Human-Annotated Benchmark

This report benchmarks the performance of ENGINEERING Ingegneria Informatica S.p.A.'s EngGPT2MoE-16B-A3B LLM, a 16B parameter Mixture of Experts (MoE) model with 3B active parameters. Performance is investigated across a wide variety of representative benchmarks, and is compared against comparably-sized open-source MoE and dense models. In comparison with popular Italian models, namely FastwebMIIA-7B, Minerva-7B, Velvet-14B, and LLaMAntino-3-ANITA-8B, EngGPT2MoE-16B-A3B performs as well or better on international benchmarks: ARC-Challenge, GSM8K, AIME24, AIME25, MMLU, and HumanEval (HE). It achieves the best performance for the longest context setting (32k) of the RULER benchmark. On the Italian benchmark dataset ITALIC, the model performs as well or better than the other models except for Velvet-14B, which outperforms it. Compared with popular MoE models of comparable size, the new model reports higher values than DeepSeek-MoE-16B-Chat on all considered benchmarks. It has higher values than Moonlight-16B-A3B on HE, MMLU, AIME24, AIME25, GSM8K, and the 32k RULER setting, but lower on BFCL and some ARC and ITALIC settings. Finally it has lower values than GPT-OSS-20B on most benchmarks, including HE, MMLU, AIME24, AIME25, GSM8K, ARC, BFCL, and the RULER 32k. When compared with popular dense models, EngGPT2MoE-16B-A3B reports higher values on AIME24 and AIME25 than Llama-3.1-8B-Instruct, Gemma-3-12b-it, and Ministral-3-8BInstruct-2512-BF16, but lower values on ITALIC, BFCL, and RULER with a 32k context. When performance is aggregated across all benchmark metrics, EngGPT2MoE-16B-A3B shows higher performance than the Italian models under evaluation while achieving lower results than some of the most performant international models, in particular GPT-5 nano and Qwen3-8B. Taken together, our findings find the new model to be a step forward for native Italian Large Language Models.

Large Language Model (LLM) systems have been the frontier of AI in many application domains, leading to new challenges and opportunities for hyperparameter optimization (HPO) for the AutoML community. However, this type of system exhibits an unprecedented compound space of hyperparameter configuration from both the AI and non-AI components; rich and nonlinear implications from the fidelity factors; and diverse costs of measuring hyperparameter configurations, none of which have been fully captured in existing benchmarks. This paper presents the first (live) benchmark suite and datasets for HPO of real-world LLM systems, dubbed LLMSYS-HPOBench, covering data related to the inference objective values of hyperparameter configurations profiled from running the LLM systems. Currently, LLMSYS-HPOBench contains 364,450 hyperparameter configurations with a dimensionality of 12-23, 3-5 dimensions of fidelity factor leading to 932 settings, 3-9 inference objective metrics, and 2-10 cost metrics, together with generated logs from measuring the LLM systems. What we seek to advocate is not only a revalidation of the existing HPO algorithms over the frontier LLM systems, but also to provide an evolving platform for the AutoML community to explore new directions of research in this regard. The benchmark suite has been made available at: https://github.com/ideas-labo/llmsys-hpobench

Autoregressive scientific forecasters often enforce physical or structural constraints by repairing each predicted state before feeding it back into the model. However, it remains unclear when stronger physical rule enforcement becomes reliable and when it becomes a source of distribution shift. We study this question through operator exactness, meaning whether the repair map is the identity on the target manifold and is aligned with the target geometry. We compare raw forecasting, post hoc repair, and in-loop repair across periodic incompressible Navier--Stokes, non-periodic CFDBench flows, and a hierarchical-forecasting support task. In the exact periodic regime, Fourier projection substantially improves rollout accuracy. On the NS-128 benchmark, a strong Raw-FNO has a final-step rollout MSE at horizon 100 of $(9.390 \pm 6.290)\times 10^{-5}$, and post hoc and in-loop projection reduce it to $(1.130 \pm 0.165)\times 10^{-6}$ and $(5.370 \pm 0.113)\times 10^{-7}$. However, once an exact projection is unavailable and only approximate boundary-preserving cleanup is available, the ordering changes. Across cavity, tube, dam, and cylinder flow, stronger Poisson-based cleanup can reduce divergence while worsening rollout error; target-distortion MSE predicts this harm far better than a linear-system residual. Controlled mismatch, screened cleanup, adaptive gating, and external-backbone checks show that the best approximate-regime operating point can be raw or near-identity. Hierarchical forecasting gives the same broader pattern. Exact forecast reconciliation is a stable baseline, whereas blended top-down repair, a validation-tuned interpolation toward historical-proportion top-down reconciliation, is dataset-dependent. Thus, constraint enforcement should be benchmarked by operator--data alignment before enforcement strength.

Existing multimodal search agents process target entities sequentially, issuing one tool call per entity and accumulating redundant interaction rounds whenever a query decomposes into independent sub-retrievals. We argue that effective multimodal agents should search wider rather than longer: dispatching multiple grounded queries concurrently within a round. To this end, we present HyperEyes, a parallel multimodal search agent that fuses visual grounding and retrieval into a single atomic action, enabling concurrent search across multiple entities while treating inference efficiency as a first-class training objective. HyperEyes is trained in two stages. For cold-start supervision, we develop a Parallel-Amenable Data Synthesis Pipeline covering visual multi-entity and textual multi-constraint queries, curating efficiency-oriented trajectories via Progressive Rejection Sampling. Building on this, our central contribution, a Dual-Grained Efficiency-Aware Reinforcement Learning framework, operates at two levels. At the macro level, we propose TRACE (Tool-use Reference-Adaptive Cost Efficiency), a trajectory-level reward whose reference is monotonically tightened during training to suppress superfluous tool calls without restricting genuine multi-hop search. At the micro level, we adapt On-Policy Distillation to inject dense token-level corrective signals from an external teacher on failed rollouts, mitigating the credit-assignment deficiency of sparse outcome rewards. Since existing benchmarks evaluate accuracy as the sole metric, omitting inference cost, we introduce IMEB, a human-curated benchmark of 300 instances that jointly evaluates search capability and efficiency. Across six benchmarks, HyperEyes-30B surpasses the strongest comparable open-source agent by 9.9% in accuracy with 5.3x fewer tool-call rounds on average.

Generative AI systems achieve impressive performance on standard benchmarks yet fail to deliver real-world utility, a disconnect we identify across 28 deployment cases spanning education, healthcare, software engineering, and law. We argue that this benchmark utility gap arises from three recurring failures in evaluation practice: proxy displacement, temporal collapse, and distributional concealment. Motivated by these observations, we argue that generative AI evaluation requires a paradigm shift from static benchmark-centered transparency toward stakeholder, goal, and context-conditioned utility transparency grounded in human outcome trajectories. Existing evaluations primarily characterize properties of model outputs, while deployment success depends on whether interaction with AI improves stakeholders' ability to achieve their goals over time. The missing construct is therefore utility: the change in a stakeholder's capability induced through sustained interaction with an AI system within a deployment context. To operationalize this perspective, we propose SCU-GenEval, a four-stage evaluation framework consisting of stakeholder-goal mapping, construct-indicator specification, mechanism modeling, and longitudinal utility measurement. To make these stages practically deployable, we introduce three supporting instruments: structured deployment protocols, context-conditioned user simulators, and persona- and goal-conditioned proxy metrics. We conclude with domain-specific calls to action, arguing that progress in generative AI must be evaluated through measurable improvements in human outcomes rather than benchmark performance alone.

Developing ceramic glazes is a costly, time-consuming process of trial and error due to complex chemistry, placing a significant burden on independent artists. While recent advances in multimodal AI offer a modern solution, the field lacks the large-scale datasets required to train these models. We propose GlazyBench, the first dataset for AI-assisted glaze design. Comprising 23,148 real glaze formulations, GlazyBench supports two primary tasks: predicting post-firing surface properties, such as color and transparency, from raw materials, and generating accurate visual representations of the glaze based on these properties. We establish comprehensive baselines for property prediction using traditional machine learning and large language models, alongside image generation benchmarks using deep generative and large multimodal models. Our experiments demonstrate promising yet challenging results. GlazyBench pioneers a new research direction in AI-assisted material design, providing a standardized benchmark for systematic evaluation.

Progress on graph foundation models is hindered by benchmark practices that conflate the contributions of node features and graph structure, making it hard to tell whether a model actually learns from connectivity, or whether it even needs to. We propose addressing this using graph invariants, i.e., permutation-invariant, task-agnostic structural descriptors that serve as a diagnostic framework for graph benchmarks. We show that (i) invariants are more expressive than standard GNNs, (ii) invariants characterize structural heterogeneity within and across benchmark datasets, (iii) invariants predict multi-task performance, and (iv) simple invariant-based models are competitive with, and sometimes exceed, transformer and message-passing baselines across 26 datasets. Our results suggest that expressivity is not the main driver of predictive performance, and that on tasks where structure matters, a non-trainable structural proxy often matches trained message-passing models. We thus posit that invariant baselines should become a standard for evaluating whether structure is required for a task and whether a model picks up on it, serving as a stepping stone towards graph foundation models.

Evaluating large language models (LLMs) today rests on fixed benchmarks that apply the same set of items to any model, producing ceiling and floor effects that mask capability gaps. We argue that the most informative evaluation signal lies at the boundary, where the per-prompt pass probability is near $0.5$ under random-sampling decoding, and propose Dynamic Boundary Evaluation (DBE), which actively locates each model's boundary and places it on a globally comparable difficulty scale. DBE delivers three artifacts: (i) a calibrated item bank covering safety, capability, and truthfulness, with per-item difficulty labels validated across $9$ reference LLMs; (ii) Skill-Guided Boundary Search (SGBS), a search algorithm that finds boundary items for a given target LLM using only API-level query access; and (iii) an evaluation protocol that places a new LLM on a unified ability scale and grows the evaluation set adaptively when the target falls outside the bank's coverage. We instantiate DBE on four categories spanning safety (harmful request refusal and over-refusal), capability (constrained instruction following), and truthfulness (multi-turn sycophancy resistance). The resulting evaluation covers a broader model spectrum without saturation while remaining compatible with existing datasets.

For years, we have built LLM serving systems like any other critical infrastructure: a single general-purpose stack, hand-tuned over many engineer-years, meant to support every model and workload. In this paper, we take the opposite bet: a multi-agent loop that automatically synthesizes bespoke serving systems for different usage scenarios. We propose VibeServe, the first agentic loop that generates entire LLM serving stacks end-to-end. VibeServe uses an outer loop to plan and track the search over system designs, and an inner loop to implement candidates, check correctness, and measure performance on the target benchmark. In the standard deployment setting, where existing stacks are highly optimized, VibeServe remains competitive with vLLM, showing that generation-time specialization need not come at the cost of performance. More interestingly, in non-standard scenarios, VibeServe outperforms existing systems by exploiting opportunities that generic systems miss in six scenarios involving non-standard model architectures, workload knowledge, and hardware-specific optimizations. Together, these results suggest a different point in the design space for infrastructure software: generation-time specialization rather than runtime generality. Code is available at https://github.com/uw-syfi/vibe-serve.

Causal reinforcement learning (RL) lacks benchmarks for complex systems that combine sequential decision making, hidden information, large masked action spaces, and explicit causal structure. We introduce MTG-Causal-RL, a Gymnasium benchmark built on Magic: The Gathering with a 3,077-dimensional partial observation, a 478-action masked discrete action space, five competitive Standard archetypes, three reward schemes, and a hand-specified Structural Causal Model (SCM) over strategic variables. Every episode exposes causal variables, SCM-predicted intervention effects, and per-factor credit traces, making causal credit assignment, leave-one-out cross-archetype transfer, and policy auditability first-class metrics. We adapt a panel of reference baselines: random, heuristic, masked PPO, a causal-world-model PPO variant, and an architecture-matched scalar control. We propose Causal Graph-Factored Advantage PPO (CGFA-PPO) as a reference causal agent that uses SCM parents of win probability as factor-aligned critic targets with an intervention-calibration loss. All comparisons use paired seeds, paired-bootstrap confidence intervals, and Holm-Bonferroni correction within pre-registered families. Masked PPO and CGFA-PPO reach competitive in-distribution win rates and exceed the random baseline; per-factor calibration trajectories and leave-one-out transfer gaps expose diagnostic structure that scalar win rate alone cannot. We release the benchmark, reference-baseline results, and full evaluation protocol openly. By coupling a strategically rich, partially observed domain with an explicit causal interface and statistical protocol, MTG-Causal-RL gives causal-RL, world-model, and LLM-agent research a shared testbed for questions current benchmarks cannot pose together: causal credit assignment under masked action spaces, structural transfer across archetypes, and SCM-grounded policy auditability.

We introduce iTRIALSPACE, a programmable evaluation framework for controlled assessment of lung CT models. Standard benchmarks are static retrospective collections that entangle lesion size, lobe prevalence, anatomy, and acquisition context, making it difficult to determine what structurally drives model accuracy. iTRIALSPACE addresses this limitation by composing real clinical CTs and lesion profiles into controlled virtual lesion trials through a four-stage pipeline: multidataset nodule profiling, explicit trial specification, anatomy-aware mask insertion, and ControlNet-conditioned CT synthesis. The framework is built on a unified 54-attribute nodule-profile dataset spanning 13,140 annotated nodules from seven public CT sources and instantiated as 13 trial modes. We evaluate iTRIALSPACE in a 55,469-sample Virtual Lesion Study spanning three medical VLMs, four spatialguidance conditions, and three clinical tasks. Across all 13 modes, the synthetic substrate remains within the real-to-real FID baseline, and synthetic performance rankings transfer strongly to real clinical data ($ρ$ = 0.93, p < 10$^{-15}$). Controlled trial modes expose findings unavailable to fixed-distribution benchmarks, including shortcut-driven size prediction collapse under lobe-equalized sampling and hostto-donor variance ratios of 8.9x and 3.3x in twin-cross analysis. These results position iTRIALSPACE as an auditable evaluation infrastructure for controlled, falsifiable testing beyond static retrospective benchmarks.

We propose Conformal Seasonal Pools (CSP), a training-free probabilistic time-series forecaster that mixes same-season empirical draws with signed residual draws around a seasonal naive forecast. In an audited rolling-origin benchmark on the six time-series datasets where DeepNPTS was originally evaluated (electricity, exchange_rate, solar_energy, taxi, traffic, wikipedia), CSP-Adaptive significantly outperforms DeepNPTS on every metric we report -- CRPS (per-window paired Wilcoxon $p \approx 4 \times 10^{-10}$), normalized mean quantile loss ($p \approx 7 \times 10^{-10}$), and empirical 95% coverage ($p \approx 8 \times 10^{-45}$, mean 0.89 vs 0.66) -- while running over 500x faster on CPU. Coverage is the most decision-critical of these: a 0.95 nominal interval that contains the truth in only ~66% of cases fails the basic calibration desideratum and would not survive deployment in safety- or decision-critical settings. The failure mode is also more severe than aggregate coverage suggests: in the worst 10% of windows, DeepNPTS's prediction interval covers none of the H forecast horizons -- the entire multi-step trajectory misses the truth at every step simultaneously. This poses serious risk in safety- and decision-critical applications such as healthcare, finance, energy operations, and autonomous systems, where prediction intervals that systematically miss the truth across the entire planning horizon translate directly into misclassified patients, regulatory capital failures, grid imbalances, and safety-case violations. CSP achieves all of this with no learned parameters and no training. We argue training-free conformal samplers should be mandatory baselines when evaluating learned non-parametric forecasters.

Turning ideas into full software projects from scratch has become a popular use case for language models. Agents are being deployed to seed, maintain, and grow codebases over extended periods with minimal human oversight. Such settings require models to make high-level software architecture decisions. However, existing benchmarks measure focused, limited tasks such as fixing a single bug or developing a single, specified feature. We therefore introduce ProgramBench to measure the ability of software engineering agents to develop software holisitically. In ProgramBench, given only a program and its documentation, agents must architect and implement a codebase that matches the reference executable's behavior. End-to-end behavioral tests are generated via agent-driven fuzzing, enabling evaluation without prescribing implementation structure. Our 200 tasks range from compact CLI tools to widely used software such as FFmpeg, SQLite, and the PHP interpreter. We evaluate 9 LMs and find that none fully resolve any task, with the best model passing 95% of tests on only 3% of tasks. Models favor monolithic, single-file implementations that diverge sharply from human-written code.

Real-world video editing demands not only expert knowledge of cinematic techniques but also multimodal reasoning to select, align, and combine footage into coherent narratives. While recent Large Multimodal Models (LMMs) have shown remarkable progress in general video understanding, their abilities in multi-video reasoning and operational editing workflows remain largely unexplored. We introduce VEBENCH, the first comprehensive benchmark designed to evaluate both editing knowledge understanding and operational reasoning in realistic video editing scenarios. VEBENCH contains 3.9K high-quality edited videos (over 257 hours) and 3,080 human-verified QA pairs, built through a three-round human-AI collaborative annotation pipeline that ensures precise temporal labeling and semantic consistency. It features two complementary QA tasks: 1) Video Editing Technique Recognition, assessing models' ability to identify 7 editing techniques using multimodal cues; and 2) Video Editing Operation Simulation, modeling real-world editing workflows by requiring the selection and temporal localization of relevant clips from multiple candidates. Extensive experiments across proprietary (e.g., Gemini-2.5-Pro) and open-source LMMs reveal a large gap between current model performance and human-level editing cognition. These results highlight the urgent need for bridging video understanding with creative operational reasoning. We envision VEBENCH as a foundation for advancing intelligent video editing systems and driving future research on complex reasoning.

Human-level agentic intelligence extends beyond low-level geometric perception, evolving from recognizing where things are to understanding what they are for. While existing benchmarks effectively evaluate the geometric perception capabilities of multimodal large language models (MLLMs), they fall short of probing the higher-order cognitive abilities required for grounded intelligence. To address this gap, we introduce the Spatial-Functional Intelligence Benchmark (SFI-Bench), a video-based benchmark with over 1,500 expert-annotated questions derived from diverse egocentric indoor video scans. SFI-Bench systematically evaluates two complementary dimensions of advanced reasoning: (1) Structured Spatial Reasoning, which requires understanding complex layouts and forming coherent spatial representations, and (2) Functional Reasoning, which involves inferring object affordances and their context-dependent utility. The benchmark includes tasks such as conditional counting, multi-hop relational reasoning, functional pairing, and knowledge-grounded troubleshooting, directly challenging models to integrate perception, memory, and inference. Our experiments reveal that current MLLMs consistently struggle to combine spatial memory with functional reasoning and external knowledge, highlighting a critical bottleneck in achieving grounded intelligence. SFI-Bench therefore provides a diagnostic tool for measuring progress toward more cognitively capable and truly grounded multimodal agents.

Machine Learning (ML) has transformed many scientific fields, yet key applications still lack standardized benchmarks. Raman spectroscopy, a widely used technique for non-invasive molecular analysis, is one such field where progress is limited by fragmented datasets, inconsistent evaluation, and models that fail to capture the structure of spectral data. We introduce RamanBench, the first large-scale, fully reproducible benchmark for ML on Raman spectroscopy, consisting of streamlined data access, evaluation protocols and code, as well as a live leaderboard. It unifies 74 datasets (including 16 first released with this benchmark) across four domains, comprising 325,668 spectra and spanning classification and regression tasks under diverse experimental conditions. We benchmark 28 models under a standardized protocol, including classical methods (e.g., PLS), Raman-specific (e.g., RamanNet), Tabular Foundation Model (TFM) (e.g., TabPFN), and time-series approaches (e.g., ROCKET). TFM consistently outperform domain-specific and gradient boosting baselines, while time-series models remain competitive. However, no method generalizes across datasets, revealing a fundamental gap. Therefore, we invite the community to contribute new approaches to our living benchmark, with the potential to accelerate advances in critical applications such as medical diagnostics, biological research, and materials science.

Structured launch signals on Product Hunt contain statistically significant predictive information for Series A funding outcomes. We construct PHBench from 67,292 featured Product Hunt posts spanning 2019-2025, linked to Crunchbase funding records via deterministic domain matching, identifying 528 verified Series A raises within 18 months of launch (positive rate: 0.78%). Our best-performing model, a three-component ensemble (ENS_avg, ENS_ISO, XGB) selected by validation F0.5, achieves F0.5 = 0.097 and AP = 0.037 (95% CI: 0.024-0.072; 4.7x lift over random) on the private held-out test set (103 positives). A paired bootstrap confirms a statistically credible advantage over the logistic regression baseline (AP delta: +0.013, 95% CI: [0.004, 0.039], p < 0.001; F0.5 delta: +0.056, 95% CI: [0.006, 0.122], p = 0.016). Validation-set metrics (F0.5 = 0.284, AP = 0.126) reflect best-of-144 selection bias on 53 positives and are reported for benchmark reproducibility only. We further evaluate three zero-shot Gemini models (Gemini 2.5 Flash, Gemini 3 Flash, and Gemini 3.1 Pro) in an anonymized numerical setting. The best LLM achieves AP = 0.034 (Gemini 3 Flash), below the LR baseline AP of 0.044. Notably, the most capable Gemini variant (Gemini 3.1 Pro, AP = 0.023) performs worst -- an unexpected pattern that warrants further investigation across providers and prompting strategies. Both ML and LLM models show the same temporal performance decay tracking the 2020-2021 funding boom and subsequent contraction, confirming the dataset captures genuine market structure rather than noise. PHBench provides a reproducible framework comprising public training, validation, and blind test splits; 61 engineered features; a five-metric evaluation harness; and a public leaderboard at https://phbench.com. All code, baseline models, and anonymized dataset splits are publicly available.

Outcome-only evaluation under-specifies whether an evaluated agent profile preserves the commitments required to solve a multi-turn task coherently. NeuroState-Bench is a human-calibrated benchmark that operationalizes commitment integrity through benchmark-defined side-query probes rather than inferred hidden activations. The released inventory contains 144 deterministic tasks and 306 benchmark-defined side-query probes spanning eight cognitively motivated failure families, paired clean and distractor variants, and three difficulty bands. The main 32-profile evaluation contains a fixed 16-profile local subset and a matched 16-profile hosted large-model subset evaluated through the same benchmark pipeline. Human calibration uses the final merged reporting scope: 104 sampled task units, 216 raw annotations, and 108 adjudicated task rows, with weighted kappa = 0.977 and ICC(2,1) = 0.977. Empirically, task success and commitment integrity diverge across this expanded grid: the success leader is not the integrity leader, 31 of 32 profiles change rank when integrity replaces task success, and integrity rankings are more stable under distractor perturbation. The primary confidence-free score HCCIS-CORE reaches 0.8469 AUC and 0.6992 PR-AUC for post-probe diagnostic discrimination of terminal task failure; the legacy full heuristic variant HCCIS-FULL reaches 0.7997 AUC and 0.6410 PR-AUC. Probe accuracy and state drift achieve slightly higher ROC-AUC, 0.8587, and better Brier/ECE, while HCCIS-CORE has substantially higher point-estimate PR-AUC and remains more closely tied to the benchmark's intended construct. The exploratory neural-augmented variant HCCIS+N is weaker overall, and a randomized subspace control approaches chance. NeuroState-Bench therefore contributes a calibrated evaluation axis for exposing commitment failures over a broader model grid than the original local-only subset.

The primary goal of Design Verification (DV) is to ensure that a proposed chip design implementation (either in code, or physical form) exactly matches its specification and is free of functional errors in order to avoid costly re-designs. Achieving this often demands extensive manual interpretation, translating the specification document into a formal, testable representation. While AI has made progress in DV, current approaches typically focus on narrow, isolated tasks rather than full end-to-end specification compliance of modern chip designs, failing to capture the complexity of real-world verification. Our method automatically formalizes natural language memory chip specifications, for industry relevant Dynamic Random Access Memory (DRAM) standards, into a formal representation called DRAMPyML that can be used for downstream DV tasks like the generation of SystemVerilog assertions, stimulus, and functional coverage. We also release our benchmarking dataset, DRAMBench, which can be used to evaluate the evolution of model capabilities (and new approaches) at hardware autoformalization.

Today's AI assistants such as OpenClaw are designed to handle context effectively, making context learning an increasingly important capability for models. As these systems move beyond professional settings into everyday life, the nature of the contexts they must handle also shifts. Real-life contexts are often messy, fragmented, and deeply tied to personal and social experience, such as multi-party conversations, personal archives, and behavioral traces. Yet it remains unclear whether current frontier language models can reliably learn from such contexts and solve tasks grounded in them. To this end, we introduce CL-bench Life, a fully human-curated benchmark comprising 405 context-task pairs and 5,348 verification rubrics, covering common real-life scenarios. Solving tasks in CL-bench Life requires models to reason over complex, messy real-life contexts, calling for strong real-life context learning abilities that go far beyond those evaluated in existing benchmarks. We evaluate ten frontier LMs and find that real-life context learning remains highly challenging: even the best-performing model achieves only 19.3% task solving rate, while the average performance across models is only 13.8%. Models still struggle to reason over contexts such as messy group chat histories and fragmented behavioral records from everyday life. CL-bench Life provides a crucial testbed for advancing real-life context learning, and progress on it can enable more intelligent and reliable AI assistants in everyday life.

Deploying a neuro-symbolic task planner on a new domain today requires significant manual effort: a domain expert must author relaxation and complementary rules, and hundreds of training problems must be solved to supervise a Graph Neural Network (GNN) object scorer. We propose LLM-Flax, a three-stage framework that eliminates all three sources of manual effort using a locally hosted LLM given only a PDDL domain file. Stage 1 automatically generates relaxation and complementary rules via structured prompting with format validation and self-correction. Stage 2 introduces LLM-guided failure recovery with a feasibility-gated budget policy that explicitly reserves API latency cost before each LLM call, preventing the downstream relaxation fallback from being starved. Stage 3 replaces the domain-trained GNN entirely with zero-shot LLM object importance scoring, requiring no training data. We evaluate all three stages on the MazeNamo benchmark across 10x10, 12x12, and 15x15 grids (8 benchmarks total). LLM-Flax achieves average SR 0.945 versus the manual baseline's 0.828 (+0.117), matching or outperforming manual rules on every one of the eight benchmarks. On 12x12 Expert, LLM-Flax attains SR 0.733 where the manual planner fails entirely (SR 0.000); on 15x15 Hard, it achieves SR 1.000 versus Manual's 0.900. Stage 3 demonstrates feasibility (SR 0.720 on 12x12 Hard with no training data) but faces a context-window bottleneck at scale, pointing to the primary open challenge for future work.

We introduce a novel task of digital battery passport (DBP) conformance classification and introduce the first public benchmark for the task: BatteryPass-12K, created synthetically from real pilot samples. This is as the EU's battery regulation on DBPs comes into effect soon and there exists no public dataset. We evaluated 22 language models (LMs) in zero-shot inference, spanning small LMs (SLMs), mixture of experts (MoEs), and dense LLMs. We also conducted analysis, additional evaluations of few-shot inference and prompt-injection attacks to find that (1) Thinking models have the best performance (with GPT-5.4 scoring 0.98 (0.03) and 0.71 (0.22) on average as F1 (and confidence interval at 95%) on the validation and test sets, respectively), (2) few-shot examples improve performance significantly, (3) generally capable frontier models find the task challenging, (4) merely scaling model parameters does not necessarily lead to improved performance, as SLMs outperformed some LLMs, and (5) prompt-injection attacks degrade performance. We note that BatteryPass-12K, though limited to real pilot samples, may be useful for other known or emerging tasks in the battery domain, e.g. lifecycle reasoning. We publicly release the dataset under a permissive licence (CC-BY-4.0).

Static benchmarks measure what AI agents can do at a fixed point in time but not how they are adopted, maintained, or experienced in deployment. We introduce AgentPulse, a continuous evaluation framework scoring 50 agents across 10 workload categories along four factors (Benchmark Performance, Adoption Signals, Community Sentiment, and Ecosystem Health) aggregated from 18 real-time signals across GitHub, package registries, IDE marketplaces, social platforms, and benchmark leaderboards. Three analyses ground the framework. The four factors capture largely complementary information (n=50; $ρ_{\max}=0.61$ for Adoption-Ecosystem, all others $|ρ| \leq 0.37$). A circularity-controlled test (n=35) shows the Benchmark+Sentiment sub-composite, which contains no GitHub-derived signals, predicts external adoption proxies it does not aggregate: GitHub stars ($ρ_s=0.52$, $p<0.01$) and Stack Overflow question volume ($ρ_s=0.49$, $p<0.01$), with VS Code installs ($ρ_s=0.44$, $p<0.05$) reported as illustrative given that only 11 of 35 agents have non-zero installs. On the n=11 subset with published SWE-bench scores, composite and benchmark-only rankings are nearly uncorrelated ($ρ_s=0.25$; 9 of 11 agents shift by at least 2 ranks), driven by a strong negative Adoption-Capability correlation among closed-source high-capability agents within this subset. This is precisely why we rest the framework's validity claim on the broader n=35 test rather than the SWE-bench overlap. AgentPulse surfaces deployment signal absent from benchmarks; it is a methodology, not a ground-truth ranking. The framework, all collected signals, scoring outputs, and evaluation harness are released under CC BY 4.0.

Recent image generation and editing models demonstrate robust adherence to instructions and high visual quality on academic benchmarks. However, their performance on paid, real-world design projects remains uncertain. We introduce \textbf{ServImage}, a benchmark that explicitly correlates model outputs with economic value in commercial design projects. ServImage consists of (i) \textbf{\textit{ServImageBench}}: a dataset of 1.07k paid commercial design tasks and 2.05k designer deliverables totaling over $295k, covering portrait, product, and digital content, along with 33k candidate images and 33k human annotations. (ii) \textbf{\textit{ServImageScore}}: an integrated scoring system that combines three quality dimensions: baseline requirements fulfilment, visual execution quality, and commercial necessity satisfaction. These three dimensions are designed to characterize the factors that drive human payment decisions and indicate whether an image is commercially acceptable. (iii) \textbf{\textit{ServImageModel}}: under this scoring system, we propose a payment prediction model trained on the human-annotated candidate images, achieving 82.00% accuracy in predicting human payment decisions and producing calibrated payment probabilities. ServImage provides a comprehensive foundation for assessing the commercial viability of image generation models and offers a scalable resource for future research on economically grounded vision systems \href{https://github.com/FengxianJi/ServImage}{Github.}

AI-agent guardrails are memoryless: each message is judged in isolation, so an adversary who spreads a single attack across dozens of sessions slips past every session-bound detector because only the aggregate carries the payload. We make three contributions to cross-session threat detection. (1) Dataset. CSTM-Bench is 26 executable attack taxonomies classified by kill-chain stage and cross-session operation (accumulate, compose, launder, inject_on_reader), each bound to one of seven identity anchors that ground-truth "violation" as a policy predicate, plus matched Benign-pristine and Benign-hard confounders. Released on Hugging Face as intrinsec-ai/cstm-bench with two 54-scenario splits: dilution (compositional) and cross_session (12 isolation-invisible scenarios produced by a closed-loop rewriter that softens surface phrasing while preserving cross-session artefacts). (2) Measurement. Framing cross-session detection as an information bottleneck to a downstream correlator LLM, we find that a session-bound judge and a Full-Log Correlator concatenating every prompt into one long-context call both lose roughly half their attack recall moving from dilution to cross_session, well inside any frontier context window. Scope: 54 scenarios per shard, one correlator family (Anthropic Claude), no prompt optimisation; we release it to motivate larger, multi-provider datasets. (3) Algorithm and metric. A bounded-memory Coreset Memory Reader retaining highest-signal fragments at $K=50$ is the only reader whose recall survives both shards. Because ranker reshuffles break KV-cache prefix reuse, we promote $\mathrm{CSR\_prefix}$ (ordered prefix stability, LLM-free) to a first-class metric and fuse it with detection into $\mathrm{CSTM} = 0.7 F_1(\mathrm{CSDA@action}, \mathrm{precision}) + 0.3 \mathrm{CSR\_prefix}$, benchmarking rankers on a single Pareto of recall versus serving stability.

We introduce TravelFraudBench (TFG), a configurable benchmark for evaluating graph neural networks (GNNs) on fraud ring detection in travel platform graphs. Existing benchmarks--YelpChi, Amazon-Fraud, Elliptic, PaySim--cover single node types or domain-generic patterns with no mechanism to evaluate across structurally distinct fraud ring topologies. TFG simulates three travel-specific ring types--ticketing fraud (star topology with shared device/IP clusters), ghost hotel schemes (reviewer x hotel bipartite cliques), and account takeover rings (loyalty transfer chains)--in a heterogeneous graph with 9 node types and 12 edge types. Ring size, count, fraud rate, scale (500 to 200,000 nodes), and composition are fully configurable. We evaluate six methods--MLP, GraphSAGE, RGCN-proj, HAN, RGCN, and PC-GNN--under a ring-based split where each ring appears entirely in one partition, eliminating transductive label leakage. GraphSAGE achieves AUC=0.992 and RGCN-proj AUC=0.987, outperforming the MLP baseline (AUC=0.938) by 5.5 and 5.0 pp, confirming graph structure adds substantial discriminative power. HAN (AUC=0.935) is a negative result, matching the MLP baseline. On the ring recovery task (>=80% of ring members flagged simultaneously), GraphSAGE achieves 100% recovery across all ring types; MLP recovers only 17-88%. The edge-type ablation shows device and IP co-occurrence are the primary signals: removing uses_device drops AUC by 5.2 pp. TFG is released as an open-source Python package (MIT license) with PyG, DGL, and NetworkX exporters and pre-generated datasets at https://huggingface.co/datasets/bsajja7/travel-fraud-graphs, with Croissant metadata including Responsible AI fields.

Spatial intelligence is essential for multimodal large language models, yet current benchmarks largely assess it only from an understanding perspective. We ask whether modern generative or unified multimodal models also possess generative spatial intelligence (GSI), the ability to respect and manipulate 3D spatial constraints during image generation, and whether such capability can be measured or improved. We introduce GSI-Bench, the first benchmark designed to quantify GSI through spatially grounded image editing. It consists of two complementary components: GSI-Real, a high-quality real-world dataset built via a 3D-prior-guided generation and filtering pipeline, and GSI-Syn, a large-scale synthetic benchmark with controllable spatial operations and fully automated labeling. Together with a unified evaluation protocol, GSI-Bench enables scalable, model-agnostic assessment of spatial compliance and editing fidelity. Experiments show that fine-tuning unified multimodal models on GSI-Syn yields substantial gains on both synthetic and real tasks and, strikingly, also improves downstream spatial understanding. This provides the first clear evidence that generative training can tangibly strengthen spatial reasoning, establishing a new pathway for advancing spatial intelligence in multimodal models.

We introduce LegalBench-BR, the first public benchmark for evaluating language models on Brazilian legal text classification. The dataset comprises 3,105 appellate proceedings from the Santa Catarina State Court (TJSC), collected via the DataJud API (CNJ) and annotated across five legal areas through LLM-assisted labeling with heuristic validation. On a class-balanced test set, BERTimbau-LoRA, updating only 0.3% of model parameters, achieves 87.6% accuracy and 0.87 macro-F1 (+22pp over Claude 3.5 Haiku, +28pp over GPT-4o mini). The gap is most striking on administrativo (administrative law): GPT-4o mini scores F1 = 0.00 and Claude 3.5 Haiku scores F1 = 0.08 on this class, while the fine-tuned model reaches F1 = 0.91. Both commercial LLMs exhibit a systematic bias toward civel (civil law), absorbing ambiguous classes rather than discriminating them, a failure mode that domain-adapted fine-tuning eliminates. These results demonstrate that general-purpose LLMs cannot substitute for domain-adapted models in Brazilian legal classification, even when the task is a simple 5-class problem, and that LoRA fine-tuning on a consumer GPU closes the gap at zero marginal inference cost. We release the full dataset, model, and pipeline to enable reproducible research in Portuguese legal NLP.

As reinforcement learning continues to scale the training of large language model-based agents, reliably verifying agent behaviors in complex environments has become increasingly challenging. Existing approaches rely on rule-based verifiers or LLM-as-a-Judge models, which struggle to generalize beyond narrow domains. Agent-as-a-Judge addresses this limitation by actively interacting with environments and tools to acquire verifiable evidence, yet its capabilities remain underexplored. We introduce a benchmark AJ-Bench to systematically evaluate Agent-as-a-Judge across three domains-search, data systems, and graphical user interfaces-comprising 155 tasks and 516 annotated trajectories. The benchmark comprehensively assesses judge agents' abilities in information acquisition, state verification, and process verification. Experiments demonstrate consistent performance gains over LLM-as-a-Judge baselines, while also revealing substantial open challenges in agent-based verification. Our data and code are available at https://aj-bench.github.io/.

Peripheral Blood Smear (PBS) is a critical microscopic examination in hematopathology that yields whole-slide imaging (WSI). Unlike solid tissue pathology, PBS interpretation focuses on individual cell morphologies rather than tissue architecture, making it distinct in both visual characteristics and diagnostic reasoning. However, current multimodal large language models (MLLMs) for pathology are primarily developed on solid-tissue WSIs and struggle to generalize to PBS. To bridge this gap, we construct PBSInstr, the first vision-language dataset for PBS interpretation, comprising 353 PBS WSIs paired with microscopic impression paragraphs and 29k cell-level image crops annotated with cell type labels and morphological descriptions. To facilitate instruction tuning, PBSInstr further includes 27k question-answer (QA) pairs for cell crops and 1,286 QA pairs for PBS slides. Building upon PBSInstr, we develop PBS-VL, a hematopathology-tailored vision-language model for multi-level PBS interpretation at both cell and slide levels. To comprehensively evaluate PBS understanding, we construct PBSBench, a visual question answering (VQA) benchmark featuring four question categories and six PBS interpretation tasks. Experiments show that PBS-VL outperforms existing general-purpose and pathology MLLMs, underscoring the value of PBS-specific data. We release our code, datasets, and model weights to facilitate future research. Our proposed framework lays the foundation for developing practical AI assistants supporting decision-making in hematopathology.

Climate research is pivotal for mitigating global environmental crises, yet the accelerating volume of multi-scale datasets and the complexity of analytical tools have created significant bottlenecks, constraining scientific discovery to fragmented and labor-intensive workflows. While the emergence Large Language Models (LLMs) offers a transformative paradigm to scale scientific expertise, existing explorations remain largely confined to simple Question-Answering (Q&A) tasks. These approaches often oversimplify real-world challenges, neglecting the intricate physical constraints and the data-driven nature required in professional climate science.To bridge this gap, we introduce ClimAgent, a general-purpose autonomous framework designed to execute a wide spectrum of research tasks across diverse climate sub-fields. By integrating a unified tool-use environment with rigorous reasoning protocols, ClimAgent transcends simple retrieval to perform end-to-end modeling and analysis. To foster systematic evaluation, we propose ClimaBench, the first comprehensive benchmark for real-world climate discovery. It encompasses challenging problems spanning 5 distinct task categories derived from professional scenarios between 2000 and 2025. Experiments on ClimaBench demonstrate that ClimAgent significantly outperforms state-of-the-art baselines, achieving a 40.21% improvement over original LLM solutions in solution rigorousness and practicality. Our code are available at https://github.com/usail-hkust/ClimAgent.

We introduce JFinTEB, the first comprehensive benchmark specifically designed for evaluating Japanese financial text embeddings. Existing embedding benchmarks provide limited coverage of language-specific and domain-specific aspects found in Japanese financial texts. Our benchmark encompasses diverse task categories including retrieval and classification tasks that reflect realistic and well-defined financial text processing scenarios. The retrieval tasks leverage instruction-following datasets and financial text generation queries, while classification tasks cover sentiment analysis, document categorization, and domain-specific classification challenges derived from economic survey data. We conduct extensive evaluations across a wide range of embedding models, including Japanese-specific models of various sizes, multilingual models, and commercial embedding services. We publicly release JFinTEB datasets and evaluation framework at https://github.com/retarfi/JFinTEB to facilitate future research and provide a standardized evaluation protocol for the Japanese financial text mining community. This work addresses a critical gap in Japanese financial text processing resources and establishes a foundation for advancing domain-specific embedding research.

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

Open-vocabulary remote sensing image segmentation (OVRSIS) remains underexplored due to fragmented datasets, limited training diversity, and the lack of evaluation benchmarks that reflect realistic geospatial application demands. Our previous \textit{OVRSISBenchV1} established an initial cross-dataset evaluation protocol, but its limited scope is insufficient for assessing realistic open-world generalization. To address this issue, we propose \textit{OVRSISBenchV2}, a large-scale and application-oriented benchmark for OVRSIS. We first construct \textbf{OVRSIS95K}, a balanced dataset of about 95K image--mask pairs covering 35 common semantic categories across diverse remote sensing scenes. Built upon OVRSIS95K and 10 downstream datasets, OVRSISBenchV2 contains 170K images and 128 categories, substantially expanding scene diversity, semantic coverage, and evaluation difficulty. Beyond standard open-vocabulary segmentation, it further includes downstream protocols for building extraction, road extraction, and flood detection, thereby better reflecting realistic geospatial application demands and complex deployment scenarios. We also propose \textbf{Pi-Seg}, a baseline for OVRSIS. Pi-Seg improves transferability through a \textbf{positive-incentive noise} mechanism, where learnable and semantically guided perturbations broaden the visual-text feature space during training. Extensive experiments on OVRSISBenchV1, OVRSISBenchV2, and downstream tasks show that Pi-Seg delivers strong and consistent results, particularly on the more challenging OVRSISBenchV2 benchmark. Our results highlight both the importance of realistic benchmark design and the effectiveness of perturbation-based transfer for OVRSIS. The code and datasets are available at \href{https://github.com/LiBingyu01/Pi-Seg}{LiBingyu01/Pi-Seg}.

Training GUI agents with traditional centralized methods faces significant cost and scalability challenges. Federated learning (FL) offers a promising solution, yet its potential is hindered by the lack of benchmarks that capture real-world, cross-platform heterogeneity. To bridge this gap, we introduce FedGUI, the first comprehensive benchmark for developing and evaluating federated GUI agents across mobile, web, and desktop platforms. FedGUI provides a suite of six curated datasets to systematically study four crucial types of heterogeneity: cross-platform, cross-device, cross-OS, and cross-source. Extensive experiments reveal several key insights: First, we show that cross-platform collaboration improves performance, extending prior mobile-only federated learning to diverse GUI environments; Second, we demonstrate the presence of distinct heterogeneity dimensions and identify platform and OS as the most influential factors. FedGUI provides a vital foundation for the community to build more scalable and privacy-preserving GUI agents for real-world deployment. Our code and data are publicly available at https://github.com/wwh0411/FedGUI..

As agent systems move into increasingly diverse execution settings, trajectory-level safety evaluation and diagnosis require benchmarks that evolve with them. ATBench is a diverse and realistic agent trajectory benchmark for safety evaluation and diagnosis. This report presents ATBench-Claw and ATBench-Codex, two domain-customized extensions that carry ATBench into the OpenClaw and OpenAI Codex / Codex-runtime settings. The key adaptation mechanism is to analyze each new setting, customize the three-dimensional Safety Taxonomy over risk source, failure mode, and real-world harm, and then use that customized taxonomy to define the benchmark specification consumed by the shared ATBench construction pipeline. This extensibility matters because agent frameworks remain relatively stable at the architectural level even as their concrete execution settings, tool ecosystems, and product capabilities evolve quickly. Concretely, ATBench-Claw targets OpenClaw-sensitive execution chains over tools, skills, sessions, and external actions, while ATBench-Codex targets trajectories in the OpenAI Codex / Codex-runtime setting over repositories, shells, patches, dependencies, approvals, and runtime policy boundaries. Our emphasis therefore falls on taxonomy customization, domain-specific risk coverage, and benchmark design under a shared ATBench generation framework.

Recent AI systems have achieved gold-medal-level performance on the International Mathematical Olympiad, demonstrating remarkable proficiency at competition-style problem solving. However, competition mathematics represents only a narrow slice of mathematical reasoning: problems are drawn from limited domains, require minimal advanced machinery, and can often reward insightful tricks over deep theoretical knowledge. We introduce Riemann-Bench, a private benchmark of expert-curated problems designed to evaluate AI systems on research-level mathematics that goes far beyond the olympiad frontier. Problems are authored by Ivy League mathematics professors, graduate students, and PhD-holding IMO medalists, and routinely took their authors weeks to solve independently. Each problem undergoes double-blind verification by two independent domain experts who must solve the problem from scratch, and yields a unique, closed-form solution assessed by programmatic verifiers. We evaluate frontier models as unconstrained research agents, with full access to coding tools, search, and open-ended reasoning, using an unbiased statistical estimator computed over 100 independent runs per problem. Our results reveal that all frontier models currently score below 10%, exposing a substantial gap between olympiad-level problem solving and genuine research-level mathematical reasoning. By keeping the benchmark fully private, we ensure that measured performance reflects authentic mathematical capability rather than memorization of training data.

Recent advances in large audio language models (LALMs) have enabled multilingual speech understanding. However, benchmarks for evaluating LALMs remain scarce for non-English languages, with Korean being one such underexplored case. In this paper, we introduce KoALa-Bench, a comprehensive benchmark for evaluating Korean speech understanding and speech faithfulness of LALMs. In particular, KoALa-Bench comprises six tasks. Four tasks evaluate fundamental speech understanding capabilities, including automatic speech recognition, speech translation, speech question answering, and speech instruction following, while the remaining two tasks evaluate speech faithfulness, motivated by our observation that several LALMs often fail to fully leverage the speech modality. Furthermore, to reflect Korea-specific knowledge, our benchmark incorporates listening questions from the Korean college scholastic ability test as well as content covering Korean cultural domains. We conduct extensive experiments across six models, including both white-box and black-box ones. Our benchmark, evaluation code, and leaderboard are publicly available at https://ksbench.github.io/Korean-Benchmark/.

Large Language Models (LLMs) have shown remarkable potential in developing role-playing agents (RPAs). However, current evaluation frameworks rely heavily on well-known fictional characters, raising a critical concern: models may be leveraging their internal training memory of these characters rather than demonstrating role-playing capabilities. This reliance often leads to significant performance degradation when RPAs encounter unseen or out-of-distribution personas. To address this, we propose a more rigorous evaluation protocol designed to decouple role-playing proficiency from character recognition. Our experiments across multiple benchmarks demonstrate that anonymizing characters degrades performance, confirming that name exposure provides implicit cues that mask a model's true capability. To mitigate this, we investigate diverse personality augmentation as a method to enhance role fidelity in anonymous settings. We systematically analyze the impact of various personality-description methods on agent behavior and consistency. Our results show that incorporating personality information consistently improves RPA performance. This work establishes a more equitable evaluation standard and validates a scalable, personality-enhanced framework for constructing robust RPAs.

Topic localization aims to identify spans of text that express a given topic defined by a name and description. To study this task, we introduce a human-annotated benchmark based on Czech historical documents, containing human-defined topics together with manually annotated spans and supporting evaluation at both document and word levels. Evaluation is performed relative to human agreement rather than a single reference annotation. We evaluate a diverse range of large language models alongside BERT-based models fine-tuned on a distilled development dataset. Results reveal substantial variability among LLMs, with performance ranging from near-human topic detection to pronounced failures in span localization. While the strongest models approach human agreement, the distilled token embedding models remain competitive despite their smaller scale. The dataset and evaluation framework are publicly available at: https://github.com/dcgm/czechtopic.

Despite rapid progress on coding agents, progress on their multimodal counterparts has lagged behind. A key challenge is the scarcity of evaluation testbeds that combine the complexity of software development with the need for deep multimodal understanding. In game development, agents must navigate large, dense codebases while manipulating intrinsically multimodal assets such as shaders, sprites, and animations within a visual game scene. We present GameDevBench, the first benchmark for evaluating agents on game development tasks. GameDevBench consists of 333 tasks derived from web and video tutorials. Tasks require significant multimodal understanding and are complex: the average solution requires over three times the lines of code and file changes compared to prior software development benchmarks. Agents struggle with game development, with the best agent and method solving only 53.8% of tasks. We find a strong correlation between perceived task difficulty and multimodal complexity, with average success rate dropping from 51.4% on gameplay-oriented tasks to 33.0% on 2D graphics tasks. To improve multimodal capability, we introduce two simple image- and video-based feedback mechanisms for agents. Despite their simplicity, these methods consistently improve performance, increasing GPT-5.4's performance from 41.1% to 52.0% when given visual feedback.

This paper proposes Omni Dense Captioning, a novel task designed to generate continuous, fine-grained, and structured audio-visual narratives with explicit timestamps. To ensure dense semantic coverage, we introduce a six-dimensional structural schema to create "script-like" captions, enabling readers to vividly imagine the video content scene by scene, akin to a cinematographic screenplay. To facilitate research, we construct OmniDCBench, a high-quality, human-annotated benchmark, and propose SodaM, a unified metric that evaluates time-aware detailed descriptions while mitigating scene boundary ambiguity. Furthermore, we construct a training dataset, TimeChatCap-42K, and present TimeChat-Captioner-7B, a strong baseline trained via SFT and GRPO with task-specific rewards. Extensive experiments demonstrate that TimeChat-Captioner-7B achieves state-of-the-art performance, surpassing Gemini-2.5-Pro, while its generated dense descriptions significantly boost downstream capabilities in audio-visual reasoning (DailyOmni and WorldSense) and temporal grounding (Charades-STA). All datasets, models, and code are available at https://github.com/yaolinli/TimeChat-Captioner.

Engineering construction automation aims to transform natural language specifications into physically viable structures, requiring complex integrated reasoning under strict physical constraints. While modern LLMs possess broad knowledge and strong reasoning capabilities that make them promising candidates for this domain, their construction competencies remain largely unevaluated. To address this gap, we introduce BuildArena, the first physics-aligned interactive benchmark designed for language-driven engineering construction. Technically, it contributes to the community in two aspects: (1) an extendable task design strategy spanning static and dynamic mechanics across multiple difficulty tiers; (2) a 3D Spatial Geometric Computation Library for supporting construction based on language instructions. On nine frontier LLMs and three additional open-weight models, BuildArena comprehensively evaluates their capabilities for language-driven and physics-grounded construction automation. We release the code at https://github.com/AI4Science-WestlakeU/BuildArena to benefit construction automation in engineering applications.

In our deployed travel-planning service, most users give minimal inputs or free-form requests rather than the structured constraint checklists assumed by existing benchmarks. We therefore present TripScore, a behavior-grounded benchmark and evaluation framework built from real user logs and calibrated against 1,468 pairwise judgments by 203 travel experts. TripScore couples a hierarchical feasibility gate (format and commonsense) with a unified, point-wise reward that aggregates soft quality and preference fulfillment. Using TripScore as both evaluator and reward signal, we benchmark direct prompting, test-time compute, neuro-symbolic solvers, code agents, and fine-tuning. We find that reinforcement learning fine-tuning (e.g., GRPO) provides consistent gains over other approaches under the same base model and practical latency.

As the mathematical capabilities of large language models (LLMs) improve, it becomes increasingly important to evaluate their performance on research-level tasks at the frontier of mathematical knowledge. However, existing benchmarks are limited, as they focus solely on final-answer questions or high-school competition problems. To address this gap, we introduce IMProofBench, a private benchmark consisting of 77 peer-reviewed problems developed by expert mathematicians. Each problem requires a detailed proof and is paired with subproblems that have final answers, supporting both an evaluation by human experts and a large-scale quantitative analysis through automated grading. Furthermore, unlike prior benchmarks, the evaluation setup simulates a realistic research environment: models operate in an agentic framework with tools like web search for literature review and mathematical software such as SageMath. Our results show that current LLMs can already solve a significant percentage of research-level questions. IMProofBench will continue to evolve as a dynamic benchmark in collaboration with the mathematical community, ensuring its relevance for evaluating the next generation of LLMs.

Most existing safe reinforcement learning (RL) benchmarks focus on robotics and control tasks, offering limited relevance to high-stakes domains that involve structured constraints, mixed-integer decisions, and industrial complexity. This gap hinders the advancement and deployment of safe RL in critical areas such as energy systems, manufacturing, and supply chains. To address this limitation, we present SafeOR-Gym, a benchmark suite of nine operations research (OR) environments tailored for safe RL under complex constraints. Each environment captures a realistic planning, scheduling, or control problems characterized by cost-based constraint violations, planning horizons, and hybrid discrete-continuous action spaces. The suite integrates seamlessly with the Constrained Markov Decision Process (CMDP) interface provided by OmniSafe. We evaluate several state-of-the-art safe RL algorithms across these environments, revealing a wide range of performance: while some tasks are tractable, others expose fundamental limitations in current approaches. SafeORGym provides a challenging and practical testbed that aims to catalyze future research in safe RL for real-world decision-making problems.

Function-guided protein design is a crucial task with significant applications in drug discovery and enzyme engineering. However, the field lacks a unified and comprehensive evaluation framework. Current models are assessed using inconsistent and limited subsets of metrics, which prevents fair comparison and a clear understanding of the relationships between different evaluation criteria. To address this gap, we introduce PDFBench, the first comprehensive benchmark for function-guided denovo protein design. Our benchmark systematically evaluates eight state-of-the-art models on 16 metrics across two key settings: description-guided design, for which we repurpose the Mol-Instructions dataset, originally lacking quantitative benchmarking, and keyword-guided design, for which we introduce a new test set, SwissTest, created with a strict datetime cutoff to ensure data integrity. By benchmarking across a wide array of metrics and analyzing their correlations, PDFBench enables more reliable model comparisons and provides key insights to guide future research.

Although recent large multimodal models (LMMs) show impressive progress on vision language tasks, their alignment with human centered (HC) principles such as fairness, ethics, inclusivity, empathy, and robustness is often overlooked. Existing LMM benchmarks are largely accuracy-agnostic. We present HumaniBench, a unified framework for characterizing HC alignment across realistic, socially grounded visual contexts. It contains 32,000 expert-verified image-question pairs from real-world news imagery, each mapped to one or more HC principles through explicit metrics. Comparing 15 state of the art LMMs reveals consistent trade -offs: proprietary systems lead on ethics, reasoning, and empathy, while open-source models show superior visual grounding and resilience. All models show persistent gaps in fairness and multilingual inclusivity. Chain-of-thought prompting and test-time scaling yield 8to 12 % gains on several HC dimensions. HumaniBench enables fine-grained analysis of alignment trade-offs not captured by conventional multimodal benchmarks. https://vectorinstitute.github.io/humanibench/

Verifying the authenticity of AI-generated images presents a growing challenge on social media platforms these days. While vision-language models (VLMs) like CLIP outdo in multimodal representation, their capacity for AI-generated image classification is underexplored due to the absence of such labels during the pre-training process. This work investigates whether CLIP embeddings inherently contain information indicative of AI generation. A proposed pipeline extracts visual embeddings using a frozen CLIP model, feeds its embeddings to lightweight networks, and fine-tunes only the final classifier. Experiments on the public CIFAKE benchmark show the performance reaches 95% accuracy without language reasoning. Few-shot adaptation to curated custom with 20% of the data results in performance to 85%. A closed-source baseline (Gemini-2.0) has the best zero-shot accuracy yet fails on specific styles. Notably, some specific image types, such as wide-angle photographs and oil paintings, pose significant challenges to classification. These results indicate previously unexplored difficulties in classifying certain types of AI-generated images, revealing new and more specific questions in this domain that are worth further investigation.

Aligning large language models (LLMs) with human values is essential for their safe deployment and widespread adoption. Current LLM safety benchmarks often focus solely on the refusal of individual problematic queries, which overlooks the importance of the context where the query occurs and may cause undesired refusal of queries under safe contexts that diminish user experience. Addressing this gap, we introduce CASE-Bench, a Context-Aware SafEty Benchmark that integrates context into safety assessments of LLMs. CASE-Bench assigns distinct, formally described contexts to categorized queries based on Contextual Integrity theory. Additionally, in contrast to previous studies which mainly rely on majority voting from just a few annotators, we recruited a sufficient number of annotators necessary to ensure the detection of statistically significant differences among the experimental conditions based on power analysis. Our extensive analysis using CASE-Bench on various open-source and commercial LLMs reveals a substantial and significant influence of context on human judgments (p<0.0001 from a z-test), underscoring the necessity of context in safety evaluations. We also identify notable mismatches between human judgments and LLM responses, particularly in commercial models within safe contexts.

Safety benchmarks for large language models often assess the risk of a user query, although the outcome of question answering depends on whether the response violates a policy. This distinction is critical in Chinese harmful-content evaluation, where linguistic variation and adversarial transformations can obscure risky intent. We introduce C-SafeQA, a policy-grounded benchmark for response-level Chinese safety evaluation. It comprises 538 base queries and 8,877 adversarial queries answered by four full-model LLM deployments, yielding 37,660 query-response records labeled safe, unsafe, or disputed. Reference labels are generated through agreement-aware multi-model adjudication and blind audits of stratified subsets by three safety experts. C-SafeQA supports both evaluation of target-model safety and auditing of seven automated safety judges against shared reference labels. Unsafe-response rates range from 0.93% to 3.35% on base queries and from 11.68% to 30.05% on adversarial queries. On the adversarial subset, judges show substantial trade-offs between unsafe-response recall and risk-query-conditioned safe-response false positive rate, and no judge dominates all metrics. Both acrostic transformations reduce unsafe recall for all seven judges, revealing mechanism-specific evaluator weaknesses. Dataset records, metadata, verification code, and judge scripts are publicly released to support recomputation, while benchmark construction, target-response generation, and private adjudication remain outside the release boundary.

Translating natural-language descriptions of physical phenomena into executable simulation code requires both programming expertise and physical reasoning. Current large language models (LLMs) lack this combination: they frequently produce code that runs but simulates the wrong physics. We introduce PhysCodeBench, the first benchmark for this task, with 1,200 expert-validated examples spanning four physical domains. Its evaluation suite, PhysCodeEval, goes beyond executability and visual fidelity to measure physical correctness directly from the engine state via conservation-law residuals and expert-written assertions, and supports cross-engine evaluation to disentangle physics reasoning from API fluency. As a reference method, we propose the Self-Corrective Multi-Agent Refinement Framework (SMRF), which decouples physics-aware error correction from code generation through specialized agents. This design is motivated by our finding that targeted correction, rather than generic iterative refinement, is the key driver of physical accuracy. SMRF nearly triples the physical-assertion pass rate of the best proprietary baseline (70.6% vs.\ 23.8%) and retains its advantage under cross-engine transfer.

Browser-based webcam gaze trackers are increasingly used for crowd-scale data collection and in clinical settings where lab eye trackers are impractical, but the reported latency numbers may not represent real world functionality. The common practice of timestamping each gaze sample when it is emitted, rather than when its source frame was captured, makes the measured inference latency read about $0\,$ms no matter how slow the engine really is. We show how to measure it honestly, recovering a per-frame capture clock from the browser's \texttt{re-quest-Video-Frame-Call-back} (rVFC) API (\texttt{captureTime} where the browser exposes it for local camera streams, else \texttt{presentationTime}, in which case every recovered latency is a verifiable lower bound): exact source-frame pairing through a per-frame queue for engines that expose their inference pipeline, and a further lower bound for engines that do not, such as WebGazer. We release an open TypeScript implementation and benchmark harness, demonstrated on two interchangeable engines: WebGazer and a new FaceMesh+KRR pipeline.