and reinforcement learning. Execution-guided evolutionary search is sample-efficient: it finds a method that significantly outperforms the GRPO baseline (69.4% vs 48.0%) on post-training, and finds a pre-training recipe that outperforms the nanoGPT baseline (19.7 minutes vs 35.9 minutes) on pre-training, all within just ten search epochs. Frontier LLMs often generate meaningful algorithmic ideas during search, but they tend to saturate early and only occasionally exhibit scaling trends. Reinforcement learning from execution reward, on the other hand, suffers from mode collapse. It successfully improves the average reward of the ideator model but not the upper-bound, due to models converging on simple ideas. We thoroughly analyze the executed ideas and training dynamics to facilitate future efforts towards execution-grounded automated AI research.

  • 6 authors
·
Jan 20

OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories

Deep search capabilities have become an indispensable competency for frontier Large Language Model (LLM) agents, yet their development remains dominated by industrial giants. The typical industry recipe involves a highly resource-intensive pipeline spanning pre-training, continual pre-training (CPT), supervised fine-tuning (SFT), and reinforcement learning (RL). In this report, we show that when fueled with informative and high-difficulty trajectories, a simple SFT approach could be surprisingly powerful for training frontier search agents. By introducing three simple data synthesis modifications: scaling knowledge graph size for richer exploration, expanding the tool set size for broader functionality, and strict low-step filtering, we establish a stronger baseline. Trained on merely 10.6k data points, our OpenSeeker-v2 achieves state-of-the-art performance across 4 benchmarks (30B-sized agents with ReAct paradigm): 46.0% on BrowseComp, 58.1% on BrowseComp-ZH, 34.6% on Humanity's Last Exam, and 78.0% on xbench, surpassing even Tongyi DeepResearch trained with heavy CPT+SFT+RL pipeline, which achieves 43.4%, 46.7%, 32.9%, and 75.0%, respectively. Notably, OpenSeeker-v2 represents the first state-of-the-art search agent within its model scale and paradigm to be developed by a purely academic team using only SFT. We are excited to open-source the OpenSeeker-v2 model weights and share our simple yet effective findings to make frontier search agent research more accessible to the community.

  • 7 authors
·
May 4 3

CAR-bench: Evaluating the Consistency and Limit-Awareness of LLM Agents under Real-World Uncertainty

Existing benchmarks for Large Language Model (LLM) agents focus on task completion under idealistic settings but overlook reliability in real-world, user-facing applications. In domains, such as in-car voice assistants, users often issue incomplete or ambiguous requests, creating intrinsic uncertainty that agents must manage through dialogue, tool use, and policy adherence. We introduce CAR-bench, a benchmark for evaluating consistency, uncertainty handling, and capability awareness in multi-turn, tool-using LLM agents in an in-car assistant domain. The environment features an LLM-simulated user, domain policies, and 58 interconnected tools spanning navigation, productivity, charging, and vehicle control. Beyond standard task completion, CAR-bench introduces Hallucination tasks that test agents' limit-awareness under missing tools or information, and Disambiguation tasks that require resolving uncertainty through clarification or internal information gathering. Baseline results reveal large gaps between occasional and consistent success on all task types. Even frontier reasoning LLMs achieve less than 50% consistent pass rate on Disambiguation tasks due to premature actions, and frequently violate policies or fabricate information to satisfy user requests in Hallucination tasks, underscoring the need for more reliable and self-aware LLM agents in real-world settings.

FineTuneBench: How well do commercial fine-tuning APIs infuse knowledge into LLMs?

There is great interest in fine-tuning frontier large language models (LLMs) to inject new information and update existing knowledge. While commercial LLM fine-tuning APIs from providers such as OpenAI and Google promise flexible adaptation for various applications, the efficacy of fine-tuning remains unclear. In this study, we introduce FineTuneBench, an evaluation framework and dataset for understanding how well commercial fine-tuning APIs can successfully learn new and updated knowledge. We analyze five frontier LLMs with commercially available fine-tuning APIs, including GPT-4o and Gemini 1.5 Pro, on their effectiveness in two settings: (1) ingesting novel information, such as recent news events and new people profiles, and (2) updating existing knowledge, such as updated medical guidelines and code frameworks. Our results reveal substantial shortcomings in all the models' abilities to effectively learn new information through fine-tuning, with an average generalization accuracy of 37% across all models. When updating existing knowledge, such as incorporating medical guideline updates, commercial fine-tuning APIs show even more limited capability (average generalization accuracy of 19%). Overall, fine-tuning GPT-4o mini is the most effective for infusing new knowledge and updating knowledge, followed by GPT-3.5 Turbo and GPT-4o. The fine-tuning APIs for Gemini 1.5 Flesh and Gemini 1.5 Pro are unable to learn new knowledge or update existing knowledge. These findings underscore a major shortcoming in using current commercial fine-tuning services to achieve reliable knowledge infusion in common scenarios. We open source the FineTuneBench dataset at https://github.com/kevinwu23/StanfordFineTuneBench.

  • 3 authors
·
Nov 7, 2024

SealQA: Raising the Bar for Reasoning in Search-Augmented Language Models

We introduce SealQA, a new challenge benchmark for evaluating SEarch-Augmented Language models on fact-seeking questions where web search yields conflicting, noisy, or unhelpful results. SealQA comes in three flavors: (1) Seal-0 (main) and (2) Seal-Hard, which assess factual accuracy and reasoning capabilities, with Seal-0 focusing on the most challenging questions where chat models (e.g., GPT-4.1) typically achieve near-zero accuracy; and (3) LongSeal, which extends SealQA to test long-context, multi-document reasoning in "needle-in-a-haystack" settings. Our evaluation reveals critical limitations in current models: Even frontier LLMs perform poorly across all SealQA flavors. On Seal-0, frontier agentic models equipped with tools like o3 and o4-mini achieve only 17.1% and 6.3% accuracy, respectively, at their best reasoning efforts. We find that advanced reasoning models such as DeepSeek-R1-671B and o3-mini are highly vulnerable to noisy search results. Notably, increasing test-time compute does not yield reliable gains across o3-mini, o4-mini, and o3, with performance often plateauing or even declining early. Additionally, while recent models are less affected by the "lost-in-the-middle" issue, they still fail to reliably identify relevant documents in LongSeal when faced with numerous distractors. To facilitate future work, we release SealQA at huggingface.co/datasets/vtllms/sealqa.

  • 6 authors
·
Jun 1, 2025 2

Frontier-Eng: Benchmarking Self-Evolving Agents on Real-World Engineering Tasks with Generative Optimization

Current LLM agent benchmarks, which predominantly focus on binary pass/fail tasks such as code generation or search-based question answering, often neglect the value of real-world engineering that is often captured through the iterative optimization of feasible designs. To this end, we introduce Frontier-Eng, a human-verified benchmark for generative optimization -- an iterative propose-execute-evaluate loop in which an agent generates candidate artifacts, receives executable verifier feedback, and revises them under a fixed interaction budget -- spanning 47 tasks across five broad engineering categories. Unlike previous suites, Frontier-Eng tasks are grounded in industrial-grade simulators and verifiers that provide continuous reward signals and enforce hard feasibility constraints under constrained budgets. We evaluate eight frontier language models using representative search frameworks, finding that while Claude 4.6 Opus achieves the most robust performance, the benchmark remains challenging for all models. Our analysis suggests a dual power-law decay in improvement frequency (sim 1/iteration) and magnitude (sim 1/improvement count). We further show that although width improves parallelism and diversity, depth remains crucial for hard-won improvements under a fixed budget. Frontier-Eng establishes a new standard for assessing the capacity of AI agents to integrate domain knowledge with executable feedback to solve complex, open-ended engineering problems.

  • 21 authors
·
Apr 13

Floor, Ceiling, and the Fusion Gap: How Much of Crowd Reading Attention Can Machines Predict?

A benchmark score means nothing without knowing what a trivial method achieves and what the best possible method could achieve. We construct both bounds for a task with a rare kind of ground truth: predicting which sentences a crowd of readers -- highlighting for their own purposes, unpaid, uninstructed, and blind to each other -- marked in 120 web documents. The floor is naive truncation (lead); the ceiling is a split-half oracle: half the crowd predicting the other half. The gap between them is +0.2028 AP [+0.1698, +0.2342, domain-clustered], and three findings structure it. First, the gap is semantic: position and length features recover 5% of it. Second, frontier language models reach 35-53% of it zero-shot -- far above classical baselines, far below the crowd; a state-of-the-art prompt compressor (LLMLingua-2) lands below the floor, indistinguishable from random selection. Third, an unweighted cross-vendor fusion of five frontier rankings plus a position prior reaches 60%, beating the best single model by +0.0159 [+0.0044, +0.0269; Holm p=0.019] -- a gain that survives ablation of its best member, split-half arm selection, prompt paraphrase, and label, gate, and seed perturbations, and was CONFIRMED by a pre-registered replication on 217 independent documents (+0.0179, Holm p=0.042). Finally, the bracket compresses: distilling the fusion into one open-weight 8B student that reads the whole document retains 90% of the fusion's edge and reaches statistical parity with the strongest single frontier model (+0.0070 [-0.0068, +0.0200]), where a local-context student retains only 63% -- the crowd's signal lives in document-level structure, and the cheapest known improvement is to ask several different models and average.

  • 2 authors
·
Aug 2

DataComp-LM: In search of the next generation of training sets for language models

We introduce DataComp for Language Models (DCLM), a testbed for controlled dataset experiments with the goal of improving language models. As part of DCLM, we provide a standardized corpus of 240T tokens extracted from Common Crawl, effective pretraining recipes based on the OpenLM framework, and a broad suite of 53 downstream evaluations. Participants in the DCLM benchmark can experiment with data curation strategies such as deduplication, filtering, and data mixing at model scales ranging from 412M to 7B parameters. As a baseline for DCLM, we conduct extensive experiments and find that model-based filtering is key to assembling a high-quality training set. The resulting dataset, DCLM-Baseline enables training a 7B parameter language model from scratch to 64% 5-shot accuracy on MMLU with 2.6T training tokens. Compared to MAP-Neo, the previous state-of-the-art in open-data language models, DCLM-Baseline represents a 6.6 percentage point improvement on MMLU while being trained with 40% less compute. Our baseline model is also comparable to Mistral-7B-v0.3 and Llama 3 8B on MMLU (63% & 66%), and performs similarly on an average of 53 natural language understanding tasks while being trained with 6.6x less compute than Llama 3 8B. Our results highlight the importance of dataset design for training language models and offer a starting point for further research on data curation.

  • 59 authors
·
Jun 17, 2024 4

LAB-Bench: Measuring Capabilities of Language Models for Biology Research

There is widespread optimism that frontier Large Language Models (LLMs) and LLM-augmented systems have the potential to rapidly accelerate scientific discovery across disciplines. Today, many benchmarks exist to measure LLM knowledge and reasoning on textbook-style science questions, but few if any benchmarks are designed to evaluate language model performance on practical tasks required for scientific research, such as literature search, protocol planning, and data analysis. As a step toward building such benchmarks, we introduce the Language Agent Biology Benchmark (LAB-Bench), a broad dataset of over 2,400 multiple choice questions for evaluating AI systems on a range of practical biology research capabilities, including recall and reasoning over literature, interpretation of figures, access and navigation of databases, and comprehension and manipulation of DNA and protein sequences. Importantly, in contrast to previous scientific benchmarks, we expect that an AI system that can achieve consistently high scores on the more difficult LAB-Bench tasks would serve as a useful assistant for researchers in areas such as literature search and molecular cloning. As an initial assessment of the emergent scientific task capabilities of frontier language models, we measure performance of several against our benchmark and report results compared to human expert biology researchers. We will continue to update and expand LAB-Bench over time, and expect it to serve as a useful tool in the development of automated research systems going forward. A public subset of LAB-Bench is available for use at the following URL: https://huggingface.co/datasets/futurehouse/lab-bench

  • 9 authors
·
Jul 14, 2024 2

LongHarness Bench: Stress-Testing Language Model Harnesses for Long-Context Reasoning

Language-model (LM) harnesses enable LMs to operate effectively over long contexts using additional compute. However, existing long-context evaluations are insufficient for distinguishing modern harnesses, reflected by saturated accuracy across harnesses and largely similar evaluation costs. In this paper, we introduce a benchmark for evaluating both the effectiveness and efficiency of long-context harnesses. Our tasks require diverse retrieval strategies, including lexical search and semantic matching, together with strategic and adaptive reasoning over global and local context. Much of the context is semantically relevant but only a small subset is useful at each step, creating both a challenging search problem and different accuracy--cost tradeoffs across processing strategies. For example, one task requires identifying every person satisfying several conditions using evidence scattered across documents; strategically checking the most selective condition first can narrow the search before verifying the remaining conditions. We evaluate multiple families of frontier language models with four state-of-the-art harnesses. Our benchmarks remain challenging even for strong model--harness combinations: the best reaches 68\% macro-average accuracy across four evaluation suites. More importantly, we find that the same underlying model can exhibit markedly different efficiency under different harnesses. Our results establish efficiency as an important axis for long-context evaluation and provide a testbed for developing harnesses that process context strategically rather than exhaustively.

  • 4 authors
·
Sep 28

The Router Within: Eliciting Native Skill Routing from a Frozen LLM

Skills extend an LLM agent beyond its parametric knowledge, and the gain they promise rests on picking the right one. Deployed harnesses route by preloading every skill's metadata into the context, which disperses the agent's attention and caps the library size. Retrieval pipelines move the selection out of the context, but also out of the agent's capability. We show that the frozen agent LLM already carries the routing signal in its own forward passes, and that two linear maps suffice to read it out with no skill text in the context. Gavel (Glance And Verdict from a frozen LLM) reads it in two steps. A glance projects the task's and each skill's mid-layer states through the two maps, the only parameters trained, and scores the full library against compact per-skill banks that one forward pass builds at installation. A verdict then resumes the shortlisted skills' forward passes and reads the model's own likelihood and yes/no judgment, fused with the glance as a product of experts. Trained once, Gavel transfers zero-shot to three public benchmarks and SkillTraj, our new benchmark of 372 simulated agent trajectories. On Qwen3-32B it outperforms progressive disclosure and retrieve-and-rerank pipelines that add 1.2B to 16B external parameters, by up to 13.4 points on written tasks and up to 21.9 when the need for a skill arises mid-rollout. Routing accuracy improves as the backbone does, and in a bash-agent harness the same 32B triggers the correct skill on Skill-Use more often than far larger frontier models running in Codex.

Separating Constraint Compliance from Semantic Accuracy: A Novel Benchmark for Evaluating Instruction-Following Under Compression

Large language models (LLMs) exhibit degraded performance under prompt compression, but the mechanisms remain poorly understood. We introduce the Compression-Decay Comprehension Test (CDCT), a benchmark that independently measures constraint compliance (CC) and semantic accuracy (SA) across compression levels. We evaluate 9 frontier LLMs across 8 concepts using 5 compression levels from extreme (c=0.0, ~2 words) to none (c=1.0, ~135 words). A three-judge LLM jury achieves almost perfect inter-rater agreement on CC (Fleiss' appa=0.90). We observe a universal U-curve pattern in constraint compliance (97.2% prevalence), with violations peaking at medium compression (c=0.5, ~27 words). Counterintuitively, models perform better at extreme compression than medium lengths. The dimensions are statistically orthogonal (r=0.193, p=0.084), with constraint effects 2.9x larger than semantic effects. Experimental validation via RLHF ablation confirms our constraint salience hypothesis: removing "helpfulness" signals improves CC by 598% on average (71/72 trials, p<0.001), with 79% achieving perfect compliance. This demonstrates that RLHF-trained helpfulness behaviors are the dominant cause of constraint violations at medium compression. Reasoning models outperform efficient models by 27.5% (Cohen's d=0.96). Our findings reveal a fundamental tension between RLHF alignment and instruction-following, providing actionable guidelines for improving deployed systems.

  • 1 authors
·
Dec 2, 2025

Exploration Structure in LLM Agents for Multi-File Change Localization

Software engineering tools increasingly rely on LLM based agents to localize files to change to resolve a software issue. Most AI agents explore repositories linearly, that is, visiting one directory or file per step. We postulate that this is a structural mismatch for changes that span several subsystems. We compare linear sequential exploration against non-linear, domain-scoped parallel agentic exploration. Using SWE Bench Pro as initial benchmark, we focus on ansible as an exemplar. We construct an approach for persistent-session evaluation of GitHub issues anchored at a single base commit. We compare our non-linear domain-agent file traversal system against a base LLM without direct repository access, a single agent Recursive Language Model (RLM) baseline with a persistent Python REPL and an external CLI baseline using Codex 5.5 High. Domain scoped parallel agent spawning with a small Haiku-class model achieves the highest micro F1 among Haiku class models by a large margin. Domain-agents is the second highest behind only the much larger Codex 5.5 High on our own expanded benchmark including over more recent PRs from 2025 and 2026. On the original, curated, 2020 SWE-bench Pro benchmark, a larger Sonnet plain LLM baseline attains higher micro F1 by predicting few files, leading to higher precision, but at significantly lower all gold recall. We also present three additional findings. First, documentation evolution is a latent dependency unresolved by any approach. Second, naive file system access can degrade localization driven by test-file over prediction. Lastly, forced multi-agent consultation does not measurably help and raises token cost substantially.

  • 4 authors
·
Jun 9

Building Production-Ready Probes For Gemini

Frontier language model capabilities are improving rapidly. We thus need stronger mitigations against bad actors misusing increasingly powerful systems. Prior work has shown that activation probes may be a promising misuse mitigation technique, but we identify a key remaining challenge: probes fail to generalize under important production distribution shifts. In particular, we find that the shift from short-context to long-context inputs is difficult for existing probe architectures. We propose several new probe architecture that handle this long-context distribution shift. We evaluate these probes in the cyber-offensive domain, testing their robustness against various production-relevant shifts, including multi-turn conversations, static jailbreaks, and adaptive red teaming. Our results demonstrate that while multimax addresses context length, a combination of architecture choice and training on diverse distributions is required for broad generalization. Additionally, we show that pairing probes with prompted classifiers achieves optimal accuracy at a low cost due to the computational efficiency of probes. These findings have informed the successful deployment of misuse mitigation probes in user-facing instances of Gemini, Google's frontier language model. Finally, we find early positive results using AlphaEvolve to automate improvements in both probe architecture search and adaptive red teaming, showing that automating some AI safety research is already possible.

  • 7 authors
·
Jan 16 3

Benchmarking at the Edge of Comprehension

As frontier Large Language Models (LLMs) increasingly saturate new benchmarks shortly after they are published, benchmarking itself is at a juncture: if frontier models keep improving, it will become increasingly hard for humans to generate discriminative tasks, provide accurate ground-truth answers, or evaluate complex solutions. If benchmarking becomes infeasible, our ability to measure any progress in AI is at stake. We refer to this scenario as the post-comprehension regime. In this work, we propose Critique-Resilient Benchmarking, an adversarial framework designed to compare models even when full human understanding is infeasible. Our technique relies on the notion of critique-resilient correctness: an answer is deemed correct if no adversary has convincingly proved otherwise. Unlike standard benchmarking, humans serve as bounded verifiers and focus on localized claims, which preserves evaluation integrity beyond full comprehension of the task. Using an itemized bipartite Bradley-Terry model, we jointly rank LLMs by their ability to solve challenging tasks and to generate difficult yet solvable questions. We showcase the effectiveness of our method in the mathematical domain across eight frontier LLMs, showing that the resulting scores are stable and correlate with external capability measures. Our framework reformulates benchmarking as an adversarial generation-evaluation game in which humans serve as final adjudicators.

  • 11 authors
·
Feb 15

Pre-review to Peer review: Pitfalls of Automating Reviews using Large Language Models

Large Language Models are versatile general-task solvers, and their capabilities can truly assist people with scholarly peer review as pre-review agents, if not as fully autonomous peer-review agents. While incredibly beneficial, automating academic peer-review, as a concept, raises concerns surrounding safety, research integrity, and the validity of the academic peer-review process. The majority of the studies performing a systematic evaluation of frontier LLMs generating reviews across science disciplines miss the mark on addressing the alignment/misalignment of reviews along with the utility of LLM generated reviews when compared against publication outcomes such as Citations, Hit-papers, Novelty, and Disruption. This paper presents an experimental study in which we gathered ground-truth reviewer ratings from OpenReview and used various frontier open-weight LLMs to generate reviews of papers to gauge the safety and reliability of incorporating LLMs into the scientific review pipeline. Our findings demonstrate the utility of frontier open-weight LLMs as pre-review screening agents despite highlighting fundamental misalignment risks when deployed as autonomous reviewers. Our results show that all models exhibit weak correlation with human peer reviewers (0.15), with systematic overestimation bias of 3-5 points and uniformly high confidence scores (8.0-9.0/10) despite prediction errors. However, we also observed that LLM reviews correlate more strongly with post-publication metrics than with human scores, suggesting potential utility as pre-review screening tools. Our findings highlight the potential and address the pitfalls of automating peer reviews with language models. We open-sourced our dataset D_{LMRSD} to help the research community expand the safety framework of automating scientific reviews.

  • 3 authors
·
Dec 14, 2025

MLGym: A New Framework and Benchmark for Advancing AI Research Agents

We introduce Meta MLGym and MLGym-Bench, a new framework and benchmark for evaluating and developing LLM agents on AI research tasks. This is the first Gym environment for machine learning (ML) tasks, enabling research on reinforcement learning (RL) algorithms for training such agents. MLGym-bench consists of 13 diverse and open-ended AI research tasks from diverse domains such as computer vision, natural language processing, reinforcement learning, and game theory. Solving these tasks requires real-world AI research skills such as generating new ideas and hypotheses, creating and processing data, implementing ML methods, training models, running experiments, analyzing the results, and iterating through this process to improve on a given task. We evaluate a number of frontier large language models (LLMs) on our benchmarks such as Claude-3.5-Sonnet, Llama-3.1 405B, GPT-4o, o1-preview, and Gemini-1.5 Pro. Our MLGym framework makes it easy to add new tasks, integrate and evaluate models or agents, generate synthetic data at scale, as well as develop new learning algorithms for training agents on AI research tasks. We find that current frontier models can improve on the given baselines, usually by finding better hyperparameters, but do not generate novel hypotheses, algorithms, architectures, or substantial improvements. We open-source our framework and benchmark to facilitate future research in advancing the AI research capabilities of LLM agents.

  • 17 authors
·
Feb 20, 2025 4

MedHELM: Holistic Evaluation of Large Language Models for Medical Tasks

While large language models (LLMs) achieve near-perfect scores on medical licensing exams, these evaluations inadequately reflect the complexity and diversity of real-world clinical practice. We introduce MedHELM, an extensible evaluation framework for assessing LLM performance for medical tasks with three key contributions. First, a clinician-validated taxonomy spanning 5 categories, 22 subcategories, and 121 tasks developed with 29 clinicians. Second, a comprehensive benchmark suite comprising 35 benchmarks (17 existing, 18 newly formulated) providing complete coverage of all categories and subcategories in the taxonomy. Third, a systematic comparison of LLMs with improved evaluation methods (using an LLM-jury) and a cost-performance analysis. Evaluation of 9 frontier LLMs, using the 35 benchmarks, revealed significant performance variation. Advanced reasoning models (DeepSeek R1: 66% win-rate; o3-mini: 64% win-rate) demonstrated superior performance, though Claude 3.5 Sonnet achieved comparable results at 40% lower estimated computational cost. On a normalized accuracy scale (0-1), most models performed strongly in Clinical Note Generation (0.73-0.85) and Patient Communication & Education (0.78-0.83), moderately in Medical Research Assistance (0.65-0.75), and generally lower in Clinical Decision Support (0.56-0.72) and Administration & Workflow (0.53-0.63). Our LLM-jury evaluation method achieved good agreement with clinician ratings (ICC = 0.47), surpassing both average clinician-clinician agreement (ICC = 0.43) and automated baselines including ROUGE-L (0.36) and BERTScore-F1 (0.44). Claude 3.5 Sonnet achieved comparable performance to top models at lower estimated cost. These findings highlight the importance of real-world, task-specific evaluation for medical use of LLMs and provides an open source framework to enable this.

  • 81 authors
·
Jun 1, 2025