Daily Papers

How should demonstration quality be used during vision-language-action (VLA) pretraining to improve performance after target-task fine-tuning? We compare weighting, filtering, and conditioning across reward definitions and label granularities using 5,000 naturally suboptimal human demonstrations and 24 target tasks. Within each VLA, we match demonstrations and training budgets. Additional comparisons examine pretraining data size and the roles of quality tags during fine-tuning and inference. Across three VLAs, we find that approach-aware episode conditioning improves mean success over plain behavioral cloning; conditioning and filtering favor episode and chunk labels, respectively, on average, with model-dependent reversals; and constant-tag fine-tuning improves mean success after conditioned pretraining with either tagged or untagged inference. We introduce AXIS-Bench to support these controlled comparisons. Built on crowdsourced simulation demonstrations, it provides recorded object and contact states for recomputing quality labels on shared trajectories. Replayable trajectories support workspace-aligned rendering and user-defined real-world target tasks. In our real-world experiment, simulation pretraining raises success from 9.6\% to 31.7\%. Project page: https://axis-bench.github.io/.

Principle-based regulation, with evaluative standards such as "fair, clear, and not misleading" or "deliver good outcomes", cannot be reduced to binary predicates, and LLM-as-judge is increasingly used as the substitute. Our position is that any such judge must be evaluated on four axes: accuracy, paraphrase robustness, adversarial robustness, and calibration. We release Principle-Bench, 168 cryptoasset financial-promotion scenarios mapped to two UK FCA principles, with paraphrase, adversarial keyword-stuffing, and boundary perturbations authored under a pre-registered rubric; the first benchmark covering all four axes for principle-based regulation. We also introduce Ceca (Calibrated Exemplar-Cluster Assessment): a calibrated, auditable assessor that emits exact per-exemplar counterfactual attributions. Across keyword counting, three sentence-transformer embedders, an open-weight LLM-judge, and a calibrated cascade, no method dominates all four axes. A 120B LLM-judge, strongest on benign inputs, loses 47 accuracy points (0.74 to 0.27) on keyword-stuffed Consumer Duty inputs: "compliance theatre." A second judge from a different model family agrees only at Cohen's kappa = 0.16 on that split, localising the failure to the model rather than the corpus. Any deployment-grade LLM-judge for principle-based regulation must report per-principle adversarial deception and post-hoc calibration alongside aggregate accuracy.

Recent music audio-language models achieve high accuracy on instrument question-answering benchmarks, but it remains unclear whether this reflects robust audio grounding or benchmark-specific shortcuts. In this paper, we introduce an OpenMIC-derived diagnostic benchmark sequence for instrument grounding in music audio-language models, extending binary instrument-presence QA to genre-prior-reduced examples, confusable instrument discrimination, longer audio context, and temporal localization. Across these settings, high binary QA accuracy often fails to predict model behavior: models can exhibit option-position bias, confusable-instrument errors, and temporal response bias. These results suggest that instrument grounding should be evaluated with multi-axis diagnostic benchmarks rather than a single aggregate accuracy.

Existing multimodal retrieval benchmarks largely emphasize semantic matching on daily-life images and offer limited diagnostics of professional knowledge and complex reasoning. To address this gap, we introduce ARK, a benchmark designed to analyze multimodal retrieval from two complementary perspectives: (i) knowledge domains (five domains with 17 subtypes), which characterize the content and expertise retrieval relies on, and (ii) reasoning skills (six categories), which characterize the type of inference over multimodal evidence required to identify the correct candidate. Specifically, ARK evaluates retrieval with both unimodal and multimodal queries and candidates, covering 16 heterogeneous visual data types. To avoid shortcut matching during evaluation, most queries are paired with targeted hard negatives that require multi-step reasoning. We evaluate 23 representative text-based and multimodal retrievers on ARK and observe a pronounced gap between knowledge-intensive and reasoning-intensive retrieval, with fine-grained visual and spatial reasoning emerging as persistent bottlenecks. We further show that simple enhancements such as re-ranking and rewriting yield consistent improvements, but substantial headroom remains.

Pixel-based reinforcement learning agents often fail under purely visual distribution shift even when latent dynamics and rewards are unchanged, but existing benchmarks entangle multiple sources of shift and hinder systematic analysis. We introduce KAGE-Env, a JAX-native 2D platformer that factorizes the observation process into independently controllable visual axes while keeping the underlying control problem fixed. By construction, varying a visual axis affects performance only through the induced state-conditional action distribution of a pixel policy, providing a clean abstraction for visual generalization. Building on this environment, we define KAGE-Bench, a benchmark of six known-axis suites comprising 34 train-evaluation configuration pairs that isolate individual visual shifts. Using a standard PPO-CNN baseline, we observe strong axis-dependent failures, with background and photometric shifts often collapsing success, while agent-appearance shifts are comparatively benign. Several shifts preserve forward motion while breaking task completion, showing that return alone can obscure generalization failures. Finally, the fully vectorized JAX implementation enables up to 33M environment steps per second on a single GPU, enabling fast and reproducible sweeps over visual factors. Code: https://avanturist322.github.io/KAGEBench/.

Many real-world questions over business, legal, and scientific corpora are natural-language versions of database-style queries over records latent in text. Existing retrieval-augmented generation (RAG) systems are optimized primarily for semantic relevance, but retrieving plausible passages does not guarantee correct query execution. We introduce QO-Bench, a diagnostic benchmark for query-operator question answering over typed event tuples. The benchmark covers 22,984 news articles and 614 corporate events across 18 query templates, evaluated on 785 questions. Each gold answer is deterministically computed from typed event tuples and scored by recall, with answers matched to the gold tuples by exact match rather than an LLM judge. This design enables operator-level diagnosis such as joins and intersection. We evaluate RAG, ReAct RAG, GraphRAG, and information-extraction-to-SQL under matched conditions, with a long-context oracle ceiling to isolate retrieval failure. A two-axis framework -- index-time preservation versus query-time execution -- predicts where each paradigm fails, and the results bear it out: systems retrieve relevant text but discard the typed values operators need, and the deployable paradigm ranking inverts across operators, with similarity retrieval leading on filter/project and extraction-to-SQL on intersection and counting. Even given the gold evidence, a long-context oracle stays far from saturated, so operator execution -- not retrieval alone -- is a core bottleneck that a stronger answer model does not remove. QO-Bench reframes the goal from passage relevance to query-operator-preserving retrieval.

In this paper, we introduce ScenePilot-Bench, a large-scale first-person driving benchmark designed to evaluate vision-language models (VLMs) in autonomous driving scenarios. ScenePilot-Bench is built upon ScenePilot-4K, a diverse dataset comprising 3,847 hours of driving videos, annotated with multi-granularity information including scene descriptions, risk assessments, key participant identification, ego trajectories, and camera parameters. The benchmark features a four-axis evaluation suite that assesses VLM capabilities in scene understanding, spatial perception, motion planning, and GPT-Score, with safety-aware metrics and cross-region generalization settings. We benchmark representative VLMs on ScenePilot-Bench, providing empirical analyses that clarify current performance boundaries and identify gaps for driving-oriented reasoning. ScenePilot-Bench offers a comprehensive framework for evaluating and advancing VLMs in safety-critical autonomous driving contexts.

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.

Standard benchmarks for optical flow, scene flow, and stereo vision algorithms generally focus on model accuracy rather than robustness to image corruptions like noise or rain. Hence, the resilience of models to such real-world perturbations is largely unquantified. To address this, we present RobustSpring, a comprehensive dataset and benchmark for evaluating robustness to image corruptions for optical flow, scene flow, and stereo models. RobustSpring applies 20 different image corruptions, including noise, blur, color changes, quality degradations, and weather distortions, in a time-, stereo-, and depth-consistent manner to the high-resolution Spring dataset, creating a suite of 20,000 corrupted images that reflect challenging conditions. RobustSpring enables comparisons of model robustness via a new corruption robustness metric. Integration with the Spring benchmark enables public two-axis evaluations of both accuracy and robustness. We benchmark a curated selection of initial models, observing that accurate models are not necessarily robust and that robustness varies widely by corruption type. RobustSpring is a new computer vision benchmark that treats robustness as a first-class citizen to foster models that combine accuracy with resilience. It will be available at https://spring-benchmark.org.

Generalist robot manipulation policies have developed rapidly, yet their reliable evaluation remains challenging due to fundamental flaws in existing simulation benchmarks: prominent sim-to-real gaps, narrow task coverage, and unfair evaluation caused by ambiguous training-test pipelines. Prior works only partially resolve these issues and lack simultaneous faithfulness, diversity, and fairness, while static benchmark designs fail to sustain long-term policy development. We present X2Real, an evolvable simulation benchmark for faithfully evaluating the real-world performance of robotic manipulation policies based on Nvidia Isaac Lab-Arena. Following three core principles (faithfulness, diversity, and fairness), X2Real calibrates simulation visual and physical properties to align with real hardware, achieving a 0.84 linear correlation between simulated and real-robot evaluation results. It features a comprehensive taxonomy with 10 capability dimensions and 44 hierarchical long-horizon tasks, covering basic manipulation skills and advanced capacities such as visual grounding, language understanding, and bimanual control. We further adopt multi-axis domain randomization and strictly disjoint training-evaluation pipelines to mitigate benchmark exploitation and ensure credible evaluation. Powered by a custom physical domain-specific language, the Mana simulation ecosystem supports modular task design and iterative performance analysis, alongside a nearly 300-hour annotated simulation trajectory dataset. X2Real offers a faithful, diverse, and fair evolving evaluation infrastructure, effectively bridging the sim-to-real evaluation gap and supporting the advancement of generalist robotic manipulation policies.

Large language models can generate plausible quantum code, but it is unclear whether they can reliably target the specific software development kit (SDK) version requested by the user. We study this problem as API drift and introduce quantum-api-drift, a benchmark for measuring version fidelity, defined here as execution success on the requested SDK version, cross-version compatibility, failure modes, and documentation-guided repair in LLM-generated quantum SDK code. We instantiate the benchmark with Qiskit, a representative quantum SDK that underwent substantial interface changes across v0.43, v1.3, and v2.0. We evaluate 17 models on 50 tasks with 3 samples per prompt, yielding 450 generated samples and 1,350 executions per model. Sixteen models are tested in a matched REST API setting with a 1024-token output cap, while GPT-5.4 (Codex CLI) is reported separately as a reference configuration. Across the 16 matched REST models, diagonal Pass@1 ranges from 0.02 to 0.85. Claude Opus 4.7 is strongest on v0.43 and v2.0, while Grok 4.20 is strongest on v1.3 at 0.513. Error profiles differ systematically by model strength: weaker models fail mainly with broken imports, while stronger models more often reach deprecation-level failures. Documentation-guided repair succeeds for 0.19 to 0.59 of repair attempts overall and is consistently much more effective for migration to v2.0 than to v1.3. The benchmark artifacts are publicly available at https://github.com/arasyi/quantum-api-drift. These results show that version alignment is a distinct evaluation axis for quantum code generation and that API drift remains only partly recoverable even with migration guidance.

Deformable object manipulation poses challenges beyond task completion: successful execution must also maintain safe physical interaction, holding the object stably without slip or drop while avoiding excessive deformation. However, existing manipulation benchmarks are predominantly success-oriented and rarely evaluate whether a policy remains physically safe throughout execution. We present SoftVTBench, a safety-aware visuo-tactile benchmark for physically constrained deformable object manipulation. Built in Isaac Sim with finite-element-simulated deformable objects, SoftVTBench provides multi-view RGB observations, RGB tactile sensing with marker motion, proprioception, and language instructions, and defines four matched task suites over object type (deformable vs. rigid) and variation axis (object vs. spatial). It separately reports Goal Success and Safety Success; the latter additionally requires no drop and peak deformation below a calibrated object-specific threshold, measured from policy-hidden privileged Finite Element Method (FEM) states. We implement pi0.5-based baselines under this protocol. Experiments show that success-only evaluation substantially overstates policy performance, as a large fraction of goal-completing rollouts still violate physical safety. Furthermore, incorporating tactile sensing improves Safety Success (e.g., from 21.4% to 35.6% on object-centric deformable tasks) and reduces object deformation during execution, while maintaining comparable Goal Success. SoftVTBench provides a reproducible benchmark for studying visuo-tactile deformable manipulation under physical interaction constraints.

Foundation-model policies for robotic manipulation are advancing rapidly on task success, but rigorous evaluation of whether they succeed safely is still lacking. We introduce ManiGuard, a specification-grounded framework for evaluating and improving the safety of foundation-model manipulation, comprising the ManiGuard-Bench task suite and a paired safety-annotated trajectory-generation pipeline. ManiGuard-Bench organizes six contact-rich household task families into 200 locked base tasks along a skill times constraint taxonomy, with safety specified independently of task success. Each task is evaluated under one in-distribution and four single-axis out-of-distribution perturbations that hold the safety specification fixed, giving 1,000 locked scenarios. Every rollout is runtime-checked by LTL_f-grounded automaton monitors over physics-grounded predicates rather than learned classifiers or LLM judges, in simulation and on a physical Franka platform. The pipeline pairs an automated motion-planning generator with human teleoperation, annotated by the same per-step monitor, and directly supports safety-aware fine-tuning; we release 8,000 safety-annotated demonstrations, 40 per base task. Benchmarking zero-shot and fine-tuned VLAs across more than 23,000 rollouts, we find: (i) safety must be evaluated independently of task success, as 6-21% of successful rollouts violate the specification; (ii) fine-tuning on our suite raises safe task completion from near zero to 7.5-29.8% and engaged-and-safe behavior from 16-40% to 51-72%; but (iii) a gap remains that scaling demonstrations does not close, with 21-42% of engaged rollouts still violating, two of six families below 2% safe success for every policy, and these failures persisting under distribution shift and on hardware.

Humans combine reasoning and motor control to solve complex manipulation tasks under diverse constraints. They build an understanding of the physical world that helps them convert reasoning into actions and quickly adapt to new scenes, tasks, and rules. We refer to this capability as intuitive manipulation. Existing benchmarks fail to capture this integration: they evaluate physical reasoning in isolation from execution, or measure policy performance without requiring explicit reasoning. We introduce IMBENCH, a benchmark designed to evaluate intuitive manipulation as an integrated capability spanning perception, physical reasoning, action generation, and iterative execution. Our tasks require models to infer task-relevant physical structure and generate feasible action sequences under explicit constraints, including contact-rich manipulation, tool use, and multi-stage dependencies. We introduce a benchmark of 35 tasks, 14K filtered trajectories, and scalable tools for generating diverse scenarios. Experiments reveal a consistent gap: vision language models show partial physical reasoning ability but fail to produce executable plans, while state-of-the-art vision-language-action models struggle to satisfy task constraints and generalize across scenarios. These results identify intuitive manipulation as a missing axis in current foundation models and generalist robot policies, and position IMBENCH as a step toward evaluating and enabling more integrated, adaptive physical intelligence.

Multi-view video understanding requires integrating spatial and temporal evidence across multiple, often non-overlapping camera streams: tracking entities as they transition between viewpoints, aligning events across time, and reasoning about latent 4D continuity rather than any single visible frame. We introduce MVVBench, a benchmark for multi-view video reasoning built from real world multi camera datasets. Questions are curated to be monocular-ambiguous along both the view and the temporal axis: each question is unanswerable from any single view in the designated input set, and the majority are further unanswerable from any single moment. Each question becomes uniquely solvable only by jointly reasoning across views and across time. MVVBench spans diverse dynamic scenes and probes six capabilities: implicit/explicit attribute identification, implicit/explicit relative distance, relative camera pose, and compositional counting, with human-authored QA and rigorous verification. Beyond benchmarking, we provide an extensive analysis of when and why current vision language models succeed or fail, characterizing errors due to temporal mis-localization, cross-view identity breaks, and brittle multi-hop reasoning. We then study inference-time elicitation strategies that unlock latent multi-view competence---task-specific chain-of-thought scaffolds and structured cross-view evidence aggregation---yielding substantial gains without retraining. Finally, we present preliminary evidence that reinforcement learning with verifiable rewards can elicit some latent multi-view competence in the base model, pointing to training-time approaches as a promising direction for future work. Together, MVVBench offers a rigorous evaluation of 4D multi-view reasoning and a foundation for future progress toward reliable embodied perception.

Benchmarks for vision-language models (VLMs) mostly test observational spatial reasoning: models describe relations already visible in the input. Existing what-if tasks typically vary the observer while keeping the scene fixed. Can VLMs instead predict the consequences of hypothetically moving or rotating an object? We introduce MindEdit-Bench, a benchmark of six spatial reasoning tasks built from three-photo smartphone triplets of newly captured indoor scenes via an automatic in-the-wild 3D scene-graph extraction pipeline. Four tasks probe perception and perspective transformation over observed structure; two new tasks, L4 (spatial editing) and L5 (cross-view visibility editing), probe object-level counterfactual reasoning, where correct answers are absent from all input images. Each question provides 8-24 structured answer choices, enabling answer-letter-level diagnosis of spatial and fallback errors. The benchmark covers 120 private indoor scenes not drawn from public datasets, reducing public-data pretraining-overlap risk. Across 15 VLMs on 1,003 human-verified questions, task-wise mean VLM accuracy is only 8%-31%, versus 81%-97% human majority-vote accuracy. The pooled human--best-VLM gap is 53 pp, with at least 39 pp on every task. The structured answer space further reveals non-uniform failures, including weaker camera-depth-axis inference and fallback behavior on difficult visibility-editing cases.

Recent benchmarks for VLMs largely assess single- or limited-view perception, leaving untested the core cognitive ability to integrate observations across viewpoints into a coherent, world-centric (allocentric) 3D mental model. We introduce MultiView-Bench, a diagnostic benchmark expressly designed to evaluate multi-view integration for holistic 3D scene comprehension. Unlike existing datasets that focus on pixel-level mapping or camera-relative navigation, MultiView-Bench requires models to decouple object positioning from transient perspectives and ground them in a fixed global coordinate system. This capability serves as a prerequisite for VLMs before being deployed for downstream tasks such as mechanical part assembly. Our systematic evaluation of frontier VLMs reveals consistent failure modes: strong performance on 2D planar relations from a single image, but marked difficulty with 3D spatial relations and with aggregating information across views. We further identify biases in VLMs, such as struggles with unconventional axis directions and sensitivity to object colorways and texture variations. Acknowledging these limitations, we propose ViewNavigator, which uses active viewpoint selection and evidence fusion to improve four base models by 12.3--20.0 percentage points under a six-image cap matching the fixed-view baseline; budget-extended gains are model-dependent and reach 27 percentage points for GPT-5.

Recent video generation is increasingly realistic and controllable, yet video editing remains less developed, particularly for precise local edits that must preserve the original scene dynamics. Video scene text editing replaces text on scene surfaces, such as storefront signs, whiteboards, and product labels, while preserving the surrounding content, motion, and camera dynamics. Although scene text editing is well studied for images, video scene text editing that achieves high visual quality, temporal consistency, and edit locality remains underexplored. Existing resources offer limited paired real-video data, and general video-editing metrics do not directly measure whether the requested text remains correct over time. We introduce ViTeX-Bench, a benchmark suite comprising ViTeX-Dataset and a three-axis evaluation protocol. The dataset contains 387 real-world 720p videos with text-region masks and editing instructions: 230 provide reviewed, pipeline-generated paired edits for training, and 157 form a frozen evaluation split. The protocol evaluates text correctness, visual and temporal quality, and edit locality through 13 metrics, with one primary metric per axis and a Pareto comparison of their trade-offs. OCR calibration, human evaluation, and annotation-sensitivity analyses support the interpretation of these scores. Across eight baselines from four editing families, accurate text, temporal stability, and scene preservation remain difficult to achieve together. We also release ViTeX-Edit-14B, an open-source reference editor fine-tuned on the paired training split with motion-aligned glyph-video conditioning. It achieves CharAcc 0.688, the highest mean among the evaluated video-native editors, and the lowest comparable text-crop Warp among raw editor outputs. ViTeX-Bench provides a reproducible foundation for studying these trade-offs in video scene text editing.

As the quality of optical sensors improves, there is a need for processing large-scale images. In particular, the ability of devices to capture ultra-high definition (UHD) images and video places new demands on the image processing pipeline. In this paper, we consider the task of low-light image enhancement (LLIE) and introduce a large-scale database consisting of images at 4K and 8K resolution. We conduct systematic benchmarking studies and provide a comparison of current LLIE algorithms. As a second contribution, we introduce LLFormer, a transformer-based low-light enhancement method. The core components of LLFormer are the axis-based multi-head self-attention and cross-layer attention fusion block, which significantly reduces the linear complexity. Extensive experiments on the new dataset and existing public datasets show that LLFormer outperforms state-of-the-art methods. We also show that employing existing LLIE methods trained on our benchmark as a pre-processing step significantly improves the performance of downstream tasks, e.g., face detection in low-light conditions. The source code and pre-trained models are available at https://github.com/TaoWangzj/LLFormer.

The rapid development of generative models has made it increasingly crucial to develop detectors that can reliably detect synthetic images. Although most of the work has now focused on cross-generator generalization, we argue that this viewpoint is too limited. Detecting synthetic images involves another equally important challenge: generalization across visual domains. To bridge this gap,we present the OmniGen Benchmark. This comprehensive evaluation dataset incorporates 12 state-of-the-art generators, providing a more realistic way of evaluating detector performance under realistic conditions. In addition, we introduce a new method, FusionDetect, aimed at addressing both vectors of generalization. FusionDetect draws on the benefits of two frozen foundation models: CLIP & Dinov2. By deriving features from both complementary models,we develop a cohesive feature space that naturally adapts to changes in both thecontent and design of the generator. Our extensive experiments demonstrate that FusionDetect delivers not only a new state-of-the-art, which is 3.87% more accurate than its closest competitor and 6.13% more precise on average on established benchmarks, but also achieves a 4.48% increase in accuracy on OmniGen,along with exceptional robustness to common image perturbations. We introduce not only a top-performing detector, but also a new benchmark and framework for furthering universal AI image detection. The code and dataset are available at http://github.com/amir-aman/FusionDetect

LLM-based agents are increasingly expected to handle real-world assistant tasks, yet existing benchmarks typically evaluate them under isolated sources of difficulty, such as a single environment or fully specified instructions. This leaves a substantial gap between current evaluation settings and the compositional challenges that arise in practical deployment. To address this gap, we introduce LiveClawBench, a benchmark to evaluate LLM agents on real-world assistant tasks. Based on an analysis of various real OpenClaw usage cases, we derive a Triple-Axis Complexity Framework that characterizes task difficulty along three dimensions: Environment Complexity, Cognitive Demand, and Runtime Adaptability. Guided by this framework, we construct a pilot benchmark with explicit complexity-factor annotations, covering real-world assistant tasks with compositional difficulty. Together, the framework and benchmark provide a principled foundation for evaluating LLM agents in realistic assistant settings, and establish a basis for future expansion across task domains and complexity axes. We are continuing to enrich our case collections to achieve more comprehensive domain and complexity coverage. The project page is at https://github.com/Mosi-AI/LiveClawBench.

Learning effective robot manipulation policies requires diverse, high-quality demonstrations, yet existing data pipelines are often difficult to scale because they rely on specialized hardware, centralized operators, or fixed task suites. We present AXIS, a growable community-driven data engine and benchmark for scalable robot learning, which enables browser-based teleoperation for large-scale demonstration collection, automatically generates and validates new manipulation tasks, and transforms community-collected demonstrations into training-ready data through automated success checking, quality filtering, trajectory smoothing, and visual and physics-based augmentation. The AXIS dataset currently contains 207 diverse tasks and 50K+ trajectories. Meanwhile, AXIS organizes data into task snapshots and evaluates policies with a systematic held-out protocol. We compare vision-language-action (VLA) policies under a unified AXIS evaluation suite and analyze scaling behavior across different data volumes. Continual pretraining on AXIS substantially improves the overall success rate of π_{0.5} by 5.8%, outperforms the model pretrained on RoboCasa365 by 37.3%, and exhibits consistent scaling with increasing data volume, with the largest gains observed under layout, sensor-noise, and camera perturbations.

Tactile sensing provides contact information that can be difficult to infer from vision alone, but tactile hardware for dexterous hands has not converged to a common design. Dexterous hands differ in finger structure, contact surfaces, and sensor layouts, while simulated tactile signals still differ from measurements produced by physical sensors. These factors make it difficult to study visuo-tactile manipulation across diverse dexterous hands within a consistent experimental setting. We present Bench2Dex, a simulation benchmark for visuo-tactile bimanual manipulation across 12 dexterous hands. We adapt existing robot models with a shared simulated tactile interface that converts local contact geometry into image-like tactile observations. The interface provides a consistent observation format across different hand morphologies without attempting to reproduce the output of a specific physical tactile sensor. Bench2Dex includes 26 bimanual manipulation tasks that involve tool use, articulated-object interaction, and multi-stage manipulation, together with about 1.3K human-teleoperated demonstrations. The benchmark provides synchronized visual, tactile, proprioceptive, action, and object-state observations, together with executable task metrics. For robustness, we group seven perturbation types into invariance axis, where the correct action does not change, and equivariance axis, where the correct action changes together with the perturbation. We evaluate ACT, Diffusion Policy, pi0.5, and GR00T N1.5 on Bench2Dex and report their performance and failure modes. Bench2Dex is meant as a platform for studying visuo-tactile learning across dexterous hands. It does not assume that simulated tactile observations can replace real tactile sensing; it offers a shared setting for algorithm development while tactile hardware and simulation models are still evolving.

Safety-aligned language models often refuse a harmful request stated directly but answer the same request inside a role-play or narrative wrapper. We measure this vulnerability across languages and registers: attack success on Qwen3-1.7B is already 89.4% in English and 93.0% in modern Chinese, and reaches 95.7% in Classical Chinese. We build GUISE, a benchmark for systematically studying this vulnerability. It includes parallel requests in English, modern Chinese, and Classical Chinese, matched harmful and benign pairs, wrapper types held out for evaluation, and a stricter criterion that counts warn-then-answer responses as attack successes. Representation analysis shows that language and register move harmful-request representations only slightly away from the model's refusal direction, whereas narrative wrappers move them much farther away. We propose AXIS, which combines preference optimisation with a rotation objective that aligns harmful-request representations with the refusal direction and a commitment objective that trains the model to refuse completely rather than produce a warn-then-answer response. Across Qwen3-1.7B, Qwen3-4B and GLM-4-9B, AXIS achieves the highest combined safety and usability score among the compared methods.

Transformer-based methods have demonstrated excellent performance on super-resolution visual tasks, surpassing conventional convolutional neural networks. However, existing work typically restricts self-attention computation to non-overlapping windows to save computational costs. This means that Transformer-based networks can only use input information from a limited spatial range. Therefore, a novel Hybrid Multi-Axis Aggregation network (HMA) is proposed in this paper to exploit feature potential information better. HMA is constructed by stacking Residual Hybrid Transformer Blocks(RHTB) and Grid Attention Blocks(GAB). On the one side, RHTB combines channel attention and self-attention to enhance non-local feature fusion and produce more attractive visual results. Conversely, GAB is used in cross-domain information interaction to jointly model similar features and obtain a larger perceptual field. For the super-resolution task in the training phase, a novel pre-training method is designed to enhance the model representation capabilities further and validate the proposed model's effectiveness through many experiments. The experimental results show that HMA outperforms the state-of-the-art methods on the benchmark dataset. We provide code and models at https://github.com/korouuuuu/HMA.

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.

Recent progress on Transformers and multi-layer perceptron (MLP) models provide new network architectural designs for computer vision tasks. Although these models proved to be effective in many vision tasks such as image recognition, there remain challenges in adapting them for low-level vision. The inflexibility to support high-resolution images and limitations of local attention are perhaps the main bottlenecks. In this work, we present a multi-axis MLP based architecture called MAXIM, that can serve as an efficient and flexible general-purpose vision backbone for image processing tasks. MAXIM uses a UNet-shaped hierarchical structure and supports long-range interactions enabled by spatially-gated MLPs. Specifically, MAXIM contains two MLP-based building blocks: a multi-axis gated MLP that allows for efficient and scalable spatial mixing of local and global visual cues, and a cross-gating block, an alternative to cross-attention, which accounts for cross-feature conditioning. Both these modules are exclusively based on MLPs, but also benefit from being both global and `fully-convolutional', two properties that are desirable for image processing. Our extensive experimental results show that the proposed MAXIM model achieves state-of-the-art performance on more than ten benchmarks across a range of image processing tasks, including denoising, deblurring, deraining, dehazing, and enhancement while requiring fewer or comparable numbers of parameters and FLOPs than competitive models. The source code and trained models will be available at https://github.com/google-research/maxim.

Object orientation understanding represents a fundamental challenge in visual perception critical for applications like robotic manipulation and augmented reality. Current vision-language benchmarks fail to isolate this capability, often conflating it with positional relationships and general scene understanding. We introduce DORI (Discriminative Orientation Reasoning Intelligence), a comprehensive benchmark establishing object orientation perception as a primary evaluation target. DORI assesses four dimensions of orientation comprehension: frontal alignment, rotational transformations, relative directional relationships, and canonical orientation understanding. Through carefully curated tasks from 11 datasets spanning 67 object categories across synthetic and real-world scenarios, DORI provides insights on how multi-modal systems understand object orientations. Our evaluation of 15 state-of-the-art vision-language models reveals critical limitations: even the best models achieve only 54.2% accuracy on coarse tasks and 33.0% on granular orientation judgments, with performance deteriorating for tasks requiring reference frame shifts or compound rotations. These findings demonstrate the need for dedicated orientation representation mechanisms, as models show systematic inability to perform precise angular estimations, track orientation changes across viewpoints, and understand compound rotations - suggesting limitations in their internal 3D spatial representations. As the first diagnostic framework specifically designed for orientation awareness in multimodal systems, DORI offers implications for improving robotic control, 3D scene reconstruction, and human-AI interaction in physical environments. DORI data: https://huggingface.co/datasets/appledora/DORI-Benchmark

We introduce SWE-Interact, a new testbed for evaluating coding agents on multi-turn, interactive, user-driven software engineering tasks. Existing frontier SWE benchmarks typically provide complete requirements upfront and evaluate agents on autonomous implementation. In contrast, SWE-Interact places agents in a realistic developer workflow: a carefully designed user simulator starts with vague or incomplete instructions, progressively reveals requirements, inspects the agent's workspace, and provides targeted feedback, revisions, and new constraints until the full task goal has been handed off. Grounded in large-scale studies of real coding-agent interactions, this setup tests whether agents can discover user intent, adapt to evolving requirements, and build on their own prior work. Across a suite of frontier and open-weight models, we find that strong performance on single-turn SWE tasks does not reliably transfer to multi-turn, user-driven workflows: the best-performing models solve roughly 50% of single-turn baseline tasks but only 25% of the corresponding SWE-Interact tasks. The strongest models in our evaluation, including Opus 4.8 and GPT 5.5, start strong even in the face of vague initial instructions, persevere until all the requirements are surfaced by the user, integrate them better and write clean code. However, they still suffer from over-agentic coding, forgetting requirements and technical mistakes. Weaker models start poorly under ambiguity, give up early, forget or ignore instructions and rework their code more. Overall, SWE-Interact measures an orthogonal, real-world capability axis for frontier model development: interactive goal discovery and iterative refinement with a user in the loop.

Informational completeness (IC) guarantees that an inverse exists, not that it is statistically well conditioned. For minimal rank-one Weyl--Heisenberg (WH) measurements, covariance makes the nonidentity projector-Gram spectrum proportional to the fiducial's ambiguity intensities, with eigenvalues \(d|χ_ϕ(u)|^2\), turning stability into an explicit worst-direction design problem; write \(λ\) for its smallest nonidentity eigenvalue. Haar fiducials are IC almost surely while \(\mathbb E[λ^{-1}]=\infty\), and an explicit geometric family used to establish balanced informationally complete measurements in every dimension has a normalized spectral floor bounded above by an exponentially decaying envelope. We then construct a hierarchy of minimal measurements. A cyclic family with exactly \(d^2\) outcomes in every integer dimension has floors \(Θ(d^{-3})\) for odd \(d\) and \(Θ(d^{-5})\) for even \(d\); a finite-field family for \(q=2^m\) obeys the uniform bound \(λ\ge4/9\). Our main result treats every prime-power dimension of characteristic \(p\ge5\). A balanced one-coordinate perturbation repairs the zero ambiguity axis of a cubic Alltop state, gives an attained floor uniformly bounded below by a positive constant, and confines the entire nonidentity spectrum to \([L_q,U_q]\) with \(U_q/L_q\to1\). Its SIC-normalized minimum tends to one, and \(λ(ϕ_q)/Λ_q^\star\to1\) for the global finite-field WH max--min optimum \(Λ_q^\star\), without assuming SIC existence. The complete spectrum determines the exact finite-sample Hilbert--Schmidt error of canonical linear inversion at \(I/d\), while its lower edge controls local Fisher efficiency and canonical-shadow bounds.

Humans perceive far more in a scene than what is explicitly depicted: a single glance captures past causes and future trajectories; a quick peek determines if a vehicle can fit between two parked cars; a few seconds of video reveals who holds authority in a room; and a fleeting clip highlights subtle abstract patterns like unwritten rules or hidden labels. This capacity reflects a form of humanity's sixth sense: an intuitive reasoning mechanism that recovers implicit information beyond raw sensory perception. Crucially, this rapid, zero-shot visual intuition underpins everyday navigation and social interaction, making it a vital capability for Multimodal Large Language Models (MLLMs) deployed alongside people. Existing visual benchmarks, however, target either deliberate expert-level analysis in academic and mathematical domains or low-level perception, leaving the intuitive reasoning that people perform largely untested. To bridge this gap, we introduce Humanity's Sixth Sense (HSS), a benchmark for intuitive visual reasoning. HSS spans diverse image and video inputs, organizes items under a structured taxonomy, and pairs each with human-written prompts probing the implicit temporal, spatial, social, and abstract structure that people infer at a glance. Frontier MLLMs fall short of human performance: participants reach 93.1% accuracy, while the strongest model, GPT-6-astra, reaches only 53.6% even at maximum reasoning effort. Despite excelling in many complex tasks that require advanced perception and knowledge, current models still struggle significantly on these visual tasks that are intuitive for humans. We further explore agentic setup that apply dynamic visual manipulation to HSS, which narrows but does not close the gap. HSS establishes intuitive visual reasoning as a measurable axis and directs attention to a capability that scaling on current benchmarks has so far left behind.

Recent advances in visual anomaly detection research have seen AUROC and AUPRO scores on public benchmark datasets such as MVTec and VisA converge towards perfect recall, giving the impression that these benchmarks are near-solved. However, high AUROC and AUPRO scores do not always reflect qualitative performance, which limits the validity of these metrics in real-world applications. We argue that the artificial ceiling imposed by the lack of an adequate evaluation metric restrains progression of the field, and it is crucial that we revisit the evaluation metrics used to rate our algorithms. In response, we introduce Per-IMage Overlap (PIMO), a novel metric that addresses the shortcomings of AUROC and AUPRO. PIMO retains the recall-based nature of the existing metrics but introduces two distinctions: the assignment of curves (and respective area under the curve) is per-image, and its X-axis relies solely on normal images. Measuring recall per image simplifies instance score indexing and is more robust to noisy annotations. As we show, it also accelerates computation and enables the usage of statistical tests to compare models. By imposing low tolerance for false positives on normal images, PIMO provides an enhanced model validation procedure and highlights performance variations across datasets. Our experiments demonstrate that PIMO offers practical advantages and nuanced performance insights that redefine anomaly detection benchmarks -- notably challenging the perception that MVTec AD and VisA datasets have been solved by contemporary models. Available on GitHub: https://github.com/jpcbertoldo/aupimo.

Current benchmarks for AI clinician systems, often based on multiple-choice exams or manual rubrics, fail to capture the depth, robustness, and safety required for real-world clinical practice. To address this, we introduce the GAPS framework, a multidimensional paradigm for evaluating Grounding (cognitive depth), Adequacy (answer completeness), Perturbation (robustness), and Safety. Critically, we developed a fully automated, guideline-anchored pipeline to construct a GAPS-aligned benchmark end-to-end, overcoming the scalability and subjectivity limitations of prior work. Our pipeline assembles an evidence neighborhood, creates dual graph and tree representations, and automatically generates questions across G-levels. Rubrics are synthesized by a DeepResearch agent that mimics GRADE-consistent, PICO-driven evidence review in a ReAct loop. Scoring is performed by an ensemble of large language model (LLM) judges. Validation confirmed our automated questions are high-quality and align with clinician judgment. Evaluating state-of-the-art models on the benchmark revealed key failure modes: performance degrades sharply with increased reasoning depth (G-axis), models struggle with answer completeness (A-axis), and they are highly vulnerable to adversarial perturbations (P-axis) as well as certain safety issues (S-axis). This automated, clinically-grounded approach provides a reproducible and scalable method for rigorously evaluating AI clinician systems and guiding their development toward safer, more reliable clinical practice.

Indic quality estimation (QE) and automatic post-editing (APE) data is spread across separate releases, so no single resource supports training and evaluation across tasks and language pairs on one footing. We consolidate the WMT 2020--2024 shared-task lineage with an extended English--Malayalam resource into \indicqe: 126{,}754 instances over nine directional pairs, with up to four label types aligned on the same segment, a direct assessment, a human post-edit, word-level OK/BAD tags and an error explanation, and a test set stratified over four difficulty axes. On it, we benchmark six prompted LLMs and three COMET metrics on segment-level QE, and three systems on APE. Two of the axes are defined partly on the direct assessment and select a compressed slice of it, so each axis is compared against a control drawn from the same language pair with the same score distribution. Only one survives that control: segments whose holistic and token-level quality signals conflict are ranked worse than equally-scored segments of the same language, for all nine systems and all seven pairs that carry the axis. Annotator disagreement, which looks second-hardest without the control, has no effect with it. Few-shot prompting costs every model leq 3.4B both correlation and output-format compliance. Within-language accuracy does not make scores comparable across pairs: of the three trained metrics, the one with the best within-language correlation loses most when the pairs are pooled. The benchmark and code will be released.

Agent benchmarks are increasingly used to compare large language models (LLMs) and guide deployment decisions, yet benchmark scores are meaningful only if they measure model capability rather than properties of the evaluation pipeline. We identify a double measurement confound: execution-critical decisions are performed by a fixed scaffold instead of the model, while the scorer evaluates outputs using criteria that may not reflect task correctness. We unify these issues within a measurement-theoretic framework that characterizes when benchmark scores can be interpreted as evidence of model capability, and instantiate it with an audit-and-repair protocol that (i) transfers execution-critical decisions from the scaffold to the model, (ii) replaces shape-based evaluation with seeded ground-truth scoring, and (iii) reports reliability beyond the mean through worst-case and tail-risk metrics. Experiments on ComtradeBench show that the joint intervention transforms a nearly flat leaderboard into a reliability spectrum that distinguishes both average performance and robustness across seeds. Applying the audit to existing benchmarks further shows that scorer validity is benchmark-specific, whereas scaffold ownership is an uncontrolled axis wherever we probed it. Our results suggest that benchmark scores should be interpreted together with their scaffolding level, scoring criterion, and reliability profile, providing a practical framework for more valid evaluation of LLM agents.

Nonverbal vocalizations (NVVs), such as laughing, sighing, and sobbing, are essential for human-like speech, yet standardized evaluation rarely jointly assesses whether systems generate the intended NVVs, place them correctly, and keep them salient without harming speech. We present NVV-SuperBench, a bilingual English/Chinese benchmark for speech generation with NVVs. It provides a unified 45-type taxonomy and a multi-axis protocol beyond conventional speech quality assessment, evaluating NVV-specific controllability, placement, and perceptual salience. We benchmark 15 speech generation systems spanning prompt-based and tag-based control paradigms, using objective metrics, human listening tests, and LLM-based multi-rater evaluation. Results show that NVV controllability often decouples from speech quality, while low-SNR oral cues and long-duration affective NVVs remain bottlenecks. NVV-SuperBench highlights current gaps and supports progress toward more human-like speech generation.

Pathology vision-language models (VLMs) have shown strong visual perception ability, but their robustness in the language domain remains poorly characterized. Existing pathology VLM benchmarks largely rely on canonical closed-set prompts or perturb only generic templates, treating language as a fixed evaluation component rather than a variable axis of model behavior. In clinical practice, however, diagnostic language varies across reports, institutions, and candidate diagnoses. We introduce PathLang, a language-centered and clinically grounded zero-shot benchmark. PathLang holds the underlying slides, ground-truth labels, and image-text evaluation direction fixed while systematically varying only the diagnostic language, so that performance differences reflect how a diagnosis is phrased rather than what is imaged. The language variation follows how pathologists actually rephrase diagnoses (terminology, specificity, and reporting style), and all prompts and candidate pools are validated by six board-certified pathologists. PathLang covers four task families: (1) zero-shot classification with image-text alignment analysis, (2) cross-modal retrieval, (3) paraphrase robustness, including semantic-equivalence paraphrases, length and reporting-style variation, and prompt ensembling, and (4) open-vocabulary diagnosis retrieval over four candidate pools with distinct forms of semantic competition. Across nine VLMs and five public datasets spanning four organs, we find that performance is highly sensitive to clinically equivalent paraphrases, varies substantially across forms of semantic competition, and that image-text alignment quality does not necessarily translate into inter-class separability. We release the prompt corpus, candidate pools, pre-computed text embeddings, and evaluation code at https://anonymous.4open.science/r/PathLang.

Current LLM safety benchmarks are predominantly English-centric and often rely on translation, failing to capture country-specific harms. Moreover, they rarely evaluate a model's ability to detect culturally embedded sensitivities as distinct from universal harms. We introduce XL-SafetyBench. a suite of 5,500 test cases across 10 country-language pairs, comprising a Jailbreak Benchmark of country-grounded adversarial prompts and a Cultural Benchmark where local sensitivities are embedded within innocuous requests. Each item is constructed via a multi-stage pipeline that combines LLM-assisted discovery, automated validation gates, and dual independent native-speaker annotators per country. To distinguish principled refusal from comprehension failure, we evaluate Attack Success Rate (ASR) alongside two complementary metrics we introduce: Neutral-Safe Rate (NSR) and Cultural Sensitivity Rate (CSR). Evaluating 10 frontier and 27 local LLMs reveals two key findings. First, jailbreak robustness and cultural awareness do not show a coupled relationship among frontier models, so a composite safety score obscures per-axis variation. Second, local models exhibit a near-linear ASR-NSR trade-off (r = -0.81), indicating that their apparent safety reflects generation failure rather than genuine alignment. XL-SafetyBench enables more nuanced, cross-cultural safety evaluation in the multilingual era.

Existing benchmarks for Vision-Language Models (VLMs) primarily evaluate spatio-temporal understanding on simple single-action videos, closed attribute sets and restricted entity types, failing to capture the freeform, multi-action interactions between diverse entities which characterize real-world video understanding. Furthermore, the lack of a systematic framework for analyzing model failures across complementary spatio-temporal axes hinders comprehensive evaluation. To address these gaps, we introduce VISTA, a Video Interaction Spatio-Temporal Analysis benchmark designed for open-set, multi-entity and multi-action spatio-temporal understanding in VLMs. VISTA decomposes videos into interpretable entities, their associated actions, and relational dynamics, enabling multi-axis diagnostics and unified assessment of relational, spatial, and temporal understanding. Our benchmark integrates multiple datasets into a single interaction-aware taxonomy and comprises ~12K curated video-query pairs spanning diverse scenes and complexities. We systematically evaluate 11 state-of-the-art VLMs on VISTA, and break down aggregate performance across our taxonomy to reveal shortcomings and pronounced spatio-temporal biases obscured by traditional metrics. By providing detailed, taxonomy-driven diagnostics on a challenging dataset, VISTA offers a nuanced framework to guide advances in model design, pretraining strategies, and evaluation protocols. Overall, VISTA is the first, large-scale, interaction-aware diagnostic benchmark for spatio-temporal understanding in VLMs.

While multimodal large language models have advanced across text, image, and audio, personalization research has remained primarily vision-language, with unified omnimodal benchmarking that jointly covers text, image, and audio still limited, and lacking the methodological rigor to account for absent-persona scenarios or systematic grounding studies. We introduce Omni-Persona, the first comprehensive benchmark for omnimodal personalization. We formalize the task as cross-modal routing over the Persona Modality Graph, encompassing 4 task groups and 18 fine-grained tasks across {sim}750 items. To rigorously diagnose grounding behavior, we propose Calibrated Accuracy (mathrm{Cal)}, which jointly rewards correct grounding and appropriate abstention, incorporating absent-persona queries within a unified evaluation framework. On our dedicated experiments, three diagnostic findings emerge: (i) open-source models show a consistent audio-vs-visual grounding gap that RLVR partially narrows via dense rule-based supervision; (ii) answerable recall and parameter scale are incomplete diagnostics, since strong recall can coexist with absent-persona hallucination and larger models do not always achieve higher Cal, exposing calibration as a separate evaluation axis; and (iii) SFT is bounded by the difficulty of constructing annotated ground-truth supervision at scale, while RLVR generalizes more consistently through outcome-level verifiable feedback yet drifts toward conservative behavior and lower generation quality under our reward design. Omni-Persona thus serves as a diagnostic framework that surfaces the pitfalls of omnimodal personalization, guiding future post-training and reward design.

Deceptive web content, widely instantiated across the internet and commonly known as social-engineering attacks, manipulates autonomous web agents into submitting users' personally identifiable information (PII) to attacker-controlled endpoints. In this paper, we show that social-engineering attacks are highly effective at extracting critical-tier PII from frontier web agents, posing a severe risk to deployed agentic systems. To quantify this risk, we introduce \textsc{Scammer4U}, a pre-registered benchmark of 91 attacker-controlled environments and 10 benign-twin baselines, spanning 8 attack vectors and 16 site categories on an 8-axis factorial taxonomy that isolates the causal contribution of individual attack design factors. Across frontier agents, we find that critical-tier PII leakage reaches 54--93\% under no privacy guidance, compared to 0\% on benign-twin baselines, confirming that leakage is attack-attributable rather than incidental form-filling. Escalating prompt-level mitigation yields sharply model-dependent reductions across the four families and remains insufficient to reliably prevent critical PII submission at the pooled level. Most critically, we identify a detection--action gap: agents whose reasoning an independent LLM judge confirms has flagged the site as suspicious still submit critical PII in 35.9\% of sessions, versus 66.1\% when no suspicion is verbalized, a 30.2\% gap robust across all four model families. Our findings reveal that defenses conditioned on the agent's own recognition of an attack are gating on the wrong signal, motivating output-level interception of outbound submissions that operates independently of the agent's reasoning loop.

We introduce Dynaboard, an evaluation-as-a-service framework for hosting benchmarks and conducting holistic model comparison, integrated with the Dynabench platform. Our platform evaluates NLP models directly instead of relying on self-reported metrics or predictions on a single dataset. Under this paradigm, models are submitted to be evaluated in the cloud, circumventing the issues of reproducibility, accessibility, and backwards compatibility that often hinder benchmarking in NLP. This allows users to interact with uploaded models in real time to assess their quality, and permits the collection of additional metrics such as memory use, throughput, and robustness, which -- despite their importance to practitioners -- have traditionally been absent from leaderboards. On each task, models are ranked according to the Dynascore, a novel utility-based aggregation of these statistics, which users can customize to better reflect their preferences, placing more/less weight on a particular axis of evaluation or dataset. As state-of-the-art NLP models push the limits of traditional benchmarks, Dynaboard offers a standardized solution for a more diverse and comprehensive evaluation of model quality.

Sycophancy in LLMs is documented across 70+ papers, but expert agreement on construct boundaries remains low (ICC=.184; Ye et al., 2026). The construct fragments because behavioral classification depends on which surface form is privileged. We adopt a materials-science framing: conversation as test specimen under load, LLM-model as material charge, pushback as progressive load, stance-flip as material failure. We characterize this failure across three loading cases (debate n=1000; false-presuppositions n=3400; ethical-setting n=3400; 10-17 material charges per case; 7800 specimens total) using 14 turn-level axis-measurements spanning velocity, damage accumulation, frame-drift, brittleness, and direction stability, plus three speaker-resolved axes from an independent pipeline. The measurements are Hooke-coupled (σ= E cdot varepsilon analog) and reproduce across loading cases with effects up to |r_{rb}| = 0.35 on debate; the sign structure adds a second pattern: the ethical-setting case inverts the velocity and accumulation blocks. Variance composition partitions into two profiles: debate is charge-dominated (brittle-fracture-like: the material grade decides), false-presuppositions and ethical-setting are topic-dominated (creep-like: the load decides); the ratios (2.03 vs 0.13/0.17) are estimator-dependent, for debate even in direction. Cross-judge reliability (GPT-4o vs Haiku 4.5) shows debate scoring is judge-robust (Cohen's κ= 0.88) while false-presupposition scoring is judge-sensitive (κ= 0.36) -- a caveat single-judge benchmarks must report. This is the methodological move Ye et al.'s diagnosis calls for: a multi-axis characterization that does not depend on which surface form of the construct one privileges.

We study a capability the dominant paradigm in synthetic tabular data does not provide: exact satisfaction of a declared analytical outcome with no source data. Imitation methods (copulas, GANs, diffusion) learn a real distribution and sample from it, and are judged on fidelity to real data. A large, practical class of needs is different: generating data with no source data ("cold start") that reproduces a declared outcome (a revenue curve, a churn rate, a group share) across a relational schema. Off-the-shelf imitation tools offer no interface for such targets, and no sampler can hit an exact aggregate, because sampling has variance. On a real public dataset, off-the-shelf learned synthesizers trained on that very data miss the declared monthly aggregate by 74 to 86 percent; a per-period steelman cuts the miss to about 19 percent and still cannot reach 0; a closed-form generator reaches exactly 0. We name this task outcome-conformant synthesis, argue its evaluation axis is conformance rather than fidelity, and show the two axes are orthogonal. We contribute: (1) a formal account showing a widely-used family of exact-aggregate generators is exactly conditional-sum sampling of a Gamma population (via Lukacs' characterization), with closed-form exactness, a closed-form marginal CV, and scale-invariance; a controlled experiment maps the boundary, enforcing the exact aggregate costs at most 0.006 in 1-Wasserstein distance to an arbitrary external marginal, the rest being shape-family mismatch; (2) SpecBench, to our knowledge the first benchmark to measure conformance to analytical outcomes for cold-start relational synthesis; and (3) a closed-form, deterministic reference system. Exact aggregation alone is trivial; the contribution is conformance jointly with closed-form marginals, integrity, determinism, and zero source data. We concede fidelity to imitation where real data exists.

Generalization in large language models (LLMs) is the ability to produce consistent and semantically stable outputs when the same input is expressed in different ways. Existing work typically evaluates generalization through aggregate accuracy on a single prompt format, task, or set of variations, which conflates robustness with overall benchmark performance. In this work, we show generalization evaluation at the level of individual examples, across multiple input variants, and across different aspects of model behavior, focusing on variability rather than reducing performance to a score that can be improved through narrow training or other ways that obfuscate generalization evaluation. Following this view, we introduce the Stability-Aware Generalization Objective (SAGO), a framework that measures how much model behavior changes for the same input under different variations and benchmarks, capturing variability across several dimensions including generation consistency, internal activations, confidence, and response mirroring. We show that many commonly used models exhibit statistically significant and consistent generalization instability: no model generalizes uniformly, behavioral axes capture independent failure modes, and cross-dataset variation can reverse model rankings.

Qualitative comparison figures are central evidence in computer vision papers, and vision-language models (VLMs) are increasingly used to judge them. Yet existing benchmarks score only scalar quality or overall preference, so a judge can be rewarded for picking the preferred image for the wrong visual reason. We introduce VisionQ, the first benchmark built from peer-reviewed CV comparison figures that grounds every judgment in a named visual criterion: each question states the criterion, and a judge is credited only when it selects the output the authors identify as best on that criterion. We call this task criterion-conditioned visual discrimination. VisionQ comprises (1) a corpus of 1,409 CVPR and ICCV papers with 1,800+ validated comparison figures and 3,911 hand-annotated data points linking method crops to author-stated visual claims; (2) a six-axis, 51-leaf taxonomy of the visual criteria behind qualitative judgment; (3) a criterion-conditioned evaluation protocol that hides method names, captions, and paper identity and reports accuracy per criterion; and (4) VisionQ-Judge, a DPO-tuned Gemma-4-E4B judge trained on symmetric evidence pairs, which reduces last-option predictions by 7.0pp and improves accuracy by 2.5pp on a held-out test set. Evaluating 20 open- and closed-source VLM judges, we find that the strongest reach only 63.1% accuracy (chance 32.2%) and that reliability varies sharply across criteria. Code: https://github.com/ReML-AI/visionq. Data: https://huggingface.co/datasets/visionq-anon-2026/VisionQ-1k.

Personalized image generation has remained narrowly focused on conditional synthesis from curated visual exemplars, rather than capturing who a user is. In practice, however, a user's personal context is much richer, comprising reviews, posts, images, captions, and metadata accumulated over time. A truly personalized generator should leverage this history to produce images aligned with the user's lifestyle and aesthetic preferences. To this end, we introduce the first unified benchmark for personalized image generation from user histories. The benchmark comprises two complementary tasks and a multi-axis evaluation protocol that assesses target fidelity, visual quality, user distinguishability, semantic alignment with the user's history, and task-specific utility. Grounded in real-world e-commerce and social media settings, the benchmark includes: (1) Personalized Scene Generation, which places a given object in a scene that reflects a user's preferences and lifestyle, motivated by personalized product presentation; and (2) Personalized Creative Generation, which generates a novel image on a specified topic that is faithful to a user's aesthetic and visual identity, motivated by social media content creation. We further propose PEARL, which couples a multimodal reasoner with a frozen image generator in an interleaved reason-reflect loop optimized with differential data reward. Across both tasks, PEARL outperforms strong baselines, achieving an average improvement of 15% across personalization metrics.

Recent studies demonstrate that tool-calling capability enables large language models (LLMs) to interact with external environments for long-horizon financial tasks. While existing benchmarks have begun evaluating financial tool calling, they focus on limited scenarios and rely on call-level metrics that fail to capture trajectory-level reasoning quality. To address this gap, we introduce FinTrace, a benchmark comprising 800 expert-annotated trajectories spanning 34 real-world financial task categories across multiple difficulty levels. FinTrace employs a rubric-based evaluation protocol with nine metrics organized along four axes -- action correctness, execution efficiency, process quality, and output quality -- enabling fine-grained assessment of LLM tool-calling behavior. Our evaluation of 13 LLMs reveals that while frontier models achieve strong tool selection, all models struggle with information utilization and final answer quality, exposing a critical gap between invoking the right tools and reasoning effectively over their outputs. To move beyond diagnosis, we construct FinTrace-Training, the first trajectory-level preference dataset for financial tool-calling, containing 8,196 curated trajectories with tool-augmented contexts and preference pairs. We fine-tune Qwen-3.5-9B using supervised fine-tuning followed by direct preference optimization (DPO) and show that training on FinTrace-Training consistently improves intermediate reasoning metrics, with DPO more effectively suppressing failure modes. However, end-to-end answer quality remains a bottleneck, indicating that trajectory-level improvements do not yet fully propagate to final output quality.

Prompt design is a primary control interface for large language models (LLMs), yet standard evaluations largely reduce performance to answer correctness, obscuring why a prompt succeeds or fails and providing little actionable guidance. We propose PEEM (Prompt Engineering Evaluation Metrics), a unified framework for joint and interpretable evaluation of both prompts and responses. PEEM defines a structured rubric with 9 axes: 3 prompt criteria (clarity/structure, linguistic quality, fairness) and 6 response criteria (accuracy, coherence, relevance, objectivity, clarity, conciseness), and uses an LLM-based evaluator to output (i) scalar scores on a 1-5 Likert scale and (ii) criterion-specific natural-language rationales grounded in the rubric. Across 7 benchmarks and 5 task models, PEEM's accuracy axis strongly aligns with conventional accuracy while preserving model rankings (aggregate Spearman rho about 0.97, Pearson r about 0.94, p < 0.001). A multi-evaluator study with four models shows consistent relative judgments (pairwise rho = 0.68-0.85), supporting evaluator-agnostic deployment. Beyond alignment, PEEM captures complementary linguistic failure modes and remains informative under prompt perturbations: prompt-quality trends track downstream accuracy under iterative rewrites, semantic adversarial manipulations induce clear score degradation, and meaning-preserving paraphrases yield high stability (robustness rate about 76.7-80.6%). Finally, using only PEEM scores and rationales as feedback, a zero-shot prompt rewriting loop improves downstream accuracy by up to 11.7 points, outperforming supervised and RL-based prompt-optimization baselines. Overall, PEEM provides a reproducible, criterion-driven protocol that links prompt formulation to response behavior and enables systematic diagnosis and optimization of LLM interactions.

Cinematic video depicts multiple subjects acting or interacting at specific moments, captured with deliberate camera movement, and stitched together by shot transitions. Together, these elements demand a level of fine-grained control beyond current text-to-video models. Existing work addresses each axis in isolation: multi-subject personalization, temporal control, multi-shot synthesis, or camera control; no prior framework jointly integrates all four. We present CineOrchestra, a unified video diffusion model that controls subjects, events, cameras, and shot transitions simultaneously. Our key insight is that these heterogeneous cinematic elements share a fundamental structure: each is an entity acting over a specific temporal interval, which can therefore all be expressed through one shared structure of entity-centric conditioning primitives, augmented with reference images for visual entities. This formulation reduces the architectural challenge to a single positional encoding problem, which we solve with two parameter-free coordinated rotary embeddings: (a) an interval-sampled temporal RoPE that yields consistent attention behavior across events of dramatically varying duration, and (b) a 2D entity-temporal cross-attention RoPE that disambiguates per-entity conditions and routes each to its corresponding spatiotemporal region. On two new benchmarks, CineOrchestra outperforms six per-axis specialists on dense caption following and shot-transition timing, with consistent gains in a pairwise user study and component ablations.

Evaluating LLM mediators remains challenging, as mediation unfolds as a real-time trajectory shaped by disputants' shifting emotions, intentions, and context. Existing testbeds rely on a few expert-authored domains, vary mainly strategic posture, and score every turn against every topic, introducing off-topic noise. We introduce SoCRATES, a benchmark for evaluating proactive LLM mediators in realistic, multi-domain testbeds. It constructs scenarios from real conflicts through an agentic pipeline across eight domains, probes five socio-cognitive adaptation axes (strategic posture, party composition, history length, emotional reactivity, and cultural identity), and scores each topic only on the turns that advance it via a topic-localized evaluator. The evaluator reaches 0.82 alignment with human experts, more than doubling a per-turn baseline. Benchmarking eight frontier LLMs, we find that even the strongest mediator closes only about a third of the unmediated consensus gap under diverse and realistic testbeds, with performance varying sharply by socio-cognitive axis, highlighting that progress lies in social adaptation to diverse conditions.

Dynamic programming (DP) algorithms for combinatorial optimization problems work with taking maximization, minimization, and classical addition in their recursion algorithms. The associated value functions correspond to convex polyhedra in the max plus semiring. Existing Neural Algorithmic Reasoning models, however, rely on softmax-normalized dot-product attention where the smooth exponential weighting blurs these sharp polyhedral structures and collapses when evaluated on out-of-distribution (OOD) settings. We introduce Tropical attention, a novel attention function that operates natively in the max-plus semiring of tropical geometry. We prove that Tropical attention can approximate tropical circuits of DP-type combinatorial algorithms. We then propose that using Tropical transformers enhances empirical OOD performance in both length generalization and value generalization, on algorithmic reasoning tasks, surpassing softmax baselines while remaining stable under adversarial attacks. We also present adversarial-attack generalization as a third axis for Neural Algorithmic Reasoning benchmarking. Our results demonstrate that Tropical attention restores the sharp, scale-invariant reasoning absent from softmax.

Reinforcement learning (RL) for non-verifiable instruction following increasingly relies on LLM judges with prompt-specific rubrics as reward signals. While recent methods adapt these rubrics to the evolving policy during training, the training prompts themselves remain static, drawn from fixed corpora. This static approach often results in a critical misalignment between prompt difficulty and policy capability, leaving the judge unable to recover a discriminative reward signal when prompts fail to elicit quality variance among rollouts. To address this misalignment, we introduce LLM-as-a-Tutor, a framework that extends the LLM's role from judge to tutor: a single model serves as an examiner that pairwise-compares policy rollouts to detect non-challenging prompts, and as a generator that appends atomic constraints to them. This append-only design monotonically raises difficulty in step with the policy's capability, producing a self-calibrating training signal without external difficulty schedules. On three complex instruction-following benchmarks, our method consistently outperforms both policy-unaware baselines and prior policy-adaptive methods that adapt rubrics or rewrite prompts, suggesting prompt adaptation as a missing axis of policy-awareness in non-verifiable RL.

Large Language Model (LLM) agents have seen rapid adoption in software engineering. As agents take a greater role in the actual generation of code, they are making larger changes, spanning tens to hundreds of lines. This makes manual review of agent results increasingly infeasible, leading developers to turn to explanations to understand enacted changes. Despite this, there are no benchmarks that evaluate the trustworthiness of agent-generated explanations. To bridge this gap, we propose ExplainBench, a benchmark to automatically evaluate explanations from coding agents. ExplainBench is based on the intuition that informative explanations should enable an LLM to correctly answer questions, allowing quantitative comparison of explanation quality between agents. With this observation, we construct a suite of questions that evaluates whether explanations accurately describe (1) the intended behavior of buggy code and (2) the effect of applying the agent patch itself. Experiments first reveal that explanation quality is a distinct axis of agent evaluation: ExplainBench ranks agents differently from the widely-used SWE-bench Verified benchmark. A deeper breakdown of explanation quality in agents shows frequent problems in explanations, such that explanations often claim that a patch is correct when it is not. Based on this insight, we implement and evaluate an explanation audit agent which runs additional tests to validate and refine explanations. This agent improved the explanations of all evaluated agents, demonstrating agent explanations can be automatically made more trustworthy.

Current Large Language Models (LLMs) benchmarks are often based on open-ended or close-ended QA evaluations, avoiding the requirement of human labor. Close-ended measurements evaluate the factuality of responses but lack expressiveness. Open-ended capture the model's capacity to produce discourse responses but are harder to assess for correctness. These two approaches are commonly used, either independently or together, though their relationship remains poorly understood. This work is focused on the healthcare domain, where both factuality and discourse matter greatly. It introduces a comprehensive, multi-axis suite for healthcare LLM evaluation, exploring correlations between open and close benchmarks and metrics. Findings include blind spots and overlaps in current methodologies. As an updated sanity check, we release a new medical benchmark--CareQA--, with both open and closed variants. Finally, we propose a novel metric for open-ended evaluations --Relaxed Perplexity-- to mitigate the identified limitations.

A personalized LLM should remember user facts, apply them correctly, and adapt over time to provide responses that the user prefers. Existing LLM personalization benchmarks are largely centered on two axes: accurately recalling user information and accurately applying remembered information in downstream tasks. We argue that a third axis, likability, is both subjective and central to user experience, yet under-measured by current benchmarks. To measure likability holistically, we introduce LikeBench, a multi-session, dynamic evaluation framework that measures likability across multiple dimensions by how much an LLM can adapt over time to a user's preferences to provide more likable responses. In LikeBench, the LLMs engage in conversation with a simulated user and learn preferences only from the ongoing dialogue. As the interaction unfolds, models try to adapt to responses, and after each turn, they are evaluated for likability across seven dimensions by the same simulated user. To the best of our knowledge, we are the first to decompose likability into multiple diagnostic metrics: emotional adaptation, formality matching, knowledge adaptation, reference understanding, conversation length fit, humor fit, and callback, which makes it easier to pinpoint where a model falls short. To make the simulated user more realistic and discriminative, LikeBench uses fine-grained, psychologically grounded descriptive personas rather than the coarse high/low trait rating based personas used in prior work. Our benchmark shows that strong memory performance does not guarantee high likability: DeepSeek R1, with lower memory accuracy (86%, 17 facts/profile), outperformed Qwen3 by 28% on likability score despite Qwen3's higher memory accuracy (93%, 43 facts/profile). Even SOTA models like GPT-5 adapt well in short exchanges but show only limited robustness in longer, noisier interactions.

As large language models (LLMs) increasingly mediate ethically sensitive decisions, understanding their moral reasoning processes becomes imperative. This study presents a comprehensive empirical evaluation of 14 leading LLMs, both reasoning enabled and general purpose, across 27 diverse trolley problem scenarios, framed by ten moral philosophies, including utilitarianism, deontology, and altruism. Using a factorial prompting protocol, we elicited 3,780 binary decisions and natural language justifications, enabling analysis along axes of decisional assertiveness, explanation answer consistency, public moral alignment, and sensitivity to ethically irrelevant cues. Our findings reveal significant variability across ethical frames and model types: reasoning enhanced models demonstrate greater decisiveness and structured justifications, yet do not always align better with human consensus. Notably, "sweet zones" emerge in altruistic, fairness, and virtue ethics framings, where models achieve a balance of high intervention rates, low explanation conflict, and minimal divergence from aggregated human judgments. However, models diverge under frames emphasizing kinship, legality, or self interest, often producing ethically controversial outcomes. These patterns suggest that moral prompting is not only a behavioral modifier but also a diagnostic tool for uncovering latent alignment philosophies across providers. We advocate for moral reasoning to become a primary axis in LLM alignment, calling for standardized benchmarks that evaluate not just what LLMs decide, but how and why.

Mechanistic interpretability is often motivated for alignment auditing, where a model's verbal explanations can be absent, incomplete, or misleading. Yet many evaluations do not control whether black-box prompting alone can recover the target behavior, so apparent gains from white-box tools may reflect elicitation rather than internal signal; we call this the elicitation confounder. We introduce Pando, a model-organism benchmark that breaks this confound via an explanation axis: models are trained to produce either faithful explanations of the true rule, no explanation, or confident but unfaithful explanations of a disjoint distractor rule. Across 720 finetuned models implementing hidden decision-tree rules, agents predict held-out model decisions from 10 labeled query-response pairs, optionally augmented with one interpretability tool output. When explanations are faithful, black-box elicitation matches or exceeds all white-box methods; when explanations are absent or misleading, gradient-based attribution improves accuracy by 3-5 percentage points, and relevance patching, RelP, gives the largest gains, while logit lens, sparse autoencoders, and circuit tracing provide no reliable benefit. Variance decomposition suggests gradients track decision computation, which fields causally drive the output, whereas other readouts are dominated by task representation, biases toward field identity and value. We release all models, code, and evaluation infrastructure.

Large Language Models (LLMs) are increasingly deployed as reasoning systems, where reasoning paradigms - such as Chain-of-Thought (CoT) and multi-agent systems (MAS) - play a critical role, yet their relative effectiveness and cost-accuracy trade-offs remain poorly understood. In this work, we conduct a comprehensive and unified evaluation of reasoning paradigms, spanning direct single-model generation, CoT-augmented single-model reasoning, and representative MAS workflows, characterizing their reasoning performance across a diverse suite of closed-form benchmarks. Beyond overall performance, we probe role-specific capability demands in MAS using targeted role isolation analyses, and analyze cost-accuracy trade-offs to identify which MAS workflows offer a favorable balance between cost and accuracy, and which incur prohibitive overhead for marginal gains. We further introduce MIMeBench, a new open-ended benchmark that targets two foundational yet underexplored semantic capabilities - semantic abstraction and contrastive discrimination - thereby providing an alternative evaluation axis beyond closed-form accuracy and enabling fine-grained assessment of semantic competence that is difficult to capture with existing benchmarks. Our results show that increased structural complexity does not consistently lead to improved reasoning performance, with its benefits being highly dependent on the properties and suitability of the reasoning paradigm itself. The codes are released at https://gitcode.com/HIT1920/OpenLLMBench.

Pre-training equips large language models (LLMs) with a broad repertoire of behavioral patterns associated with roles, styles, values, and goals. Post-training teaches conditional enactment and makes a helpful Assistant the default, but it does not erase alternative modes from the weights; explicit prompts can therefore elicit personas that repeatedly shape judgment, language, and action. In open-weight settings, runtime controls can be removed, motivating persona unlearning: a weight-level edit that makes a designated persona difficult to elicit and enact on unseen contexts. We introduce PersonaUnlearnBench, a model-specific paired benchmark spanning six LLMs from three families and five personas, with aligned forget/retain sets, held-out instruction paraphrases, and four-axis evaluation. The benchmark shows that standard unlearning methods cannot reliably erase the target persona without sacrificing meaningful generation or general utility. We therefore propose PaCE, which compares target and desirable responses to the same questions to locate an internal behavior direction, then trains target-prompt states away from the target mode and toward the matched desirable response. Experiments show that PaCE consistently suppresses target personas with high response quality and useful counterpart behavior, at moderate utility cost. These results establish persona unlearning as a distinct behavior-level editing problem and a practical route toward persistent control of latent LLM response policies.

Leaderboards rank frontier models on independent axes but do not reveal whether capabilities reinforce or trade off across releases -- and at the frontier, this interaction is the more informative signal. We decompose paired SWE-bench and GPQA Diamond scores into a population coupling trend and per-release residual (h-field) that diagnoses capability emphasis and identifies which measurement or stress test is most informative next. Across 34 models from 10 labs (2024--2026), capabilities cooperate (r = +0.72, p < 10^{-6}), but cooperation varies by lab and over time: DeepSeek reversed from reasoning-rich to coding-first (h: +11.2 to -4.7, 15.9-pp swing); Google maintains consistent reasoning emphasis; Anthropic oscillates between coding excursions and recovery. Cooperation is not static -- it cascades. Six open-weight architectures confirm a second capability transition at 30--72B, and SWE-bench is now saturating while HLE and instruction-following retain discriminatory spread -- signaling the next axis rotation. We provide a three-level playbook (locate, diagnose, rotate), a per-lab measurement-priority table, and seven falsifiable predictions with timestamped criteria for the next 12 months of frontier releases. Per-lab coupling slopes vary 5times (Google 1.15 vs. DeepSeek 0.23), quantifying how efficiently each recipe converts coding gains into reasoning. Five April 2026 releases confirm the diagnostic out of sample (r rises from +0.72 to +0.75). An interactive dashboard provides phase classification with actionable recommendations, h-field diagnostics, per-lab coupling trajectories, ODE-based scaling predictions, benchmark rotation guidance, self-steering demo, and live tracking of all seven predictions: https://zehenlabs.com/cape/.

As large-language models have been increasingly used as automatic raters for evaluating free-form content, including document summarization, dialog, and story generation, work has been dedicated to evaluating such models by measuring their correlations with human judgment. For sample-level performance, methods which operate by using pairwise comparisons between machine-generated text perform well but often lack the ability to assign absolute scores to individual summaries, an ability crucial for use cases that require thresholding. In this work, we propose a direct-scoring method which uses synthetic summaries to act as pairwise machine rankings at test time. We show that our method performs comparably to state-of-the-art pairwise evaluators in terms of axis-averaged sample-level correlations on the SummEval (+0.03), TopicalChat (-0.03), and HANNA (+0.05) meta-evaluation benchmarks, and release the synthetic in-context summaries as data to facilitate future work.

Large Language Model (LLM) unlearning aims to remove undesirable knowledge or behaviors while preserving retained capabilities. Current unlearning methods all involve a trade-off between unlearning and retention. We have found that the retention activation bias can also be used to quantify the damage an unlearning method inflicts on retention, without considering the specific implementation of the unlearning process. This allows us to restore retention performance for any unlearning method using a post-hoc approach. Therefore, we propose a complementary post-hoc setting to sanitize the final update vector without rerunning the original unlearning pipeline. In this setting, we design SAGE, Spectral Activation-GEometry Sanitization, a source-agnostic correction for final unlearning updates. SAGE collects real module inputs from a small retain proxy, extracts their dominant activation geometry, and solves a source-anchored optimization objective in closed form, which suppresses update components aligned with high-energy retained directions while preserving the source method's forgetting carrier. Across multiple unlearning methods, model scales, and benchmarks, SAGE consistently relieves the retain-forget trade-off, identifying post-hoc sanitization of final vectors as a practical and underexplored axis for machine unlearning.

Despite the success of deep learning for text and image data, tree-based ensemble models are still state-of-the-art for machine learning with heterogeneous tabular data. However, there is a significant need for tabular-specific gradient-based methods due to their high flexibility. In this paper, we propose GRANDE, GRAdieNt-Based Decision Tree Ensembles, a novel approach for learning hard, axis-aligned decision tree ensembles using end-to-end gradient descent. GRANDE is based on a dense representation of tree ensembles, which affords to use backpropagation with a straight-through operator to jointly optimize all model parameters. Our method combines axis-aligned splits, which is a useful inductive bias for tabular data, with the flexibility of gradient-based optimization. Furthermore, we introduce an advanced instance-wise weighting that facilitates learning representations for both, simple and complex relations, within a single model. We conducted an extensive evaluation on a predefined benchmark with 19 classification datasets and demonstrate that our method outperforms existing gradient-boosting and deep learning frameworks on most datasets. The method is available under: https://github.com/s-marton/GRANDE

Constructing environments for training and evaluating claw-like agents remains a manual, human-intensive process that does not scale. We argue that what is needed is not just a dataset, but an automated pipeline capable of generating diverse, verified environments on demand. To this end, we introduce ClawEnvKit, an autonomous generation pipeline that instantiates this formalism from natural language descriptions. The pipeline comprises three modules: (1) a parser that extracts structured generation parameters from natural language input; (2) a generator that produces the task specification, tool interface, and scoring configuration; and (3) a validator that enforces feasibility, diversity, structural validity, and internal consistency across the generated environments. Using ClawEnvKit, we construct Auto-ClawEval, the first large-scale benchmark for claw-like agents, comprising 1,040 environments across 24 categories. Empirically, Auto-ClawEval matches or exceeds human-curated environments on coherence and clarity at 13,800x lower cost. Evaluated across 4 model families and 8 agent harness frameworks, we find that harness engineering boosts performance by up to 15.7 percentage points over a bare ReAct baseline, completion remains the primary axis of variation with no model saturating the benchmark, and automated generation enables evaluation at a scale previously infeasible. Beyond static benchmarking, ClawEnvKit enables live evaluation: users describe a desired capability in natural language and obtain a verified environment on demand, turning evaluation into a continuous, user-driven process. The same mechanism serves as an on-demand training environment generator, producing task distributions that adapt to an agent's current weaknesses rather than being bounded by existing user logs.

Safety evaluations for large language models (LLMs) increasingly target high-stakes National Security and Public Safety (NSPS) risks, yet multilingual safety is typically assessed through translation-only benchmarks that preserve the underlying scenario, and empirical evidence of how language and geopolitical context interact remains limited to a narrow set of language pairs. We introduce ROK-FORTRESS https://huggingface.co/datasets/ScaleAI/ROK-FORTRESS_public, a bilingual, culturally adversarial NSPS benchmark that uses the English--Korean language pair and U.S.--ROK geopolitical axis as a case study, separating the effects of language and geopolitical grounding via a transcreation matrix: adversarial intents are evaluated under controlled combinations of (i) English versus Korean language and (ii) U.S.\ versus Korean entities, institutions, and operational details. Each adversarial prompt is paired with a dual-use benign counterpart to quantify over-refusal. Model responses are then scored using calibrated LLM-as-a-judge panels, applying our expert-crafted, prompt-specific binary rubrics. Across a dual-track set of frontier and Korean-optimized models, we find a consistent suppression effect in Korean variants and substantial model-to-model variation in how geopolitical grounding interacts with language. In many models, Korean grounding mitigates the Korean language-driven suppression -- with no model showing significant amplification in the other direction -- indicating that, at least in the English--Korean case, safety behavior is shaped by language-as-risk signals and context interactions that translation-only evaluations miss. The transcreation matrix methodology is designed to generalize to other language--culture pairs.

Large language models, and the agents built on them, spend an ever-growing share of their compute and memory on remembering: caching attention keys and values, carrying long prompts, maintaining recurrent state, and storing what happened in previous turns and sessions. Because none of this memory is free, four largely separate research communities have each learned to compact it. They evict or quantize the KV cache, prune or distill prompts, bound architectural state, and consolidate agent memory. We argue that these are instances of one problem: a rate--distortion decision about what context-derived information to retain versus discard, at what fidelity, under a resource budget, so as to preserve downstream task utility. We make this lens precise with a single compaction objective and a layer-agnostic lower bound, use it to build a seven-axis taxonomy that classifies methods from across the stack uniformly, and use it to transfer mechanisms between layers that have never been connected, from serving-stack KV management to agent long-term memory. Two patterns hold across the survey. At every layer the signal that decides what to keep is attention magnitude or recency, and it fails in the same way everywhere, by discarding, before the query is known and with no way to undo it, information the query later needs. And while compression is measured carefully on single-turn long context, the repeated compaction that agents actually perform is almost never measured, and no benchmark holds one budget axis across all the layers at once. We turn both observations into a benchmark proposal, a small reference experiment, and a set of compaction-aware design principles, and we map the open problems.

All-atom molecular simulation serves as a quintessential ``computational microscope'' for understanding the machinery of life, yet it remains fundamentally limited by the trade-off between quantum-mechanical (QM) accuracy and biological scale. We present UBio-MolFM, a universal foundation model framework specifically engineered to bridge this gap. UBio-MolFM introduces three synergistic innovations: (1) UBio-Mol26, a large bio-specific dataset constructed via a multi-fidelity ``Two-Pronged Strategy'' that combines systematic bottom-up enumeration with top-down sampling of native protein environments (up to 1,200 atoms); (2) E2Former-V2, a linear-scaling equivariant transformer that integrates Equivariant Axis-Aligned Sparsification (EAAS) and Long-Short Range (LSR) modeling to capture non-local physics with up to ~4x higher inference throughput in our large-system benchmarks; and (3) a Three-Stage Curriculum Learning protocol that transitions from energy initialization to energy-force consistency, with force-focused supervision to mitigate energy offsets. Rigorous benchmarking across microscopic forces and macroscopic observables -- including liquid water structure, ionic solvation, and peptide folding -- demonstrates that UBio-MolFM achieves ab initio-level fidelity on large, out-of-distribution biomolecular systems (up to ~1,500 atoms) and realistic MD observables. By reconciling scalability with quantum precision, UBio-MolFM provides a robust, ready-to-use tool for the next generation of computational biology.