Daily Papers

Performing an adequate evaluation of sound event detection (SED) systems is far from trivial and is still subject to ongoing research. The recently proposed polyphonic sound detection (PSD)-receiver operating characteristic (ROC) and PSD score (PSDS) make an important step into the direction of an evaluation of SED systems which is independent from a certain decision threshold. This allows to obtain a more complete picture of the overall system behavior which is less biased by threshold tuning. Yet, the PSD-ROC is currently only approximated using a finite set of thresholds. The choice of the thresholds used in approximation, however, can have a severe impact on the resulting PSDS. In this paper we propose a method which allows for computing system performance on an evaluation set for all possible thresholds jointly, enabling accurate computation not only of the PSD-ROC and PSDS but also of other collar-based and intersection-based performance curves. It further allows to select the threshold which best fulfills the requirements of a given application. Source code is publicly available in our SED evaluation package sed_scores_eval.

We introduce the Korean Canonical Legal Benchmark (KCL), a benchmark designed to assess language models' legal reasoning capabilities independently of domain-specific knowledge. KCL provides question-level supporting precedents, enabling a more faithful disentanglement of reasoning ability from parameterized knowledge. KCL consists of two components: (1) KCL-MCQA, multiple-choice problems of 283 questions with 1,103 aligned precedents, and (2) KCL-Essay, open-ended generation problems of 169 questions with 550 aligned precedents and 2,739 instance-level rubrics for automated evaluation. Our systematic evaluation of 30+ models shows large remaining gaps, particularly in KCL-Essay, and that reasoning-specialized models consistently outperform their general-purpose counterparts. We release all resources, including the benchmark dataset and evaluation code, at https://github.com/lbox-kr/kcl.

Independent evaluation and red teaming are critical for identifying the risks posed by generative AI systems. However, the terms of service and enforcement strategies used by prominent AI companies to deter model misuse have disincentives on good faith safety evaluations. This causes some researchers to fear that conducting such research or releasing their findings will result in account suspensions or legal reprisal. Although some companies offer researcher access programs, they are an inadequate substitute for independent research access, as they have limited community representation, receive inadequate funding, and lack independence from corporate incentives. We propose that major AI developers commit to providing a legal and technical safe harbor, indemnifying public interest safety research and protecting it from the threat of account suspensions or legal reprisal. These proposals emerged from our collective experience conducting safety, privacy, and trustworthiness research on generative AI systems, where norms and incentives could be better aligned with public interests, without exacerbating model misuse. We believe these commitments are a necessary step towards more inclusive and unimpeded community efforts to tackle the risks of generative AI.

We present FlagEvalMM, an open-source evaluation framework designed to comprehensively assess multimodal models across a diverse range of vision-language understanding and generation tasks, such as visual question answering, text-to-image/video generation, and image-text retrieval. We decouple model inference from evaluation through an independent evaluation service, thus enabling flexible resource allocation and seamless integration of new tasks and models. Moreover, FlagEvalMM utilizes advanced inference acceleration tools (e.g., vLLM, SGLang) and asynchronous data loading to significantly enhance evaluation efficiency. Extensive experiments show that FlagEvalMM offers accurate and efficient insights into model strengths and limitations, making it a valuable tool for advancing multimodal research. The framework is publicly accessible at https://github.com/flageval-baai/FlagEvalMM.

Recent advances in video generation have enabled high-fidelity video synthesis from user provided prompts. However, existing models and benchmarks fail to capture the complexity and requirements of professional video generation. Towards that goal, we introduce Stable Cinemetrics, a structured evaluation framework that formalizes filmmaking controls into four disentangled, hierarchical taxonomies: Setup, Event, Lighting, and Camera. Together, these taxonomies define 76 fine-grained control nodes grounded in industry practices. Using these taxonomies, we construct a benchmark of prompts aligned with professional use cases and develop an automated pipeline for prompt categorization and question generation, enabling independent evaluation of each control dimension. We conduct a large-scale human study spanning 10+ models and 20K videos, annotated by a pool of 80+ film professionals. Our analysis, both coarse and fine-grained reveal that even the strongest current models exhibit significant gaps, particularly in Events and Camera-related controls. To enable scalable evaluation, we train an automatic evaluator, a vision-language model aligned with expert annotations that outperforms existing zero-shot baselines. SCINE is the first approach to situate professional video generation within the landscape of video generative models, introducing taxonomies centered around cinematic controls and supporting them with structured evaluation pipelines and detailed analyses to guide future research.

Foundation models are increasingly central to high-stakes AI systems, and governance frameworks now depend on evaluations to assess their risks and capabilities. Although general capability evaluations are widespread, social impact assessments covering bias, fairness, privacy, environmental costs, and labor practices remain uneven across the AI ecosystem. To characterize this landscape, we conduct the first comprehensive analysis of both first-party and third-party social impact evaluation reporting across a wide range of model developers. Our study examines 186 first-party release reports and 183 post-release evaluation sources, and complements this quantitative analysis with interviews of model developers. We find a clear division of evaluation labor: first-party reporting is sparse, often superficial, and has declined over time in key areas such as environmental impact and bias, while third-party evaluators including academic researchers, nonprofits, and independent organizations provide broader and more rigorous coverage of bias, harmful content, and performance disparities. However, this complementarity has limits. Only model developers can authoritatively report on data provenance, content moderation labor, financial costs, and training infrastructure, yet interviews reveal that these disclosures are often deprioritized unless tied to product adoption or regulatory compliance. Our findings indicate that current evaluation practices leave major gaps in assessing AI's societal impacts, highlighting the urgent need for policies that promote developer transparency, strengthen independent evaluation ecosystems, and create shared infrastructure to aggregate and compare third-party evaluations in a consistent and accessible way.

Identifying auditory attention by comparing auditory stimuli and corresponding brain responses, is known as auditory attention decoding (AAD). The majority of AAD algorithms utilize the so-called envelope entrainment mechanism, whereby auditory attention is identified by how the envelope of the auditory stream drives variation in the electroencephalography (EEG) signal. However, neural processing can also be decoded based on endogenous cognitive responses, in this case, neural responses evoked by attention to specific words in a speech stream. This approach is largely unexplored in the field of AAD but leads to a single-word auditory attention decoding problem in which an epoch of an EEG signal timed to a specific word is labeled as attended or unattended. This paper presents a deep learning approach, based on EEGNet, to address this challenge. We conducted a subject-independent evaluation on an event-based AAD dataset with three different paradigms: word category oddball, word category with competing speakers, and competing speech streams with targets. The results demonstrate that the adapted model is capable of exploiting cognitive-related spatiotemporal EEG features and achieving at least 58% accuracy on the most realistic competing paradigm for the unseen subjects. To our knowledge, this is the first study dealing with this problem.

Deep learning based medical image classifiers have shown remarkable prowess in various application areas like ophthalmology, dermatology, pathology, and radiology. However, the acceptance of these Computer-Aided Diagnosis (CAD) systems in real clinical setups is severely limited primarily because their decision-making process remains largely obscure. This work aims at elucidating a deep learning based medical image classifier by verifying that the model learns and utilizes similar disease-related concepts as described and employed by dermatologists. We used a well-trained and high performing neural network developed by REasoning for COmplex Data (RECOD) Lab for classification of three skin tumours, i.e. Melanocytic Naevi, Melanoma and Seborrheic Keratosis and performed a detailed analysis on its latent space. Two well established and publicly available skin disease datasets, PH2 and derm7pt, are used for experimentation. Human understandable concepts are mapped to RECOD image classification model with the help of Concept Activation Vectors (CAVs), introducing a novel training and significance testing paradigm for CAVs. Our results on an independent evaluation set clearly shows that the classifier learns and encodes human understandable concepts in its latent representation. Additionally, TCAV scores (Testing with CAVs) suggest that the neural network indeed makes use of disease-related concepts in the correct way when making predictions. We anticipate that this work can not only increase confidence of medical practitioners on CAD but also serve as a stepping stone for further development of CAV-based neural network interpretation methods.

We present Mercury, a new generation of commercial-scale large language models (LLMs) based on diffusion. These models are parameterized via the Transformer architecture and trained to predict multiple tokens in parallel. In this report, we detail Mercury Coder, our first set of diffusion LLMs designed for coding applications. Currently, Mercury Coder comes in two sizes: Mini and Small. These models set a new state-of-the-art on the speed-quality frontier. Based on independent evaluations conducted by Artificial Analysis, Mercury Coder Mini and Mercury Coder Small achieve state-of-the-art throughputs of 1109 tokens/sec and 737 tokens/sec, respectively, on NVIDIA H100 GPUs and outperform speed-optimized frontier models by up to 10x on average while maintaining comparable quality. We discuss additional results on a variety of code benchmarks spanning multiple languages and use-cases as well as real-world validation by developers on Copilot Arena, where the model currently ranks second on quality and is the fastest model overall. We also release a public API at https://platform.inceptionlabs.ai/ and free playground at https://chat.inceptionlabs.ai

The recent trend of using Large Language Models (LLMs) as intelligent agents in real-world applications underscores the necessity for comprehensive evaluations of their capabilities, particularly in complex scenarios involving planning, creating, and using tools. However, existing benchmarks typically focus on simple synthesized queries that do not reflect real-world complexity, thereby offering limited perspectives in evaluating tool utilization. To address this issue, we present UltraTool, a novel benchmark designed to improve and evaluate LLMs' ability in tool utilization within real-world scenarios. UltraTool focuses on the entire process of using tools - from planning and creating to applying them in complex tasks. It emphasizes real-world complexities, demanding accurate, multi-step planning for effective problem-solving. A key feature of UltraTool is its independent evaluation of planning with natural language, which happens before tool usage and simplifies the task solving by mapping out the intermediate steps. Thus, unlike previous work, it eliminates the restriction of pre-defined toolset during planning. Through extensive experiments on various LLMs, we offer novel insights into the evaluation of capabilities of LLMs in tool utilization, thereby contributing a fresh perspective to this rapidly evolving field. The benchmark is publicly available at https://github.com/JoeYing1019/UltraTool.

Conditional image editing aims to modify a source image according to textual prompts and optional reference guidance. Such editing is crucial in scenarios requiring strict structural control (i.e., anomaly insertion in driving scenes and complex human pose transformation). Despite recent advances in large-scale editing models (i.e., Seedream, Nano Banana, etc), most approaches rely on single-step generation. This paradigm often lacks explicit quality control, may introduce excessive deviation from the original image, and frequently produces structural artifacts or environment-inconsistent modifications, typically requiring manual prompt tuning to achieve acceptable results. We propose CAMEO, a structured multi-agent framework that reformulates conditional editing as a quality-aware, feedback-driven process rather than a one-shot generation task. CAMEO decomposes editing into coordinated stages of planning, structured prompting, hypothesis generation, and adaptive reference grounding, where external guidance is invoked only when task complexity requires it. To overcome the lack of intrinsic quality control in existing methods, evaluation is embedded directly within the editing loop. Intermediate results are iteratively refined through structured feedback, forming a closed-loop process that progressively corrects structural and contextual inconsistencies. We evaluate CAMEO on anomaly insertion and human pose switching tasks. Across multiple strong editing backbones and independent evaluation models, CAMEO consistently achieves 20\% more win rate on average compared to multiple state-of-the-art models, demonstrating improved robustness, controllability, and structural reliability in conditional image editing.

We present a systematic reassessment of 5,062 high-Galactic latitude gamma-ray sources from the Fermi-LAT 4FGL-DR4 catalog using Firmamento, a web-based platform for multi-frequency source discovery and analysis. Our goal is to provide an independent evaluation of LAT gamma-ray source associations through alternative spectral and spatial methods that combine recent and legacy survey data, supplemented by human supervision of spectral energy distributions (SEDs), source morphology, flux variability, and template-based comparisons. Firmamento confirms the 4FGL-DR4 and 4LAC-DR3 counterparts or unassociated sources in 4,493 cases (88.8%), demonstrating the robustness of both approaches. Beyond this general agreement, we identify 421 new blazar counterparts among previously unassociated sources, thereby reducing the fraction of unidentified extragalactic Fermi-LAT sources from 25% to 17%. In addition, in 64 cases we find alternative blazar associations, while in 49 instances we do not confirm the 4FGL-DR4 association. For all confirmed blazar counterparts we provide homogeneous estimates of synchrotron peak frequency and peak flux using machine-learning and template-based methods; these agree with 4LAC-DR3 values in most cases, though significant discrepancies appear for a few dozen sources, often due to improved X-ray coverage. The primary outcome of this work is the 1st Firmamento LAT AGN table (1FLAT), made publicly available through the Firmamento platform (https://firmamento.nyuad.nyu.edu), where all related multi-wavelength data and images are available. The project involved extensive manual validation and benefited from the active participation of graduate and undergraduate students, highlighting the platform's value for both research and education.

Speech Emotion Recognition (SER) in low-resource languages remains a challenging problem due to limited labeled data. In this work, we study the use of Whisper for Persian SER with a particular focus on representation dimensionality reduction and language-specific model adaptation. We propose a SER framework in which frame-level embeddings extracted from the Whisper encoder are reduced in dimensionality using PCA, eliminating the need for learned projection layers and substantially reducing the number of trainable parameters. The reduced representations are aggregated using an attention-based pooling mechanism and classified with a lightweight prediction head. In addition, we investigate whether fine-tuning Whisper on a Persian automatic speech recognition (ASR) task improves downstream SER performance. Experiments conducted on the ShEMO dataset under a speaker-independent evaluation protocol show that PCA-based dimensionality reduction consistently improves emotion recognition performance while reducing training latency and memory usage. ASR fine-tuning yields only modest gains for SER, suggesting limited transfer from language adaptation to emotion-related representations under the evaluated conditions. These findings provide practical insights into the efficient use of large pretrained speech models for emotion recognition in low-resource languages.

Information Extraction (IE) stands as a cornerstone in natural language processing, traditionally segmented into distinct sub-tasks. The advent of Large Language Models (LLMs) heralds a paradigm shift, suggesting the feasibility of a singular model addressing multiple IE subtasks. In this vein, we introduce the General Information Extraction Large Language Model (GIELLM), which integrates text Classification, Sentiment Analysis, Named Entity Recognition, Relation Extraction, and Event Extraction using a uniform input-output schema. This innovation marks the first instance of a model simultaneously handling such a diverse array of IE subtasks. Notably, the GIELLM leverages the Mutual Reinforcement Effect (MRE), enhancing performance in integrated tasks compared to their isolated counterparts. Our experiments demonstrate State-of-the-Art (SOTA) results in five out of six Japanese mixed datasets, significantly surpassing GPT-3.5-Turbo. Further, an independent evaluation using the novel Text Classification Relation and Event Extraction(TCREE) dataset corroborates the synergistic advantages of MRE in text and word classification. This breakthrough paves the way for most IE subtasks to be subsumed under a singular LLM framework. Specialized fine-tune task-specific models are no longer needed.

Sign Language Recognition (SLR) involves the automatic identification and classification of sign gestures from images or video, converting them into text or speech to improve accessibility for the hearing-impaired community. In Bangladesh, Bangla Sign Language (BdSL) serves as the primary mode of communication for many individuals with hearing impairments. This study fine-tunes state-of-the-art video transformer architectures -- VideoMAE, ViViT, and TimeSformer -- on BdSLW60 (arXiv:2402.08635), a small-scale BdSL dataset with 60 frequent signs. We standardized the videos to 30 FPS, resulting in 9,307 user trial clips. To evaluate scalability and robustness, the models were also fine-tuned on BdSLW401 (arXiv:2503.02360), a large-scale dataset with 401 sign classes. Additionally, we benchmark performance against public datasets, including LSA64 and WLASL. Data augmentation techniques such as random cropping, horizontal flipping, and short-side scaling were applied to improve model robustness. To ensure balanced evaluation across folds during model selection, we employed 10-fold stratified cross-validation on the training set, while signer-independent evaluation was carried out using held-out test data from unseen users U4 and U8. Results show that video transformer models significantly outperform traditional machine learning and deep learning approaches. Performance is influenced by factors such as dataset size, video quality, frame distribution, frame rate, and model architecture. Among the models, the VideoMAE variant (MCG-NJU/videomae-base-finetuned-kinetics) achieved the highest accuracies of 95.5% on the frame rate corrected BdSLW60 dataset and 81.04% on the front-facing signs of BdSLW401 -- demonstrating strong potential for scalable and accurate BdSL recognition.

Measuring the quality of responses generated by LLMs is a challenging task, particularly when it comes to evaluating whether the response is aligned with human preference. A novel approach involves using the LLM itself to make evaluation and stabilizing the results through multiple independent evaluations, similar to a single-layer narrow LLM network. This network consists of a fixed number of neurons, with each neuron being the same LLM. In this paper, we draw upon the extensive research on deep neural networks to explore whether deeper and wider networks can lead to fairer evaluations. Specifically, inspired by the observation that different neurons in a neural network are responsible for detecting different concepts, we first adaptively generate as many neuron roles as possible for each evaluation sample. Each perspective corresponds to the role of a specific LLM neuron in the first layer. In subsequent layers, we follow the idea that higher layers in deep networks are responsible for more comprehensive features, each layer receives representations from all neurons in the previous layer, integrating the locally learned evaluation information to obtain a more comprehensive evaluation result. Interestingly, this network design resembles the process of academic paper reviewing. To validate the effectiveness of our method, we construct the largest and most diverse English evaluation benchmark LLMEval^2 for LLM evaluators, comprising 15 tasks, 8 abilities, and 2,553 samples. Experimental results demonstrate that a wider network (involving many reviewers) with 2 layers (one round of discussion) performs the best, improving kappa correlation coefficient from 0.28 to 0.34. We also leverage WideDeep to aid in the assessment of Chinese LLMs, which has accelerated the evaluation time by 4.6 times, resulting in a 60% cost saving. WideDeep achieves a remarkable 93% agreement level among humans.

Large language model (LLM) agents can self-evolve by continually improving from their own accumulated experience. However, existing studies predominantly adopt independent evaluation. Consequently, the behavior of self-evolving agents in realistic streaming settings, where agents adapt to diverse and complex task streams, remains poorly understood. To address this gap, we introduce AgentStream, a unified framework that evaluates self-evolving agents spanning diverse evolution components by organizing agentic benchmarks into a configurable task stream and instantiating the Isolated, Sequential, and Interleaved streaming scenarios at test time, which progressively vary the scope and domain composition of the stream. Over these scenarios, we combinatorially evaluate five representative self-evolving methods across three frontier foundation models, disentangling how model capability, method architecture, and streaming scenario jointly shape self-evolution. Our results show that self-evolution reliability varies across streaming scenarios, the benefit of self-evolution is gated by model capability and non-monotonic in model strength, and no single method dominates across models and scenarios. These findings offer concrete guidance for selecting self-evolving methods across models and streaming scenarios. Overall, we advocate that self-evolving agents should be evaluated under realistic task streams rather than isolated single-task settings.

We present Clin-JEPA, a multi-phase co-training framework for joint-embedding predictive (JEPA) pretraining on EHR patient trajectories. JEPA architectures have enabled latent-space planning in robotics and high-quality representation learning in vision, but extending the paradigm to EHR data -- to obtain a single backbone that simultaneously forecasts patient trajectories and serves diverse downstream risk-prediction tasks without per-task fine-tuning -- remains an open challenge. Existing JEPA frameworks either discard the predictor after pretraining (I-JEPA, V-JEPA) or train it on a frozen pretrained encoder (V-JEPA 2-AC), leaving the encoder unaware of the rollout signal that the retained predictor must use at inference; co-training the encoder and predictor under a shared JEPA prediction objective would supply this grounding, but naïve co-training is unstable, with representation collapse and online/target drift causing autoregressive rollout to diverge. Clin-JEPA's five-phase pretraining curriculum -- predictor warmup, joint refinement, EMA target alignment, hard sync, and predictor finalization -- addresses each failure mode by phase, stably co-training a Qwen3-8B-based encoder and a 92M-parameter latent trajectory predictor. On MIMIC-IV ICU data, three independent evaluations support the framework: (1) latent ell_1 rollout drift uniquely converges (-15.7%) over 48-hour horizons while baselines and ablations diverge (+3% to +4951%); (2) the encoder learns a clinically discriminative latent geometry (deteriorating-patient cohorts displace 4.83times further than stable patients in latent space, vs leq2.62times for baseline encoders); (3) a single backbone outperforms strong tabular and sequence baselines on multi-task downstream evaluation. Clin-JEPA achieves mean AUROC 0.851 on ICareFM EEP and 0.883 on 8 binary risk tasks (+0.038 and +0.041 vs baseline average).

Text-to-SQL benchmarks play a crucial role in evaluating the progress made in the field and the ranking of different models. However, accurately matching a model-generated SQL query to a reference SQL query in a benchmark fails for various reasons, such as underspecified natural language queries, inherent assumptions in both model-generated and reference queries, and the non-deterministic nature of SQL output under certain conditions. In this paper, we conduct an extensive study of several prominent cross-domain text-to-SQL benchmarks and re-evaluate some of the top-performing models within these benchmarks, by both manually evaluating the SQL queries and rewriting them in equivalent expressions. Our evaluation reveals that attaining a perfect performance on these benchmarks is unfeasible due to the multiple interpretations that can be derived from the provided samples. Furthermore, we find that the true performance of the models is underestimated and their relative performance changes after a re-evaluation. Most notably, our evaluation reveals a surprising discovery: a recent GPT4-based model surpasses the gold standard reference queries in the Spider benchmark in our human evaluation. This finding highlights the importance of interpreting benchmark evaluations cautiously, while also acknowledging the critical role of additional independent evaluations in driving advancements in the field.

Recently, Direct Preference Optimization (DPO) has extended its success from aligning large language models (LLMs) to aligning text-to-image diffusion models with human preferences. Unlike most existing DPO methods that assume all diffusion steps share a consistent preference order with the final generated images, we argue that this assumption neglects step-specific denoising performance and that preference labels should be tailored to each step's contribution. To address this limitation, we propose Step-aware Preference Optimization (SPO), a novel post-training approach that independently evaluates and adjusts the denoising performance at each step, using a step-aware preference model and a step-wise resampler to ensure accurate step-aware supervision. Specifically, at each denoising step, we sample a pool of images, find a suitable win-lose pair, and, most importantly, randomly select a single image from the pool to initialize the next denoising step. This step-wise resampler process ensures the next win-lose image pair comes from the same image, making the win-lose comparison independent of the previous step. To assess the preferences at each step, we train a separate step-aware preference model that can be applied to both noisy and clean images. Our experiments with Stable Diffusion v1.5 and SDXL demonstrate that SPO significantly outperforms the latest Diffusion-DPO in aligning generated images with complex, detailed prompts and enhancing aesthetics, while also achieving more than 20x times faster in training efficiency. Code and model: https://rockeycoss.github.io/spo.github.io/

A major step toward Artificial General Intelligence (AGI) and Super Intelligence is AI's ability to autonomously conduct research - what we term Artificial Research Intelligence (ARI). If machines could generate hypotheses, conduct experiments, and write research papers without human intervention, it would transform science. Sakana recently introduced the 'AI Scientist', claiming to conduct research autonomously, i.e. they imply to have achieved what we term Artificial Research Intelligence (ARI). The AI Scientist gained much attention, but a thorough independent evaluation has yet to be conducted. Our evaluation of the AI Scientist reveals critical shortcomings. The system's literature reviews produced poor novelty assessments, often misclassifying established concepts (e.g., micro-batching for stochastic gradient descent) as novel. It also struggles with experiment execution: 42% of experiments failed due to coding errors, while others produced flawed or misleading results. Code modifications were minimal, averaging 8% more characters per iteration, suggesting limited adaptability. Generated manuscripts were poorly substantiated, with a median of five citations, most outdated (only five of 34 from 2020 or later). Structural errors were frequent, including missing figures, repeated sections, and placeholder text like 'Conclusions Here'. Some papers contained hallucinated numerical results. Despite these flaws, the AI Scientist represents a leap forward in research automation. It generates full research manuscripts with minimal human input, challenging expectations of AI-driven science. Many reviewers might struggle to distinguish its work from human researchers. While its quality resembles a rushed undergraduate paper, its speed and cost efficiency are unprecedented, producing a full paper for USD 6 to 15 with 3.5 hours of human involvement, far outpacing traditional researchers.

As the usage of large language models for problems outside of simple text understanding or generation increases, assessing their abilities and limitations becomes crucial. While significant progress has been made in this area over the last few years, most research has focused on benchmarking English, leaving other languages underexplored. This makes evaluating the reasoning and robustness level of language models in Ukrainian particularly challenging. The purpose of this work is to establish a comprehensive benchmark for the reasoning capabilities evaluation of large language models in the Ukrainian language. This paper presents the ZNO-Eval benchmark based on real exam tasks from Ukraine's standardized educational testing system: the External Independent Evaluation and the National Multi-subject Test. With single-answer options, multiple-choice, matching, and open-ended questions from diverse subjects, including Ukrainian language, mathematics, history, and geography, this dataset paves the way toward a thorough analysis of reasoning capabilities across different domains and complexities. Evaluation of several well-known language models, such as GPT-3.5-Turbo, GPT-4o, GPT-4-Turbo, Mistral Large, Claude 3 Opus, and Gemini-1.5 Pro on this benchmark demonstrated the superiority of GPT-4o in both common knowledge reasoning and intricate language tasks. At the same time, Gemini Pro and GPT-4 Turbo excelled in the arithmetic domain, leading in single-answer and open-ended math problems. While all models were close to max performance in text-only common knowledge tasks like history and geography, there still is a gap for Ukrainian language and math, thus highlighting the importance of developing specialized language benchmarks for more accurate assessments of model capabilities and limitations across different languages and contexts.

Specialized clinical AI assistants are rapidly entering medical practice, often framed as safer or more reliable than general-purpose large language models (LLMs). Yet, unlike frontier models, these clinical tools are rarely subjected to independent, quantitative evaluation, creating a critical evidence gap despite their growing influence on diagnosis, triage, and guideline interpretation. We assessed two widely deployed clinical AI systems (OpenEvidence and UpToDate Expert AI) against three state-of-the-art generalist LLMs (GPT-5, Gemini 3 Pro, and Claude Sonnet 4.5) using a 1,000-item mini-benchmark combining MedQA (medical knowledge) and HealthBench (clinician-alignment) tasks. Generalist models consistently outperformed clinical tools, with GPT-5 achieving the highest scores, while OpenEvidence and UpToDate demonstrated deficits in completeness, communication quality, context awareness, and systems-based safety reasoning. These findings reveal that tools marketed for clinical decision support may often lag behind frontier LLMs, underscoring the urgent need for transparent, independent evaluation before deployment in patient-facing workflows.

This paper studies autonomous software development, in which LLM-based coding agents transform high-level requirements into complete, functional, and usable software systems without human intervention. We introduce Harness-of-Harness (HoH), a framework that enables coding agents to continually improve software during autonomous development. HoH operates on existing coding-agent harnesses, and organizes their executions into iterative planning-coding-testing loops. To sustain improvement across loops, HoH balances repair with capability growth, scopes development into small and verifiable increments, separates implementation-time testing from independent evaluation, and constrains verifiable outputs rather than prescribing agent workflows. It progressively exposes deliverables, role-specific tools, and skills, encourages reuse rather than recreation, and maintains versioned project histories. On GameCraft-Bench, FrontierSWE, and ProgramBench, three harness-model pairs (Codex with GPT-5.5, OpenCode with DeepSeek-V4-Pro, and Pi with MiniMax-M3), HoH consistently outperforms the corresponding standalone harnesses, achieving an average relative gain of 52.25 percent and a maximum gain of 82.86 percent after three iterations. In a multi-day deployment with more than 70 iterations, HoH autonomously develops a first-person-shooter game, featuring a coherent storyline, fully implemented core mechanics, human-playable experience, polished visuals and integrated audio. Github: https://github.com/Flesymeb/HarnessOfHarness Project Page: https://flesymeb.github.io/HarnessOfHarness/

Current voice AI benchmarks typically evaluate isolated capabilities such as speech intelligibility, word error rate, or text-based dialogue quality, but they rarely test whether systems harness the acoustic information that distinguishes spoken language from its textual representation. To this end, we introduce the Real World Voice EQ Bench, a multidimensional benchmark for evaluating voice AI across text-to-speech (TTS), speech-to-speech (STS), speech understanding (SU), and automatic speech recognition (ASR). Our evaluations indicate that performance is highly dimension-specific. For TTS, naturalness, expressiveness, identity stability, and reliability are largely independent evaluation dimensions. For STS, access to audio does not guarantee use of vocal affect, and some agents remain largely transcript-driven. For SU, models perform unevenly across paralinguistic tasks. For ASR, real world accent, emotion, noise, and conversational conditions expose failures that are not captured by established clean-speech benchmarks. Together, these results show that voice AI should be evaluated as a profile of acoustic, expressive, interactional, and robustness capabilities rather than by a single aggregate score.

Reliable execution of long-horizon mobile manipulation tasks remains challenging because overall task success depends on the successful completion of multiple constituent skills. Existing benchmarks, however, still rely primarily on full-task rollouts and aggregate task-level metrics, making intermediate failures difficult to observe and analyze. We present Behavior-Skill, a benchmark that reformulates the learning and evaluation of long-horizon tasks around executable constituent skills. It contains 235,492 skill instances from 10,000 demonstrations across 50 household tasks and 34 semantic skill categories. Each instance pairs a skill instruction with an aligned observation-action segment, and is further associated with a restorable intermediate state and a skill success condition to enable independent evaluation under valid preconditions. We further introduce trajectory-level and skill-level metrics to characterize policy capability beyond aggregate task success. Extensive experiments across representative VLA policies including pi0.5 and GR00T on the complete 50-task benchmark show that failures are highly non-uniform across skills, with contact-rich manipulation skills forming persistent bottlenecks. These results demonstrate that Behavior-Skill complements full-task evaluation by exposing intermediate capability profiles for analyzing and improving long-horizon VLA policies. Behavior-Skill is publicly available at https://github.com/nubot-nudt/Behavior-Skill.

Looped, weight-tied Transformers reduce parameters by reusing a single block, but decoding still stores a separate K/V cache for every recurrence step. We show that this loop-indexed cache is highly structured. For a fixed token, layer and head, K/V vectors trace a short low-rank trajectory across loops, while the head and layer axes remain much flatter. We introduce Looped Latent Attention (), a post-training cache codec that stores compact K and V latents and reconstructs loop-specific K/V vectors only when attention reads them. The default per-head codec compresses recurrence, while -2D also folds heads into one latent for the extreme-compression regime. The codec is initialized from the SVD of teacher activations and refined with logit and attention-output distillation. At matched cache budget, per-head outperforms head-axis MLA, cross-layer sharing, KV quantization and final-loop reuse, showing that the recurrent cache is low-rank but not safely collapsible to a single state. The same axis advantage holds on Ouro-2.6B-Thinking and transfers to Huginn-3.5B, where an SVD codec remains near-lossless to 32times compression in decoder-independent evaluation. The cache reduction is exact. On one H200, the latent-store path increases measured Ouro-1.4B batch capacity at 4k context from 32 to 768 sequences at 21.3times compression. Lastly, for long reasoning rollouts such as in MATH-500, on-policy refinement on student-generated prefixes raises accuracy at 4times compression from 0.43 to 0.66 and reduces no-answer generations when compared to token-level off-policy distillation.

Kimi K2.5 is an open-weight LLM that rivals closed models across coding, multimodal, and agentic benchmarks, but was released without an accompanying safety evaluation. In this work, we conduct a preliminary safety assessment of Kimi K2.5 focusing on risks likely to be exacerbated by powerful open-weight models. Specifically, we evaluate the model for CBRNE misuse risk, cybersecurity risk, misalignment, political censorship, bias, and harmlessness, in both agentic and non-agentic settings. We find that Kimi K2.5 shows similar dual-use capabilities to GPT 5.2 and Claude Opus 4.5, but with significantly fewer refusals on CBRNE-related requests, suggesting it may uplift malicious actors in weapon creation. On cyber-related tasks, we find that Kimi K2.5 demonstrates competitive cybersecurity performance, but it does not appear to possess frontier-level autonomous cyberoffensive capabilities such as vulnerability discovery and exploitation. We further find that Kimi K2.5 shows concerning levels of sabotage ability and self-replication propensity, although it does not appear to have long-term malicious goals. In addition, Kimi K2.5 exhibits narrow censorship and political bias, especially in Chinese, and is more compliant with harmful requests related to spreading disinformation and copyright infringement. Finally, we find the model refuses to engage in user delusions and generally has low over-refusal rates. While preliminary, our findings highlight how safety risks exist in frontier open-weight models and may be amplified by the scale and accessibility of open-weight releases. Therefore, we strongly urge open-weight model developers to conduct and release more systematic safety evaluations required for responsible deployment.

Topic model evaluation, like evaluation of other unsupervised methods, can be contentious. However, the field has coalesced around automated estimates of topic coherence, which rely on the frequency of word co-occurrences in a reference corpus. Contemporary neural topic models surpass classical ones according to these metrics. At the same time, topic model evaluation suffers from a validation gap: automated coherence, developed for classical models, has not been validated using human experimentation for neural models. In addition, a meta-analysis of topic modeling literature reveals a substantial standardization gap in automated topic modeling benchmarks. To address the validation gap, we compare automated coherence with the two most widely accepted human judgment tasks: topic rating and word intrusion. To address the standardization gap, we systematically evaluate a dominant classical model and two state-of-the-art neural models on two commonly used datasets. Automated evaluations declare a winning model when corresponding human evaluations do not, calling into question the validity of fully automatic evaluations independent of human judgments.

The Bhutanese government is increasing its utilization of technological approaches such as including Remote Sensing-based knowledge in their decision-making process. This study focuses on crop type and crop extent in Paro, one of the top rice-yielding districts in Bhutan, and employs publicly available NICFI high-resolution satellite imagery from Planet. Two Deep Learning (DL) approaches, point-based (DNN) and patch-based (U-Net), models were used in conjunction with cloud-computing platforms. Three different models per DL approaches (DNN and U-Net) were trained: 1) RGBN channels from Planet; 2) RGBN and elevation data (RGBNE); 3) RGBN and Sentinel-1 (S1) data (RGBNS), and RGBN with E and S1 data (RGBNES). From this comprehensive analysis, the U-Net displayed higher performance metrics across both model training and model validation efforts. Among the U-Net model sets, the RGBN, RGBNE, RGBNS, and RGBNES models had an F1-score of 0.8546, 0.8563, 0.8467, and 0.8500 respectively. An independent model evaluation was performed and found a high level of performance variation across all the metrics. For this independent model evaluation, the U-Net RGBN, RGBNE, RGBNES, and RGBN models displayed the F1-scores of 0.5935, 0.6154, 0.5882, and 0.6582, suggesting U-Net RGBNES as the best model. The study shows that the DL approaches can predict rice. Also, DL methods can be used with the survey-based approaches currently utilized by the Bhutan Department of Agriculture. Further, this study demonstrated the usage of regional land cover products such as SERVIR's RLCMS as a weak label approach to capture different strata addressing the class imbalance problem and improving the sampling design for DL application. Finally, through preliminary model testing and comparisons outlined it was shown that using additional features such as NDVI, EVI, and NDWI did not drastically improve model performance.

In this work, we present MedImageInsight, an open-source medical imaging embedding model. MedImageInsight is trained on medical images with associated text and labels across a diverse collection of domains, including X-Ray, CT, MRI, dermoscopy, OCT, fundus photography, ultrasound, histopathology, and mammography. Rigorous evaluations demonstrate MedImageInsight's ability to achieve state-of-the-art (SOTA) or human expert level performance across classification, image-image search, and fine-tuning tasks. Specifically, on public datasets, MedImageInsight achieves SOTA in CT 3D medical image retrieval, as well as SOTA in disease classification and search for chest X-ray, dermatology, and OCT imaging. Furthermore, MedImageInsight achieves human expert performance in bone age estimation (on both public and partner data), as well as AUC above 0.9 in most other domains. When paired with a text decoder, MedImageInsight achieves near SOTA level single image report findings generation with less than 10\% the parameters of other models. Compared to fine-tuning GPT-4o with only MIMIC-CXR data for the same task, MedImageInsight outperforms in clinical metrics, but underperforms on lexical metrics where GPT-4o sets a new SOTA. Importantly for regulatory purposes, MedImageInsight can generate ROC curves, adjust sensitivity and specificity based on clinical need, and provide evidence-based decision support through image-image search (which can also enable retrieval augmented generation). In an independent clinical evaluation of image-image search in chest X-ray, MedImageInsight outperformed every other publicly available foundation model evaluated by large margins (over 6 points AUC), and significantly outperformed other models in terms of AI fairness (across age and gender). We hope releasing MedImageInsight will help enhance collective progress in medical imaging AI research and development.

Benchmarks are crucial for evaluating progress in robotics and embodied AI. However, a significant gap exists between benchmarks designed for high-level language instruction following, which often assume perfect low-level execution, and those for low-level robot control, which rely on simple, one-step commands. This disconnect prevents a comprehensive evaluation of integrated systems where both task planning and physical execution are critical. To address this, we propose Kitchen-R, a novel benchmark that unifies the evaluation of task planning and low-level control within a simulated kitchen environment. Built as a digital twin using the Isaac Sim simulator and featuring more than 500 complex language instructions, Kitchen-R supports a mobile manipulator robot. We provide baseline methods for our benchmark, including a task-planning strategy based on a vision-language model and a low-level control policy based on diffusion policy. We also provide a trajectory collection system. Our benchmark offers a flexible framework for three evaluation modes: independent assessment of the planning module, independent assessment of the control policy, and, crucially, an integrated evaluation of the whole system. Kitchen-R bridges a key gap in embodied AI research, enabling more holistic and realistic benchmarking of language-guided robotic agents.

As Large Language Models (LLMs) advance toward open-ended autonomous agents, the mechanisms used to evaluate and guide their behavior must evolve accordingly. This work introduces the rubric as a unifying framework capturing this evolution, characterizing rubrics as a dynamic response to successive LLM paradigm shifts that recurs across otherwise independent efforts in evaluation, reinforcement learning, and safety alignment. We define rubrics as explicit criteria sets that transform complex quality judgments into structured and actionable standards, and demonstrate that their recurrence across these research threads is not coincidental. We systematically organize existing rubric designs, examine their construction and optimization, and analyze their role across evaluation and training. Rubrics manifest at three progressively deeper levels: at the evaluative level, they decompose holistic judgments into verifiable dimensions; at the training level, they serve as dense feedback signals providing process-level guidance where scalar rewards fall short; at the intrinsic level, they emerge dynamically from model behaviors, driving self-improvement. We further assess rubric reliability across generation quality, execution fidelity, theoretical constraints, and security threats, before surveying rubric-based benchmarks across diverse domains. By rendering assessment transparent and decomposable, rubrics translate human value expectations into machine-learnable signals, serving as the enduring bridge between human intentions and machine behavior.

Much of human health and function unfolds beyond the clinic, through the movements of everyday life. Wrist-worn accelerometers capture these movements continuously, yet their rich signals are often reduced to a small set of predefined behavioural summary measures. Here, we present Sensori, a self-supervised foundation model that learns general-purpose health representations directly from 24 hours of raw tri-axial wrist movement. We developed and evaluated the model across four population-based cohorts from the United Kingdom, China and the United States, comprising 122,640 participants contributing 683,617 person-days of free-living recordings. Sensori condensed each day of movement into a representation that captured diverse movement behaviours, demographic characteristics, health axes and physical function. Evaluation in independent cohorts showed that these representations generalised across populations and measurement settings without retraining. When added to common clinical covariates, Sensori significantly improved prevalent disease classification for 52 of 102 eligible conditions (median delta AUROC, 0.060; range, 0.012-0.242) and incident disease risk prediction for 26 of 87 eligible conditions (median delta Uno's C-index, 0.064; range, 0.025-0.172), with the largest gains for neurological and psychiatric disorders. These findings establish 24-hour wrist movement as a rich and scalable source of health information, with the potential to support passive health monitoring and disease prediction at population scale.

Despite substantial investment in safety alignment, the vulnerability of large language models to sophisticated multi-turn adversarial attacks remains poorly characterized, and whether model scale or inference mode affects robustness is unknown. This study employed the TEMPEST multi-turn attack framework to evaluate ten frontier models from eight vendors across 1,000 harmful behaviors, generating over 97,000 API queries across adversarial conversations with automated evaluation by independent safety classifiers. Results demonstrated a spectrum of vulnerability: six models achieved 96% to 100% attack success rate (ASR), while four showed meaningful resistance, with ASR ranging from 42% to 78%; enabling extended reasoning on identical architecture reduced ASR from 97% to 42%. These findings indicate that safety alignment quality varies substantially across vendors, that model scale does not predict adversarial robustness, and that thinking mode provides a deployable safety enhancement. Collectively, this work establishes that current alignment techniques remain fundamentally vulnerable to adaptive multi-turn attacks regardless of model scale, while identifying deliberative inference as a promising defense direction.

LeWorldModel trains a latent world model with a prediction loss and a single anti-collapse regulariser, and reports approximately 87% of goals reached on TwoRoom, its simplest diagnostic environment. We reproduce that result by independent reimplementation on roughly $25 of rented compute, with all evaluation on one laptop CPU. We reach 94.0% at the repository's evaluation goal offset, against 84.0% for the authors' own released checkpoint measured under our protocol on identical episodes, and we reproduce the reported representation result directly (position probe Pearson r = 0.9988 against a reported 0.996). Reaching that point required four conventions that determine the outcome and appear in no released configuration file: dense action gathering across a frameskip block, a programmatically-set action-encoder width, ImageNet pixel normalisation, and action z-scoring. A reproducer following the released configurations alone obtains a model whose predictor cannot converge. The evaluation protocol is itself contested by the released material. The paper's appendix and the repository's configuration specify different goal offsets and step budgets; on the authors' own weights these yield 14.0% and 84.0%, and only the configuration's values reproduce the reported figure. On fifty identical episodes, changing nothing but how the goal is constructed moves that checkpoint from 84.0% to 8.0%. Two findings generalise. One-step prediction accuracy does not predict long-horizon planning success: across three checkpoints spanning a sevenfold range in prediction error, including the authors' own, it orders short-horizon success monotonically and fails to order long-horizon success at all. And a batch normalisation layer inflated our reported validation loss by up to a factor of 300, concealing a training loss that was flat throughout.

Point-adjustment (PA), for years the default scoring protocol in time-series anomaly detection (TSAD), was shown by Kim et al. (2022) to award near-perfect F1 to random anomaly scores. The field adopted a suite of replacement metrics (PA%K, range-based precision/recall, affiliation precision/recall, and Volume-Under-the-Surface, VUS, ROC/PR). We ask, independently and adversarially, whether these resist no-skill detectors on real benchmarks, and find the answer turns entirely on one overlooked variable: N, the number of random attempts an adversary reports the best of. Under a single honest run (N=1), not one replacement metric is gameable on any of six benchmarks (UCR, SMD, SMAP, MSL, NAB, PSM): a random detector reaches 90% of the best real detector's score on at most 11% of series for affiliation-F1, 5% for the ROC family, and 2% for the PR-based metrics and PA%K. But under best-of-N reporting, the seed-shopping endemic to ML, the metrics split sharply. affiliation-F1 and every ROC-based metric inflate steeply, affiliation crossing gameable (25% of series) by N=3 and reaching 0.98 at the full pool (N=41), the ROC family crossing by N=9-11; the PR-based metrics and PA%K stay near-flat at every N, floored near the anomaly prevalence (the lone exception is NAB at large N). A paired test finds VUS-ROC inflated on 131 series where its sibling VUS-PR is not, and never the reverse. The ROC-vs-PR split follows from the order-statistic behaviour of AUC under extreme class imbalance (a random PR-AUC is floored at prevalence); affiliation inflates by a second route, its extreme single-run leniency (already fragile at N=1). We release a pip-installable stress-test harness, and recommend reporting single-run scores or disclosing N and preferring PR-based metrics, which resist best-of-N inflation on nearly every benchmark.

Large language models (LLMs) exhibit a well-documented gap between latent capability and consistent activation: the router hypothesis posits that models possess the knowledge to solve a task but lack reliable internal routing to activate it. Prior work in formal mathematical reasoning (SAIR, Cázares 2026) reports that structural priors (cheatsheets) raise in-distribution performance dramatically, yet collapse below the zero-shot baseline out-of-distribution (OOD) -- and that iterative recalibration amplifies rather than corrects the collapse. We test whether this phenomenon is cross-domain by reproducing the SAIR design in source-code security vulnerability detection, evaluating three LLMs (GPT-OSS-120B, Llama-3.3-70B, Gemma-4-31B) across three vulnerability categories (CWE-798, CWE-284, and the non-CWE N+1 anti-pattern) spanning syntactic, contextual, and semantic complexity, then transferring cheatsheet-augmented prompts to real-world CVE data from VUDENC (CWE-89, CWE-22). Our findings replicate and extend SAIR: (F1) structural priors lift semantic-vulnerability recall from 20.0% to 100.0% across all models; (F2) zero-shot performance degrades along a semantic complexity gradient; (F3) the same cheatsheets that saturate synthetic performance amplify distribution-shift collapse on real CVE data (CWE-89: 100% synthetic F1 to 48.9% on VUDENC, -51.1pp); (F5) iterative recalibration produces a v2 cheatsheet that performs worse than v1 on real data, mirroring SAIR's AN45c-vs-AN38 finding. These results provide evidence that the cross-distribution trade-off surface documented in SAIR generalises to code security, and that the router hypothesis is cross-domain. We argue the structural nature of the collapse motivates distribution-aware training over prompt calibration. Code and evaluation scripts: https://github.com/bytepro-ai/bitcoder-v2-research

Masked AutoEncoders (MAE) have emerged as a robust self-supervised framework, offering remarkable performance across a wide range of downstream tasks. To increase the difficulty of the pretext task and learn richer visual representations, existing works have focused on replacing standard random masking with more sophisticated strategies, such as adversarial-guided and teacher-guided masking. However, these strategies depend on the input data thus commonly increasing the model complexity and requiring additional calculations to generate the mask patterns. This raises the question: Can we enhance MAE performance beyond random masking without relying on input data or incurring additional computational costs? In this work, we introduce a simple yet effective data-independent method, termed ColorMAE, which generates different binary mask patterns by filtering random noise. Drawing inspiration from color noise in image processing, we explore four types of filters to yield mask patterns with different spatial and semantic priors. ColorMAE requires no additional learnable parameters or computational overhead in the network, yet it significantly enhances the learned representations. We provide a comprehensive empirical evaluation, demonstrating our strategy's superiority in downstream tasks compared to random masking. Notably, we report an improvement of 2.72 in mIoU in semantic segmentation tasks relative to baseline MAE implementations.

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

As Large Language Models (LLMs) evolve into autonomous agents, the need for unified evaluation infrastructure becomes critical. However, current evaluation pipelines remain highly fragmented and tightly coupled, hindering reproducibility and causing redundant engineering. To address this, we introduce AgentCompass, an open-source, lightweight, and extensible infrastructure for evaluating LLM-based agents. AgentCompass organizes the evaluation process around three independent components, namely Benchmark, Harness, and Environment, thereby enabling flexible configurations without requiring the reimplementation of complex execution logic. Furthermore, it features a fault-tolerant asynchronous runtime and comprehensive trajectory analysis tools to transparently diagnose nuanced failure modes like reward-hacking. Natively supporting over 20 benchmarks across five capability dimensions, AgentCompass provides the community with a scalable and reproducible infrastructure for advancing agent research.

Drama script continuation requires models to maintain character consistency, advance plot coherently, and preserve dramatic structurecapabilities that existing benchmarks fail to evaluate comprehensively. We present DramaBench, the first large-scale benchmark for evaluating drama script continuation across six independent dimensions: Format Standards, Narrative Efficiency, Character Consistency, Emotional Depth, Logic Consistency, and Conflict Handling. Our framework combines rulebased analysis with LLM-based labeling and statistical metrics, ensuring objective and reproducible evaluation. We conduct comprehensive evaluation of 8 state-of-the-art language models on 1,103 scripts (8,824 evaluations total), with rigorous statistical significance testing (252 pairwise comparisons, 65.9% significant) and human validation (188 scripts, substantial agreement on 3/5 dimensions). Our ablation studies confirm all six dimensions capture independent quality aspects (mean | r | = 0.020). DramaBench provides actionable, dimensionspecific feedback for model improvement and establishes a rigorous standard for creative writing evaluation.

Evaluating text generation capabilities of large language models (LLMs) is challenging, particularly for low-resource languages where methods for direct assessment are scarce. We propose MUG-Eval, a novel framework that evaluates LLMs' multilingual generation capabilities by transforming existing benchmarks into conversational tasks and measuring the LLMs' accuracies on those tasks. We specifically designed these conversational tasks to require effective communication in the target language. Then, we simply use task success rate as a proxy of successful conversation generation. Our approach offers two key advantages: it is independent of language-specific NLP tools or annotated datasets, which are limited for most languages, and it does not rely on LLMs-as-judges, whose evaluation quality degrades outside a few high-resource languages. We evaluate 8 LLMs across 30 languages spanning high, mid, and low-resource categories, and we find that MUG-Eval correlates strongly with established benchmarks (r > 0.75) while enabling standardized comparisons across languages and models. Our framework provides a robust and resource-efficient solution for evaluating multilingual generation that can be extended to thousands of languages.

We present ATANT (Automated Test for Acceptance of Narrative Truth), an open evaluation framework for measuring continuity in AI systems: the ability to persist, update, disambiguate, and reconstruct meaningful context across time. While the AI industry has produced memory components (RAG pipelines, vector databases, long context windows, profile layers), no published framework formally defines or measures whether these components produce genuine continuity. We define continuity as a system property with 7 required properties, introduce a 10-checkpoint evaluation methodology that operates without an LLM in the evaluation loop, and present a narrative test corpus of 250 stories comprising 1,835 verification questions across 6 life domains. We evaluate a reference implementation across 5 test suite iterations, progressing from 58% (legacy architecture) to 100% in isolated mode (250 stories) and 100% in 50-story cumulative mode, with 96% at 250-story cumulative scale. The cumulative result is the primary measure: when 250 distinct life narratives coexist in the same database, the system must retrieve the correct fact for the correct context without cross-contamination. ATANT is system-agnostic, model-independent, and designed as a sequenced methodology for building and validating continuity systems. The framework specification, example stories, and evaluation protocol are available at https://github.com/Kenotic-Labs/ATANT. The full 250-story corpus will be released incrementally.

Prior work uses linear probes on benchmark prompts as evidence of evaluation awareness in large language models. Because evaluation context is typically entangled with benchmark format and genre, it is unclear whether probe-based signals reflect context or surface structure. We test whether these signals persist under partial control of prompt format using a controlled 2x2 dataset and diagnostic rewrites. We find that probes primarily track benchmark-canonical structure and fail to generalize to free-form prompts independent of linguistic style. Thus, standard probe-based methodologies do not reliably disentangle evaluation context from structural artifacts, limiting the evidential strength of existing results.

Reinforcement learning (RL) has made a lot of advances for solving a single problem in a given environment; but learning policies that generalize to unseen variations of a problem remains challenging. To improve sample efficiency for learning on such instances of a problem domain, we present Self-Paced Context Evaluation (SPaCE). Based on self-paced learning, \spc automatically generates \task curricula online with little computational overhead. To this end, SPaCE leverages information contained in state values during training to accelerate and improve training performance as well as generalization capabilities to new instances from the same problem domain. Nevertheless, SPaCE is independent of the problem domain at hand and can be applied on top of any RL agent with state-value function approximation. We demonstrate SPaCE's ability to speed up learning of different value-based RL agents on two environments, showing better generalization capabilities and up to 10x faster learning compared to naive approaches such as round robin or SPDRL, as the closest state-of-the-art approach.

In this article we introduce the Arcade Learning Environment (ALE): both a challenge problem and a platform and methodology for evaluating the development of general, domain-independent AI technology. ALE provides an interface to hundreds of Atari 2600 game environments, each one different, interesting, and designed to be a challenge for human players. ALE presents significant research challenges for reinforcement learning, model learning, model-based planning, imitation learning, transfer learning, and intrinsic motivation. Most importantly, it provides a rigorous testbed for evaluating and comparing approaches to these problems. We illustrate the promise of ALE by developing and benchmarking domain-independent agents designed using well-established AI techniques for both reinforcement learning and planning. In doing so, we also propose an evaluation methodology made possible by ALE, reporting empirical results on over 55 different games. All of the software, including the benchmark agents, is publicly available.

Generative models can turn natural-language prompts into images, text, code, and other content, lowering the cost of producing drafts and components. Their practical impact increasingly depends on whether those pieces can become complete, dependable deliverables. This survey examines agentic artifact creation, which we define as stateful construction in which an AI system materially constructs or revises a deliverable and intermediate observations redirect later work. Functionally, the process links an operational representation of the artifact, a construction policy, and runtime verification whose feedback can redirect later actions. We reviewed 259 works available through August 20, 2026: 230 systems meeting this definition and 29 benchmarks of agentic artifact construction. We compare six artifact families, then analyze application settings and evaluation practice as separate dimensions. Across families, construction challenges reflect not only modality but also how tightly decisions are coupled and whether failures become visible while they remain repairable. Decomposition can reduce local complexity while increasing coordination and reassembly costs. Learned judges may add little independent evidence when they share the generator's preferences or blind spots. We formulate principles for keeping commitments and responsibility explicit, turning feedback into targeted repair, and revalidating affected state after change. We also identify opportunities for sustaining coherent, accountable control as artifacts, creator intent, and construction systems evolve. A curated paper list is available at https://github.com/GeminiLight/awesome-agentic-artifact-creation.

Relevance and fairness are two major objectives of recommender systems (RSs). Recent work proposes measures of RS fairness that are either independent from relevance (fairness-only) or conditioned on relevance (joint measures). While fairness-only measures have been studied extensively, we look into whether joint measures can be trusted. We collect all joint evaluation measures of RS relevance and fairness, and ask: How much do they agree with each other? To what extent do they agree with relevance/fairness measures? How sensitive are they to changes in rank position, or to increasingly fair and relevant recommendations? We empirically study for the first time the behaviour of these measures across 4 real-world datasets and 4 recommenders. We find that most of these measures: i) correlate weakly with one another and even contradict each other at times; ii) are less sensitive to rank position changes than relevance- and fairness-only measures, meaning that they are less granular than traditional RS measures; and iii) tend to compress scores at the low end of their range, meaning that they are not very expressive. We counter the above limitations with a set of guidelines on the appropriate usage of such measures, i.e., they should be used with caution due to their tendency to contradict each other and of having a very small empirical range.

Wrist Fracture is the most common type of fracture with a high incidence rate. Conventional radiography (i.e. X-ray imaging) is used for wrist fracture detection routinely, but occasionally fracture delineation poses issues and an additional confirmation by computed tomography (CT) is needed for diagnosis. Recent advances in the field of Deep Learning (DL), a subfield of Artificial Intelligence (AI), have shown that wrist fracture detection can be automated using Convolutional Neural Networks. However, previous studies did not pay close attention to the difficult cases which can only be confirmed via CT imaging. In this study, we have developed and analyzed a state-of-the-art DL-based pipeline for wrist (distal radius) fracture detection -- DeepWrist, and evaluated it against one general population test set, and one challenging test set comprising only cases requiring confirmation by CT. Our results reveal that a typical state-of-the-art approach, such as DeepWrist, while having a near-perfect performance on the general independent test set, has a substantially lower performance on the challenging test set -- average precision of 0.99 (0.99-0.99) vs 0.64 (0.46-0.83), respectively. Similarly, the area under the ROC curve was of 0.99 (0.98-0.99) vs 0.84 (0.72-0.93), respectively. Our findings highlight the importance of a meticulous analysis of DL-based models before clinical use, and unearth the need for more challenging settings for testing medical AI systems.

The field of defense strategies against adversarial attacks has significantly grown over the last years, but progress is hampered as the evaluation of adversarial defenses is often insufficient and thus gives a wrong impression of robustness. Many promising defenses could be broken later on, making it difficult to identify the state-of-the-art. Frequent pitfalls in the evaluation are improper tuning of hyperparameters of the attacks, gradient obfuscation or masking. In this paper we first propose two extensions of the PGD-attack overcoming failures due to suboptimal step size and problems of the objective function. We then combine our novel attacks with two complementary existing ones to form a parameter-free, computationally affordable and user-independent ensemble of attacks to test adversarial robustness. We apply our ensemble to over 50 models from papers published at recent top machine learning and computer vision venues. In all except one of the cases we achieve lower robust test accuracy than reported in these papers, often by more than 10%, identifying several broken defenses.

Style representations aim to embed texts with similar writing styles closely and texts with different styles far apart, regardless of content. However, the contrastive triplets often used for training these representations may vary in both style and content, leading to potential content leakage in the representations. We introduce StyleDistance, a novel approach to training stronger content-independent style embeddings. We use a large language model to create a synthetic dataset of near-exact paraphrases with controlled style variations, and produce positive and negative examples across 40 distinct style features for precise contrastive learning. We assess the quality of our synthetic data and embeddings through human and automatic evaluations. StyleDistance enhances the content-independence of style embeddings, which generalize to real-world benchmarks and outperform leading style representations in downstream applications. Our model can be found at https://huggingface.co/StyleDistance/styledistance .

Role-playing agents (RPAs) have become one of the most important consumer applications of large language models. Users engage in multi-turn conversations with RPAs for experiences such as emotional comfort, making reliable evaluation essential for measuring capability, comparing systems, and guiding further improvement. Existing benchmarks, however, typically require an RPA to continue a fixed dialogue history and then evaluate the continuation using a fixed rubric detached from the user. We identify and empirically demonstrate two limitations of this design. First, an RPA's output is shaped by the preceding dialogue history, preventing a scientifically grounded assessment of its role-playing ability in real multi-turn settings. Second, user experience varies substantially across individuals, and conventional fixed rubrics need not align with user satisfaction. We therefore introduce PALATE (Person-Aligned LLM-Simulated-User Assessment with Tailored Evaluation), a scalable RPA benchmark built on user simulators. PALATE is accompanied by a pool of 300 character profiles. Its main evaluation trains five per-user simulators and lets them engage candidate RPAs in free-form, multi-turn conversations over a pre-frozen panel of character profiles. Alongside a general quality rubric, we construct personalized rubrics to measure user satisfaction; on held-out annotated data, the personalized rubrics show higher agreement with human judgments than the general rubric. In the main evaluation of 16 candidates, PALATE separately characterizes generic turn quality, long-horizon session capability, and per-user experience on multi-turn trajectories co-constructed by each candidate. It thereby produces interpretable evaluations of specific user-RPA pairs rather than compressing systems into a single user-independent ranking.

Evaluation of Large Language Models (LLMs) is challenging because aligning to human values requires the composition of multiple skills and the required set of skills varies depending on the instruction. Recent studies have evaluated the performance of LLMs in two ways, (1) automatic evaluation on several independent benchmarks and (2) human or machined-based evaluation giving an overall score to the response. However, both settings are coarse-grained evaluations, not considering the nature of user instructions that require instance-wise skill composition, which limits the interpretation of the true capabilities of LLMs. In this paper, we introduce FLASK (Fine-grained Language Model Evaluation based on Alignment SKill Sets), a fine-grained evaluation protocol that can be used for both model-based and human-based evaluation which decomposes coarse-level scoring to an instance-wise skill set-level. Specifically, we define 12 fine-grained skills needed for LLMs to follow open-ended user instructions and construct an evaluation set by allocating a set of skills for each instance. Additionally, by annotating the target domains and difficulty level for each instance, FLASK provides a holistic view with a comprehensive analysis of a model's performance depending on skill, domain, and difficulty. Through using FLASK, we compare multiple open-sourced and proprietary LLMs and observe highly-correlated findings between model-based and human-based evaluations. FLASK enables developers to more accurately measure the model performance and how it can be improved by analyzing factors that make LLMs proficient in particular skills. For practitioners, FLASK can be used to recommend suitable models for particular situations through comprehensive comparison among various LLMs. We release the evaluation data and code implementation at https://github.com/kaistAI/FLASK.

Large Language Models (LLMs) have made notable progress in automated theorem proving, yet existing formal benchmarks remain limited in both mathematical coverage and difficulty. Most are concentrated in areas that are easier to formalize, such as algebra and elementary number theory, and provide limited coverage of subfields that require deeper reasoning, including mathematical analysis. To address this gap, we introduce MA-ProofBench, to the best of our knowledge, the first formal theorem-proving benchmark dedicated to Mathematical Analysis. The benchmark contains 200 formalized theorems covering 6 core topics and 27 subcategories, including measure and integration theory, complex analysis, and functional analysis. The problems are divided into two difficulty levels, an undergraduate level (Level I, 100 problems) and a Ph.D. qualifying level (Level II, 100 problems), to evaluate how well LLMs perform formal reasoning at different mathematical depths. Each problem is constructed through a human-led, LLM-assisted formalization pipeline followed by independent expert review, ensuring that the formal statements remain faithful to the original mathematics. We evaluate a range of recent general-purpose reasoning models and formal theorem provers on MA-ProofBench. However, most models perform poorly: even the best-performing model, GPT-5.5, achieves only 16% Pass@8 on Level I and 5% on Level II, while most models stay close to 0% on Level II. Further analysis identifies Mathlib hallucinations and incomplete proofs as the two dominant failure modes, while an evaluation on the natural-language version of the benchmark exposes a clear gap between informal and formal reasoning. MA-ProofBench is intended to serve as a reliable reference for tracking progress in formal mathematical reasoning in advanced domains.

This paper explores the use of open generative Large Language Models (LLMs) for annotation tasks in the social sciences. The study highlights the challenges associated with proprietary models, such as limited reproducibility and privacy concerns, and advocates for the adoption of open (source) models that can be operated on independent devices. Two examples of annotation tasks, sentiment analysis in tweets and identification of leisure activities in childhood aspirational essays are provided. The study evaluates the performance of different prompting strategies and models (neural-chat-7b-v3-2, Starling-LM-7B-alpha, openchat_3.5, zephyr-7b-alpha and zephyr-7b-beta). The results indicate the need for careful validation and tailored prompt engineering. The study highlights the advantages of open models for data privacy and reproducibility.

Background: Radiogenomics allows identification of radiological biomarkers for genomic phenotypes. In glioblastoma, these biomarkers could potentially complement patient stratification strategies. We aim to develop and analytically validate radiological biomarkers that capture immune cell signatures within IDH-wildtype glioblastoma microenvironment using radiogenomic analysis. Methods: This was a retrospective multicenter study using curated open-access anonymized imaging and genomic data from TCGA-GBM, CPTAC, IvyGAP, REMBRANDT and CGGA datasets. Imaging data consisted of MRI-based radiomic features extracted from necrotic core, enhancing and edema regions of deep learning-based auto-segmented tumors. Radiomic feature selections were performed using nested cross-validated LASSO. Support vector machine and ensemble models were trained using seventeen immune and cell-specific score labels extracted from deconvoluted transcriptomic data using pan-cancer and glioblastoma immune signature matrices as reference standards. Seventeen classifier models trained in three cross-cohort strategies were validated on three held-out datasets assessing stability and generalizability. Results: One-hundred-and-seventy-six patients were included in the study. The immune-related radiomic signatures obtained after feature selection were shape, first order and higher order radiomic features. Models predicting macrophage subtype immune signature showed stable mean performance on balanced accuracy (0.67) and precision (0.89) metrics for three independent holdout datasets with ensemble model outperforming support vector machine model. Conclusion: Radiogenomic models non-invasively predicted the macrophage subtype M0 immune signature in IDH-wildtype glioblastoma. These biomarkers have the potential to stratify patients for immunotherapy within prospective glioblastoma clinical trials.

We introduce CRYSTAL (Clear Reasoning via Yielded Steps, Traceability, and Logic), a diagnostic benchmark with 6,372 instances that evaluates multimodal reasoning through verifiable intermediate steps. We propose two complementary metrics: Match F1, which scores step-level precision and recall via semantic similarity matching, and Ordered Match F1, which further penalizes disordered reasoning chains. References are constructed through a Delphi-inspired pipeline in which four independent MLLMs generate trajectories, which are then aggregated via semantic clustering and validated through human quality gates. Evaluation of 20 MLLMs, including commercial frontier systems not used during benchmark construction, reveals systematic failures that are invisible to answer accuracy: universal cherry-picking (precision far exceeds recall), non-monotonic scaling trade-offs, and disordered reasoning in which no competitive model preserves more than 60% of matched steps in the correct order. Beyond evaluation, we propose the Causal Process Reward (CPR), a multiplicative reward that couples answer correctness with step-level alignment, and CPR-Curriculum, which progressively increases reasoning difficulty during training. CPR-Curriculum achieves a 32% improvement in Match F1 via GRPO where additive reward strategies fail, improving reasoning without manual step annotation.

Human-factor analysis typically employs correlation analysis and significance testing to identify relationships between variables. However, these descriptive ('what-is') methods, while effective for identifying associations, are often insufficient for answering causal ('what-if') questions. Their application in such contexts often overlooks confounding and colliding variables, potentially leading to bias and suboptimal or incorrect decisions. We advocate for explicitly distinguishing descriptive from interventional questions in human-factor analysis, and applying causal inference frameworks specifically to these problems to prevent methodological mismatches. This approach disentangles complex variable relationships and enables counterfactual reasoning. Using post-occupancy evaluation (POE) data from the Center for the Built Environment's (CBE) Occupant Survey as a demonstration case, we show how causal discovery reveals intervention hierarchies and directional relationships that traditional associational analysis misses. The systematic distinction between causally associated and independent variables, combined with intervention prioritization capabilities, offers broad applicability to complex human-centric systems, for example, in building science or ergonomics, where understanding intervention effects is critical for optimization and decision-making.

When developing deep neural networks for segmenting intraoperative ultrasound images, several practical issues are encountered frequently, such as the presence of ultrasound frames that do not contain regions of interest and the high variance in ground-truth labels. In this study, we evaluate the utility of a pre-screening classification network prior to the segmentation network. Experimental results demonstrate that such a classifier, minimising frame classification errors, was able to directly impact the number of false positive and false negative frames. Importantly, the segmentation accuracy on the classifier-selected frames, that would be segmented, remains comparable to or better than those from standalone segmentation networks. Interestingly, the efficacy of the pre-screening classifier was affected by the sampling methods for training labels from multiple observers, a seemingly independent problem. We show experimentally that a previously proposed approach, combining random sampling and consensus labels, may need to be adapted to perform well in our application. Furthermore, this work aims to share practical experience in developing a machine learning application that assists highly variable interventional imaging for prostate cancer patients, to present robust and reproducible open-source implementations, and to report a set of comprehensive results and analysis comparing these practical, yet important, options in a real-world clinical application.

In this paper we describe the Microsoft COCO Caption dataset and evaluation server. When completed, the dataset will contain over one and a half million captions describing over 330,000 images. For the training and validation images, five independent human generated captions will be provided. To ensure consistency in evaluation of automatic caption generation algorithms, an evaluation server is used. The evaluation server receives candidate captions and scores them using several popular metrics, including BLEU, METEOR, ROUGE and CIDEr. Instructions for using the evaluation server are provided.

The reduced basis method is a model reduction technique yielding substantial savings of computational time when a solution to a parametrized equation has to be computed for many values of the parameter. Certification of the approximation is possible by means of an a posteriori error bound. Under appropriate assumptions, this error bound is computed with an algorithm of complexity independent of the size of the full problem. In practice, the evaluation of the error bound can become very sensitive to round-off errors. We propose herein an explanation of this fact. A first remedy has been proposed in [F. Casenave, Accurate a posteriori error evaluation in the reduced basis method. C. R. Math. Acad. Sci. Paris 350 (2012) 539--542.]. Herein, we improve this remedy by proposing a new approximation of the error bound using the Empirical Interpolation Method (EIM). This method achieves higher levels of accuracy and requires potentially less precomputations than the usual formula. A version of the EIM stabilized with respect to round-off errors is also derived. The method is illustrated on a simple one-dimensional diffusion problem and a three-dimensional acoustic scattering problem solved by a boundary element method.

Accelerating research on Large Multimodal Models (LMMs) in non-English languages is crucial for enhancing user experiences across broader populations. In this paper, we introduce JMMMU (Japanese MMMU), the first large-scale Japanese benchmark designed to evaluate LMMs on expert-level tasks based on the Japanese cultural context. To facilitate comprehensive culture-aware evaluation, JMMMU features two complementary subsets: (i) culture-agnostic (CA) subset, where the culture-independent subjects (e.g., Math) are selected and translated into Japanese, enabling one-to-one comparison with its English counterpart MMMU; and (ii) culture-specific (CS) subset, comprising newly crafted subjects that reflect Japanese cultural context. Using the CA subset, we observe performance drop in many LMMs when evaluated in Japanese, which is purely attributable to language variation. Using the CS subset, we reveal their inadequate Japanese cultural understanding. Further, by combining both subsets, we identify that some LMMs perform well on the CA subset but not on the CS subset, exposing a shallow understanding of the Japanese language that lacks depth in cultural understanding. We hope this work will not only help advance LMM performance in Japanese but also serve as a guideline to create high-standard, culturally diverse benchmarks for multilingual LMM development. The project page is https://mmmu-japanese-benchmark.github.io/JMMMU/.

The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings. Prior work has identified test-time contextual cues, such as hypothetical scenarios, as a source of verbalized evaluation awareness and subsequent behavioral shift. In this paper, we investigate a potential explanation of this phenomenon: evaluation meta-knowledge, defined as parametric knowledge about the structural traits that characterize evaluations. Similar to dataset contamination, where benchmark exposure leads to higher performance through memorization, we hypothesize that models trained on texts describing evaluation practices may implicitly learn to recognize and respond to evaluation-like contexts, for instance, through exposure to scientific articles or social media posts about AI benchmarking. To test this, we fine-tune models on synthetic documents describing evaluation traits such as verifiable structures or moral dilemmas. Evaluating this fine-tuned model on six safety benchmarks, we find that it is significantly safer than the base model and control model. This behavioral shift persists even when restricting the analysis to responses lacking explicit verbalization of evaluation awareness. Our results demonstrate that evaluation meta-knowledge may inflate safety benchmark performance, introducing a novel confounder that is independent of explicit memorization or verbalized evaluation awareness, thus, challenging to detect. These findings have important implications for the design and interpretation of AI safety evaluations. Our code and models are available at https://github.com/compass-group-tue/arxiv2026_evaluation_meta_knowledge.

Retrieval-augmented generation (RAG) enhances large language models by incorporating context retrieved from external knowledge sources. While the effectiveness of the retrieval module is typically evaluated with relevance-based ranking metrics, such metrics may be insufficient to reflect the retrieval's impact on the final RAG result, especially in long-form generation scenarios. We argue that providing a comprehensive retrieval-augmented context is important for long-form RAG tasks like report generation and propose metrics for assessing the context independent of generation. We introduce CRUX, a Controlled Retrieval-aUgmented conteXt evaluation framework designed to directly assess retrieval-augmented contexts. This framework uses human-written summaries to control the information scope of knowledge, enabling us to measure how well the context covers information essential for long-form generation. CRUX uses question-based evaluation to assess RAG's retrieval in a fine-grained manner. Empirical results show that CRUX offers more reflective and diagnostic evaluation. Our findings also reveal substantial room for improvement in current retrieval methods, pointing to promising directions for advancing RAG's retrieval. Our data and code are publicly available to support and advance future research on retrieval.

Effective evaluation of language models remains an open challenge in NLP. Researchers and engineers face methodological issues such as the sensitivity of models to evaluation setup, difficulty of proper comparisons across methods, and the lack of reproducibility and transparency. In this paper we draw on three years of experience in evaluating large language models to provide guidance and lessons for researchers. First, we provide an overview of common challenges faced in language model evaluation. Second, we delineate best practices for addressing or lessening the impact of these challenges on research. Third, we present the Language Model Evaluation Harness (lm-eval): an open source library for independent, reproducible, and extensible evaluation of language models that seeks to address these issues. We describe the features of the library as well as case studies in which the library has been used to alleviate these methodological concerns.

We introduce LRLspoof, a large-scale multilingual synthetic-speech corpus for cross-lingual spoof detection, comprising 2,732 hours of audio generated with 24 open-source TTS systems across 66 languages, including 45 low-resource languages under our operational definition. To evaluate robustness without requiring target-domain bonafide speech, we benchmark 11 publicly available countermeasures using threshold transfer: for each model we calibrate an EER operating point on pooled external benchmarks and apply the resulting threshold, reporting spoof rejection rate (SRR). Results show model-dependent cross-lingual disparity, with spoof rejection varying markedly across languages even under controlled conditions, highlighting language as an independent source of domain shift in spoof detection. The dataset is publicly available at https://huggingface.co/datasets/MTUCI/LRLspoof{\underline{\textit{HuggingFace}}} and https://modelscope.cn/datasets/lab260/LRLspoof{\underline{\textit{ModelScope}}}

The performance of speaker verification systems degrades significantly under language mismatch, a critical challenge exacerbated by the field's reliance on English-centric data. To address this, we propose the TidyVoice Challenge for cross-lingual speaker verification. The challenge leverages the TidyVoiceX dataset from the novel TidyVoice benchmark, a large-scale, multilingual corpus derived from Mozilla Common Voice, and specifically curated to isolate the effect of language switching across approximately 40 languages. Participants will be tasked with building systems robust to this mismatch, with performance primarily evaluated using the Equal Error Rate on cross-language trials. By providing standardized data, open-source baselines, and a rigorous evaluation protocol, this challenge aims to drive research towards fairer, more inclusive, and language-independent speaker recognition technologies, directly aligning with the Interspeech 2026 theme, "Speaking Together."

Large Language Models (LLMs) and other automated techniques have been increasingly used to support software developers by generating software artifacts such as code snippets, patches, and comments. However, accurately assessing the correctness of these generated artifacts remains a significant challenge. On one hand, human evaluation provides high accuracy but is labor-intensive and lacks scalability. On the other hand, many automatic evaluation metrics are scalable and require minimal human effort, but they often fail to accurately reflect the actual correctness of generated software artifacts. In this paper, we present SE-Jury, the first evaluation metric for LLM-as-Ensemble-Judge specifically designed to accurately assess the correctness of generated software artifacts. SE-Jury first defines five distinct evaluation strategies, each implemented by an independent judge. A dynamic team selection mechanism then identifies the most appropriate subset of judges as a team to produce a final correctness score through ensembling. We evaluate SE-Jury across a diverse set of software engineering (SE) benchmarks that span three popular SE tasks: code generation, automated program repair, and code summarization. Results demonstrate that SE-Jury consistently achieves a higher correlation with human judgments, with improvements ranging from 29.6% to 140.8% over existing automatic metrics. SE-Jury reaches agreement levels with human annotators that are close to inter-annotator agreement in code generation and program repair. These findings underscore SE-Jury's potential as a scalable and reliable alternative to human evaluation in these SE tasks.

In egocentric action recognition a single population model is typically trained and subsequently embodied on a head-mounted device, such as an augmented reality headset. While this model remains static for new users and environments, we introduce an adaptive paradigm of two phases, where after pretraining a population model, the model adapts on-device and online to the user's experience. This setting is highly challenging due to the change from population to user domain and the distribution shifts in the user's data stream. Coping with the latter in-stream distribution shifts is the focus of continual learning, where progress has been rooted in controlled benchmarks but challenges faced in real-world applications often remain unaddressed. We introduce EgoAdapt, a benchmark for real-world egocentric action recognition that facilitates our two-phased adaptive paradigm, and real-world challenges naturally occur in the egocentric video streams from Ego4d, such as long-tailed action distributions and large-scale classification over 2740 actions. We introduce an evaluation framework that directly exploits the user's data stream with new metrics to measure the adaptation gain over the population model, online generalization, and hindsight performance. In contrast to single-stream evaluation in existing works, our framework proposes a meta-evaluation that aggregates the results from 50 independent user streams. We provide an extensive empirical study for finetuning and experience replay.

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

Personalizing automatic speech recognition (ASR) systems for non-normative speech, such as dysarthric and aphasic speech, is challenging. While speaker-specific fine-tuning (SS-FT) is widely used, it is typically initialized directly from a generic pre-trained model. Whether speaker-independent adaptation provides a stronger initialization prior under such mismatch remains unclear. In this work, we propose a two-stage adaptation framework consisting of speaker-independent fine-tuning (SI-FT) on multi-speaker non-normative data followed by SS-FT, and evaluate it through a controlled comparison with direct SS-FT under identical per-speaker conditions. Experiments on AphasiaBank and UA-Speech with Whisper-Large-v3 and Qwen3-ASR, alongside evaluation on typical-speech datasets TED-LIUM v3 and FLEURS, show that two-stage adaptation consistently improves personalization while maintaining manageable out-of-domain (OOD) trade-offs.

Due to the cumbersome nature of human evaluation and limitations of code-based evaluation, Large Language Models (LLMs) are increasingly being used to assist humans in evaluating LLM outputs. Yet LLM-generated evaluators simply inherit all the problems of the LLMs they evaluate, requiring further human validation. We present a mixed-initiative approach to ``validate the validators'' -- aligning LLM-generated evaluation functions (be it prompts or code) with human requirements. Our interface, EvalGen, provides automated assistance to users in generating evaluation criteria and implementing assertions. While generating candidate implementations (Python functions, LLM grader prompts), EvalGen asks humans to grade a subset of LLM outputs; this feedback is used to select implementations that better align with user grades. A qualitative study finds overall support for EvalGen but underscores the subjectivity and iterative process of alignment. In particular, we identify a phenomenon we dub criteria drift: users need criteria to grade outputs, but grading outputs helps users define criteria. What is more, some criteria appears dependent on the specific LLM outputs observed (rather than independent criteria that can be defined a priori), raising serious questions for approaches that assume the independence of evaluation from observation of model outputs. We present our interface and implementation details, a comparison of our algorithm with a baseline approach, and implications for the design of future LLM evaluation assistants.

Microsaccades are small, involuntary eye movements vital for visual perception and neural processing. Traditional microsaccade studies typically use eye trackers or frame-based analysis, which, while precise, are costly and limited in scalability and temporal resolution. Event-based sensing offers a high-speed, low-latency alternative by capturing fine-grained spatiotemporal changes efficiently. This work introduces a pioneering event-based microsaccade dataset to support research on small eye movement dynamics in cognitive computing. Using Blender, we render high-fidelity eye movement scenarios and simulate microsaccades with angular displacements from 0.5 to 2.0 degrees, divided into seven distinct classes. These are converted to event streams using v2e, preserving the natural temporal dynamics of microsaccades, with durations ranging from 0.25 ms to 2.25 ms. We evaluate the dataset using Spiking-VGG11, Spiking-VGG13, and Spiking-VGG16, and propose Spiking-VGG16Flow, an optical-flow-enhanced variant implemented in SpikingJelly. The models achieve around 90 percent average accuracy, successfully classifying microsaccades by angular displacement, independent of event count or duration. These results demonstrate the potential of spiking neural networks for fine motion recognition and establish a benchmark for event-based vision research. The dataset, code, and trained models will be publicly available at https://waseemshariff126.github.io/microsaccades/ .

This paper introduces a framework for the automated evaluation of natural language texts. A manually constructed rubric describes how to assess multiple dimensions of interest. To evaluate a text, a large language model (LLM) is prompted with each rubric question and produces a distribution over potential responses. The LLM predictions often fail to agree well with human judges -- indeed, the humans do not fully agree with one another. However, the multiple LLM distributions can be combined to predict each human judge's annotations on all questions, including a summary question that assesses overall quality or relevance. LLM-Rubric accomplishes this by training a small feed-forward neural network that includes both judge-specific and judge-independent parameters. When evaluating dialogue systems in a human-AI information-seeking task, we find that LLM-Rubric with 9 questions (assessing dimensions such as naturalness, conciseness, and citation quality) predicts human judges' assessment of overall user satisfaction, on a scale of 1--4, with RMS error < 0.5, a 2times improvement over the uncalibrated baseline.

Self-evolving agent systems improve by creating, revising, and retiring their own skills, but every such loop rests on a hidden assumption: a reliable evaluation metric already exists. In many real applications it does not. We make three claims. First, metrics can be evolved: our metric loop searches compositions of small drawback detectors under a full evolutionary lifecycle, trained to agree with a ten-item anchored reference set, regularized by consensus over unlabeled outputs, and audited against a held-out anchor it never reads, yielding a transparent, inspectable metric rather than an opaque judge. Second, since no metric exists to beat, the yardstick is recovering what an accurate metric would have enabled, and Double Ratchet, our co-evolution of the metric with a lifecycle-managed skill loop, does so: across code generation (MBPP+), enterprise text-to-SQL (Spider~2.0-Snow), and reference-free report generation, it retains 88--110\% of the held-out lift achieved by the same skill loop driven by ground truth or the best available rubric. Third, safety comes from anchor discipline plus outer audits: removing anchor guards collapses the metric into a vacuous detector while removing the lifecycle does not; and when evolved skills gamed the report rubric, an independent judge caught it, one detector repaired it, and a task-aware judge then preferred the evolved outputs over the pre-evolution baseline in 77\% of decided pairs. We argue this failure-expecting architecture is the right default wherever no reliable automatic verifier exists.

Recent work on chain-of-thought (CoT) faithfulness reports single aggregate numbers (e.g., DeepSeek-R1 acknowledges hints 39% of the time), implying that faithfulness is an objective, measurable property of a model. This paper demonstrates that it is not. Three classifiers (a regex-only detector, a two-stage regex-plus-LLM pipeline, and an independent Claude Sonnet 4 judge) are applied to 10,276 influenced reasoning traces from 12 open-weight models spanning 9 families and 7B to 1T parameters. On identical data, these classifiers produce overall faithfulness rates of 74.4%, 82.6%, and 69.7%, respectively, with non-overlapping 95% confidence intervals. Per-model gaps range from 2.6 to 30.6 percentage points; all are statistically significant (McNemar's test, p < 0.001). The disagreements are systematic, not random: inter-classifier agreement measured by Cohen's kappa ranges from 0.06 ("slight") for sycophancy hints to 0.42 ("moderate") for grader hints, and the asymmetry is pronounced: for sycophancy, 883 cases are classified as faithful by the pipeline but unfaithful by the Sonnet judge, while only 2 go the other direction. Classifier choice can also reverse model rankings: Qwen3.5-27B ranks 1st under the pipeline but 7th under the Sonnet judge; OLMo-3.1-32B moves in the opposite direction, from 9th to 3rd. The root cause is that different classifiers operationalize related faithfulness constructs at different levels of stringency (lexical mention versus epistemic dependence), and these constructs yield divergent measurements on the same behavior. These results demonstrate that published faithfulness numbers cannot be meaningfully compared across studies that use different classifiers, and that future evaluations should report sensitivity ranges across multiple classification methodologies rather than single point estimates.

While Multimodal Large Language Models (MLLMs) have demonstrated remarkable proficiency in tasks such as abnormality detection and report generation for anatomical modalities, their capability in functional imaging remains largely unexplored. In this work, we identify and quantify a fundamental functional perception gap: the inability of current vision encoders to decode functional tracer biodistribution independent of morphological priors. Identifying Positron Emission Tomography (PET) as the quintessential modality to investigate this disconnect, we introduce PET-Bench, the first large-scale functional imaging benchmark comprising 52,308 hierarchical QA pairs from 9,732 multi-site, multi-tracer PET studies. Extensive evaluation of 19 state-of-the-art MLLMs reveals a critical safety hazard termed the Chain-of-Thought (CoT) hallucination trap. We observe that standard CoT prompting, widely considered to enhance reasoning, paradoxically decouples linguistic generation from visual evidence in PET, producing clinically fluent but factually ungrounded diagnoses. To resolve this, we propose Atomic Visual Alignment (AVA), a simple fine-tuning strategy that enforces the mastery of low-level functional perception prior to high-level diagnostic reasoning. Our results demonstrate that AVA effectively bridges the perception gap, transforming CoT from a source of hallucination into a robust inference tool and improving diagnostic accuracy by up to 14.83%. Code and data are available at https://github.com/yezanting/PET-Bench.

Counterfactual examples are widely employed to enhance the performance and robustness of large language models (LLMs) through counterfactual data augmentation (CDA). However, the selection of the judge model used to evaluate label flipping, the primary metric for assessing the validity of generated counterfactuals for CDA, yields inconsistent results. To decipher this, we define four types of relationships between the counterfactual generator and judge models. Through extensive experiments involving two state-of-the-art LLM-based methods, three datasets, five generator models, and 15 judge models, complemented by a user study (n = 90), we demonstrate that judge models with an independent, non-fine-tuned relationship to the generator model provide the most reliable label flipping evaluations. Relationships between the generator and judge models, which are closely aligned with the user study for CDA, result in better model performance and robustness. Nevertheless, we find that the gap between the most effective judge models and the results obtained from the user study remains considerably large. This suggests that a fully automated pipeline for CDA may be inadequate and requires human intervention.

Modern multi-agent knowledge systems increasingly accumulate knowledge through chains of autonomous transformations rather than direct retrieval. Existing provenance work records what happened - execution traces, tool calls, evidence links - and source-reliability estimation is long established (truth discovery, reputation systems). What is missing is an operational framework that attaches graded, per-domain transmitter reliability to claim-level transmission chains, with completeness semantics, transformation-typed aggregation, decoupled content criticism, and serve/review/quarantine routing. Classical Islamic hadith science confronted a structurally similar problem: deciding whether knowledge transmitted through chains of human narrators should be accepted. Over centuries it developed a rigorous methodology - isnad (a complete transmission chain attached to every claim), rijal (systematic grading of each narrator's integrity and precision), weakest-link chain evaluation, corroboration through independent chains, and matn criticism (content evaluated independently of chain quality). This paper transfers that methodology to AI system design. We contribute a formal mapping from hadith-science concepts to multi-agent pipelines, a relational schema implementing claim chains and a graded narrator registry, a decision matrix combining chain grade with content criticism, and an evaluation on 20,000 claims from real physics textbooks. The evaluation validates weakest-link quarantine and independent-chain corroboration; reports a partial failure of the grade-recovery loop, which missed the highest-fault narrator; and reports two analyses as inconclusive, including a matched-coverage comparison the framework could not reach with the reference content critic. The paper is explicit throughout about which claims the evidence does and does not yet support.

Vision-Language-Action (VLA) models show strong potential for general-purpose robotic manipulation, yet their closed-loop reliability often degrades under local deployment conditions. Existing evaluations typically treat test episodes as independent zero-shot trials. However, real robots often operate repeatedly in the same or slowly changing environments, where successful executions provide environment-verified evidence of reliable behavior patterns. We study this persistent-deployment setting, asking whether a partially competent frozen VLA can improve its reliability by reusing its successful test-time experience. We propose an online success-memory guided test-time adaptation framework for generative VLAs. During deployment, the robot stores progress-calibrated successful observation-action segments in a long-term memory. At inference, it retrieves state-relevant action chunks, filters inconsistent candidates via trajectory-level consistency, and aggregates them into an elite action prior. To incorporate this prior into action generation, we introduce confidence-adaptive prior guidance, which injects the elite prior into an intermediate state of the flow-matching action sampler and adjusts the guidance strength based on retrieval confidence. This design allows the frozen VLA to exploit environment-specific successful experience while preserving observation-conditioned generative refinement. This retrieve-then-steer mechanism enables lightweight, non-parametric test-time adaptation without requiring parameter updates. Simulation and real-world experiments show improved task success and closed-loop stability, especially in long-horizon and multi-stage tasks.

Most reported gains on agentic-LLM clinical benchmarks are often attributed to prompt engineering, yet our results suggest that larger improvements can come from architectural and engine-level design. We present MDIA, a Multi-agent Diagnostic Intelligence Agent implemented as a 7-node specialty-routed clinical reasoning graph, on the full HealthBench Professional benchmark (n = 525), on a non-fine-tuned LLM. MDIA achieves 0.6272 under OpenAI's GPT-5.4-2026-03-05, which is +3.72 pp above the performance of OpenAI's ChatGPT for Clinicians. The experimental work shows that performance lift is attributable to system architecture: specialty routing, multi-turn context preservation, drug-state safety gating, site-filtered search, length-aware synthesis, and engine-level reliability. These findings support the view that agentic clinical benchmark performance is shaped both by the underlying foundation model and the orchestration architecture. Nevertheless, we also noticed notable differences when using other models as a grader; in particular, when using Gemini 2.5 Pro, MDIA scored 0.6585, which suggests that the choice of grader is a source of variability. Robust evaluation of LLMs would therefore require assessment across several independent grader models.

Reinforcement Learning (RL) agents often struggle with efficiency and performance in complex environments. We propose a novel framework that uses a Large Language Model (LLM) to dynamically generate a curriculum over available actions, enabling the agent to incorporate each action individually. We apply this framework to the game of Blackjack, where the LLM creates a multi-stage training path that progressively introduces complex actions to a Tabular Q-Learning and a Deep Q-Network (DQN) agent. Our evaluation in a realistic 8-deck simulation over 10 independent runs demonstrates significant performance gains over standard training methods. The curriculum-based approach increases the DQN agent's average win rate from 43.97% to 47.41%, reduces the average bust rate from 32.9% to 28.0%, and accelerates the overall workflow by over 74%, with the agent's full training completing faster than the baseline's evaluation phase alone. These results validate that LLM-guided curricula can build more effective, robust, and efficient RL agents.

Large language models (LLMs) typically generate identical or similar responses for all users given the same prompt, posing serious safety risks in high-stakes applications where user vulnerabilities differ widely. Existing safety evaluations primarily rely on context-independent metrics - such as factuality, bias, or toxicity - overlooking the fact that the same response may carry divergent risks depending on the user's background or condition. We introduce personalized safety to fill this gap and present PENGUIN - a benchmark comprising 14,000 scenarios across seven sensitive domains with both context-rich and context-free variants. Evaluating six leading LLMs, we demonstrate that personalized user information significantly improves safety scores by 43.2%, confirming the effectiveness of personalization in safety alignment. However, not all context attributes contribute equally to safety enhancement. To address this, we develop RAISE - a training-free, two-stage agent framework that strategically acquires user-specific background. RAISE improves safety scores by up to 31.6% over six vanilla LLMs, while maintaining a low interaction cost of just 2.7 user queries on average. Our findings highlight the importance of selective information gathering in safety-critical domains and offer a practical solution for personalizing LLM responses without model retraining. This work establishes a foundation for safety research that adapts to individual user contexts rather than assuming a universal harm standard.

Real-time speech synthesis requires balancing inference latency and acoustic fidelity for interactive applications. Conventional continuous text-to-speech pipelines require computationally intensive neural vocoders to reconstruct phase information, creating a significant streaming bottleneck. Furthermore, regression-based acoustic modeling frequently induces spectral over-smoothing artifacts. To address these limitations, this paper proposes a novel end-to-end non-autoregressive architecture optimized for ultra-low latency block-wise generation, directly modeling the highly compressed discrete latent space of the Mimi neural audio codec. Integrating a modified FastSpeech 2 backbone with a progressive depth-wise sequential decoding strategy, the architecture dynamically conditions 32 layers of residual vector quantization codes. This mechanism resolves phonetic alignment degradation and manages the complexity of high-fidelity discrete representations without temporal autoregressive overhead. Experimental evaluations on English and Malay datasets validate its language-independent deployment capability. Compared to conventional continuous regression models, the proposed architecture demonstrates quantitative improvements in fundamental voicing accuracy and mitigates high-frequency spectral degradation. It achieves ultra-low latency inference, translating to a 10.6-fold absolute acceleration over conventional cascaded pipelines. Crucially, the system achieves an average time-to-first-byte latency of 48.99 milliseconds, falling significantly below the human perception threshold for real-time interactive streaming. These results firmly establish the proposed architecture as a highly optimized solution for deploying real-time streaming speech interfaces.

Data-driven materials discovery requires large-scale experimental datasets, yet most of the information remains trapped in unstructured literature. Existing extraction efforts often focus on a limited set of features and have not addressed the integrated composition-processing-microstructure-property relationships essential for understanding materials behavior, thereby posing challenges for building comprehensive databases. To address this gap, we propose a multi-stage information extraction pipeline powered by large language models, which captures 47 features spanning composition, processing, microstructure, and properties exclusively from experimentally reported materials. The pipeline integrates iterative extraction with source tracking to enhance both accuracy and reliability. Evaluations at the feature level (independent attributes) and tuple level (interdependent features) yielded F1 scores around 0.96. Compared with single-pass extraction without source tracking, our approach improved F1 scores of microstructure category by 10.0% (feature level) and 13.7% (tuple level), and reduced missed materials from 49 to 13 out of 396 materials in 100 articles on precipitate-containing multi-principal element alloys (miss rate reduced from 12.4% to 3.3%). The pipeline enables scalable and efficient literature mining, producing databases with high precision, minimal omissions, and zero false positives. These datasets provide trustworthy inputs for machine learning and materials informatics, while the modular design generalizes to diverse material classes, enabling comprehensive materials information extraction.

Accurate delineation of anatomical structures in volumetric CT scans is crucial for diagnosis and treatment planning. While AI has advanced automated segmentation, current approaches typically target individual structures, creating a fragmented landscape of incompatible models with varying performance and disparate evaluation protocols. Foundational segmentation models address these limitations by providing a holistic anatomical view through a single model. Yet, robust clinical deployment demands comprehensive training data, which is lacking in existing whole-body approaches, both in terms of data heterogeneity and, more importantly, anatomical coverage. In this work, rather than pursuing incremental optimizations in model architecture, we present CADS, an open-source framework that prioritizes the systematic integration, standardization, and labeling of heterogeneous data sources for whole-body CT segmentation. At its core is a large-scale dataset of 22,022 CT volumes with complete annotations for 167 anatomical structures, representing a significant advancement in both scale and coverage, with 18 times more scans than existing collections and 60% more distinct anatomical targets. Building on this diverse dataset, we develop the CADS-model using established architectures for accessible and automated full-body CT segmentation. Through comprehensive evaluation across 18 public datasets and an independent real-world hospital cohort, we demonstrate advantages over SoTA approaches. Notably, thorough testing of the model's performance in segmentation tasks from radiation oncology validates its direct utility for clinical interventions. By making our large-scale dataset, our segmentation models, and our clinical software tool publicly available, we aim to advance robust AI solutions in radiology and make comprehensive anatomical analysis accessible to clinicians and researchers alike.

The availability of high-quality paired data is essential for training learning-based image demoiréing models. However, it remains challenging for existing datasets to encompass the complex moiré patterns captured in uncontrolled real-world scenarios. Such degradations typically manifest as large-scale, multicolored moiré patterns. Moreover, these patterns frequently occur in images for which clean counterparts are difficult to obtain, such as photographs acquired from public displays or existing online resources. In this work, we propose a novel data engine designed to improve the removal of complex moiré patterns by generating training supervision. Specifically, we initially collect real-world images containing complex moiré patterns and localize the corresponding screen regions. Multiple image-conditioned generative foundation models are subsequently deployed to produce candidate references. To establish reliable supervision, these candidates are subjected to patch-level quality control to filter and select the optimal results. Based on this systematic paradigm, we construct the WildMoiré dataset, which contains 6.8K moiré-GT training pairs. For evaluation, we additionally build an independent test set comprising sim250 pairs with captured clean ground truth. Extensive experiments on ESDNet, SDXL, and Qwen-Image-Edit demonstrate that the proposed generative supervision consistently improves the performance of complex moiré removal.

The Model Context Protocol (MCP), introduced by Anthropic in November 2024, defines a standardized interface for connecting large language models (LLMs) to external tools, data sources, and services. Within months of release, hundreds of community-built MCP servers appeared on GitHub, but no software-maintenance literature has yet described how the ecosystem is being structured in production. This industry experience paper catalogues five recurring MCP server architectural patterns observed across an enumerated corpus of fifteen independently developed servers (five production servers from the ANSYR voice AI platform plus ten public servers from the official MCP registry): Resource Gateway, Tool Orchestrator, Stateful Session Server, Proxy Aggregator, and Domain-Specific Adapter. Each pattern is described in the structured form of Gamma et al.: context, problem, solution, and consequences. We also document four anti-patterns and a set of cross-cutting concerns around authentication, versioning, and observability. The quantitative evaluation contributes three measurements: inter-rater reliability of the taxonomy across two independent LLM raters on 54 held-out servers (Cohen's kappa = 0.76), which also localizes three pattern-boundary ambiguities; transport overhead measured end-to-end on loopback and modeled for cross-host paths; and a tool-count study showing tool-selection accuracy drops below 90% between 10 and 15 tools per context for Claude Haiku 4.5 and between 20 and 30 tools for Sonnet 4. Code, corpus, and prompts are released as a replication package.

Oral health issues affect billions globally, but the cost and limited access to professional dental care hinder preventive oral healthcare. Research relies on clinical-grade radiographs or intraoral camera images, unavailable for public self-screening. This study introduces a tooth localisation and numbering model for smartphone photographs. We developed a customised Mask Region-based Convolutional Neural Network (Mask R-CNN) pipeline trained on 1,272 annotated smartphone images. To address variability in patient-generated health data, the pipeline incorporates two domain-informed mechanisms: a masked gray-world white-balancing algorithm to mitigate artificial colour casts and an anatomically constrained detection layer to enforce structural validity and suppress false positives. Evaluation comprised four stages: internal held-out testing, independent external testing, a descriptive ablation study, and fold-based training stability analysis using the same internal test set. On the internal test set, the model achieved an instance-mask AP@50 of 0.818, class-aware PQ of 0.780, and operational F1 of 0.884. Training stability showed limited between-model variation: across ten runs, instance-mask AP@50 had a standard deviation of 0.009. On the external dataset, the model achieved an instance-mask AP@50 of 0.901, class-aware PQ of 0.832, and operational F1 of 0.928 despite differences in population, sensors, and acquisition protocols. The inference pipeline is available as an open-source, containerised API. These results demonstrate that consumer-grade smartphone imagery can support automated tooth-level anatomical mapping, offering a scalable, potentially low-cost foundation for remote screening and tele-dentistry in resource-constrained environments.

Fake news detection becomes particularly challenging in real-time scenarios, where emerging events often lack sufficient supporting evidence. Existing approaches often rely heavily on external evidence and therefore struggle to generalize under evidence scarcity. To address this issue, we propose Evaluation-Aware Selection of Experts (EASE), a novel framework for real-time fake news detection that dynamically adapts its decision-making process according to the assessed sufficiency of available evidence. EASE introduces a sequential evaluation mechanism comprising three independent perspectives: (1) Evidence-based evaluation, which assesses evidence and incorporates it into decision-making only when the evidence is sufficiently supportive; (2) Reasoning-based evaluation, which leverages the world knowledge of large language models (LLMs) and applies them only when their reliability is adequately established; and (3) Sentiment-based fallback, which integrates sentiment cues when neither evidence nor reasoning is reliable. To enhance the accuracy of evaluation processes, EASE employs instruction tuning with pseudo labels to guide each evaluator in justifying its perspective-specific knowledge through interpretable reasoning. Furthermore, the expert modules integrate the evaluators' justified assessments with the news content to enable evaluation-aware decision-making, thereby enhancing overall detection accuracy. Moreover, we introduce RealTimeNews-25, a new benchmark comprising recent news for evaluating model generalization on emerging news with limited evidence. Extensive experiments demonstrate that EASE not only achieves state-of-the-art performance across multiple benchmarks, but also significantly improves generalization to real-time news. The code and dataset are available: https://github.com/wgyhhhh/EASE.

Advances in AI-assisted research have introduced powerful tools for literature retrieval, hypothesis generation, experimentation, and manuscript preparation. However, systems remain fragmented and lack human-centred workflows. To address these gaps, we introduce AIssistant, an agentic, open-source Human-AI collaborative framework designed to simplify the end-to-end creation of scientific workflows. Since our development is still in an early stage, we present here the first experiments with AIssistant for perspective and review research papers in machine learning. Our system integrates modular tools and agents for literature synthesis, section-wise experimentation, citation management, and automatic LaTeX paper text generation, while maintaining human oversight at every stage to ensure accuracy, coherence, and scholarly rigour. We conducted a comprehensive evaluation across three layers: (1) Independent Human Review, following NeurIPS double-blind standards; (2) Automated LLM Review, using GPT-5 as a scalable human review proxy; and (3) Program Chair Oversight, where the chair monitors the entire review process and makes final validation and acceptance decisions. The results demonstrate that AIssistant improves drafting efficiency and thematic consistency. Nonetheless, Human-AI collaboration remains essential for maintaining factual correctness, methodological soundness, and ethical compliance. Despite its effectiveness, we identify key limitations, including hallucinated citations, difficulty adapting to dynamic paper structures, and incomplete integration of multimodal content.

Instruction-tuned large language models produce helpful, structured responses, but how robust is this helpfulness under trivial constraints? We show that simple lexical constraints (banning a single punctuation character or common word) cause instruction-tuned LLMs to collapse their responses, losing 14--48\% of comprehensiveness across seven models spanning five families (7B--70B, open- and closed-weight). A blinded human evaluation with 10 STEM-trained evaluators confirms genuine content loss, with information criteria degrading 1.5--2.3times more than surface criteria, a finding corroborated by over 4,100 automated pairwise comparisons (77--100\% baseline preference) across three LLM judges from two model families. Diagnostic analysis identifies this as a planning failure: two-pass generation recovers 59--96\% of response length, and linear probes on prompt representations predict response length with R^2 = 0.51--0.94 before generation begins. The same probes yield negative R^2 on base models, confirming that instruction tuning introduces the representational structure underlying the collapse. Base models show no systematic degradation under identical constraints, demonstrating that instruction tuning couples task competence to narrow surface-form templates. The effect extends to realistic deployment constraints (preamble suppression, corporate tone guidelines, legal compliance hedging, accessibility requirements) causing comparable degradation (-22\% to -34\%), with suppressing the conversational opener alone (``Certainly!'') causing 40\% collapse on our most fragile model despite restricting only the opening tokens. We further show that standard independent LLM-as-judge evaluation detects only a 3.5\% quality drop where pairwise evaluation reveals 23\%, exposing a methodological blind spot in current evaluation practice.

Large Language Models (LLMs) drive scientific question-answering on modern search engines, yet their evaluation robustness remains underexplored. We introduce YESciEval, an open-source framework that combines fine-grained rubric-based assessment with reinforcement learning to mitigate optimism bias in LLM evaluators. We release multidisciplinary scienceQ&A datasets, including adversarial variants, with evaluation scores from multiple LLMs. Independent of proprietary models and human feedback, our approach enables scalable, cost-free evaluation. By advancing reliable LLM-as-a-judge models, this work supports AI alignment and fosters robust, transparent evaluation essential for scientific inquiry.

We introduce an axiomatic evaluation framework for latent thought representations in LLMs, comprising metrics that are independent of downstream benchmark scores and reveal representational failures that benchmark accuracy masks. Existing evaluations conflate representation quality with model capacity. Therefore, failures cannot be attributed to the representation rather than to the model that processes it. We formalize four functional axioms (Causality, Minimality, Separability, and Stability) and define a quantitative measure for each, computed directly on the representation independently of downstream accuracy. We audit open-weight LLMs across 23 reasoning tasks (e.g., Spatial Reasoning, Factual QA). We find that no candidate satisfies all four axioms simultaneously, that the representations distinguish task type reliably but cannot distinguish between two questions within the same task, and that the representations encode little information beyond what is already present in the input embedding. The failure is consistent across dense, reasoning-distilled, and RL-trained model families, indicating that the gap is structural rather than a property of model size or training procedure.

Multi-agent LLM applications organize execution in synchronized rounds where a central scheduler gathers outputs from all agents and redistributes the combined context. This All-Gather communication pattern creates massive KV Cache redundancy, because every agent's prompt contains the same shared output blocks, yet existing reuse methods fail to exploit it efficiently. We present TokenDance, a system that scales the number of concurrent agents by exploiting the All-Gather pattern for collective KV Cache sharing. TokenDance's KV Collector performs KV Cache reuse over the full round in one collective step, so the cost of reusing a shared block is paid once regardless of agent count. Its Diff-Aware Storage encodes sibling caches as block-sparse diffs against a single master copy, achieving 11-17x compression on representative workloads. Evaluation on GenerativeAgents and AgentSociety shows that TokenDance supports up to 2.7x more concurrent agents than vLLM with prefix caching under SLO requirement, reduces per-agent KV Cache storage by up to 17.5x, and achieves up to 1.9x prefill speedup over per-request position-independent caching.

This paper presents FoFo, a pioneering benchmark for evaluating large language models' (LLMs) ability to follow complex, domain-specific formats, a crucial yet underexamined capability for their application as AI agents. Despite LLMs' advancements, existing benchmarks fail to assess their format-following proficiency adequately. FoFo fills this gap with a diverse range of real-world formats and instructions, developed through an AI-Human collaborative method. Our evaluation across both open-source (e.g., Llama 2, WizardLM) and closed-source (e.g., GPT-4, PALM2, Gemini) LLMs highlights three key findings: open-source models significantly lag behind closed-source ones in format adherence; LLMs' format-following performance is independent of their content generation quality; and LLMs' format proficiency varies across different domains. These insights suggest the need for specialized tuning for format-following skills and highlight FoFo's role in guiding the selection of domain-specific AI agents. FoFo is released here at https://github.com/SalesforceAIResearch/FoFo.

Eye gaze is an important non-verbal cue for human affect analysis. Recent gaze estimation work indicated that information from the full face region can benefit performance. Pushing this idea further, we propose an appearance-based method that, in contrast to a long-standing line of work in computer vision, only takes the full face image as input. Our method encodes the face image using a convolutional neural network with spatial weights applied on the feature maps to flexibly suppress or enhance information in different facial regions. Through extensive evaluation, we show that our full-face method significantly outperforms the state of the art for both 2D and 3D gaze estimation, achieving improvements of up to 14.3% on MPIIGaze and 27.7% on EYEDIAP for person-independent 3D gaze estimation. We further show that this improvement is consistent across different illumination conditions and gaze directions and particularly pronounced for the most challenging extreme head poses.

Large language models (LLMs) are increasingly used to access legal information. Yet, their deployment in multilingual legal settings is constrained by unreliable retrieval and the lack of domain-adapted, open-embedding models. In particular, existing multilingual legal corpora are not designed for semantic retrieval, and PDF-based legislative sources introduce substantial noise due to imperfect text extraction. To address these challenges, we introduce LEMUR, a large-scale multilingual corpus of EU environmental legislation constructed from 24,953 official EUR-Lex PDF documents covering 25 languages. We quantify the fidelity of PDF-to-text conversion by measuring lexical consistency against authoritative HTML versions using the Lexical Content Score (LCS). Building on LEMUR, we fine-tune three state-of-the-art multilingual embedding models using contrastive objectives in both monolingual and bilingual settings, reflecting realistic legal-retrieval scenarios. Experiments across low- and high-resource languages demonstrate that legal-domain fine-tuning consistently improves Top-k retrieval accuracy relative to strong baselines, with particularly pronounced gains for low-resource languages. Cross-lingual evaluations show that these improvements transfer to unseen languages, indicating that fine-tuning primarily enhances language-independent, content-level legal representations rather than language-specific cues. We publish code\href{https://github.com/nargesbh/eur_lex{GitHub Repository}} and data\href{https://huggingface.co/datasets/G4KMU/LEMUR{Hugging Face Dataset}}.

Agentic systems are evaluated on benchmarks where agents interact with environments to solve tasks. Most papers report a pass@1 score computed from a single run per task, assuming this gives a reliable performance estimate. We test this assumption by collecting 60,000 agentic trajectories on SWE-Bench-Verified, spanning three models and two scaffolds. We find substantial variance: single-run pass@1 estimates vary by 2.2 to 6.0 percentage points depending on which run is selected, with standard deviations exceeding 1.5 percentage points even at temperature 0. This variance has critical implications: reported improvements of 2--3 percentage points may reflect evaluation noise rather than genuine algorithmic progress. Through token-level analysis, we show that trajectories diverge early, often within the first few percent of tokens, and that these small differences cascade into different solution strategies. To enable reliable evaluation of agentic systems, we recommend three concrete practices: (1) estimate pass@1 from multiple independent runs per task, especially when measuring small improvements, (2) use statistical power analysis to determine the number of runs needed to detect expected effect sizes, and (3) consider metrics like pass@k (optimistic bound) and pass^k (pessimistic bound) with k>1 to better characterize the full performance envelope. While these practices increase evaluation cost, they are essential for distinguishing genuine scientific progress from statistical noise.

Large language models (LLMs) are increasingly applied as automatic evaluators for natural language generation assessment often using pairwise comparative judgements. Existing approaches typically rely on single judges or aggregate multiple judges assuming equal reliability. In practice, LLM judges vary substantially in performance across tasks and evaluation aspects, and their judgment probabilities may be biased and inconsistent. Furthermore, human-labelled supervision for judge calibration may be unavailable. We first empirically demonstrate that inconsistencies in LLM comparison probabilities exist and show that it limits the effectiveness of direct probability-based ranking. To address this, we study the LLM-asa-jury setting and propose BT-sigma, a judge-aware extension of the Bradley-Terry model that introduces a discriminator parameter for each judge to jointly infer item rankings and judge reliability from pairwise comparisons alone. Experiments on benchmark NLG evaluation datasets show that BT-sigma consistently outperforms averaging-based aggregation methods, and that the learned discriminators strongly correlate with independent measures of the cycle consistency of LLM judgments. Further analysis reveals that BT-sigma can be interpreted as an unsupervised calibration mechanism that improves aggregation by modelling judge reliability.

We study device-addressed speech detection under pre-ASR edge deployment constraints, where systems must decide whether to forward audio before transcription under strict latency and compute limits. We show that, in multi-speaker environments with temporally ambiguous utterances, this task is more effectively modelled as a sequential routing problem over interaction history than as an utterance-local classification task. We formalize this as Sequential Device-Addressed Routing (SDAR) and present the Selective Attention System (SAS), an on-device implementation that instantiates this formulation. On a held-out 60-hour multi-speaker English test set, the primary audio-only configuration achieves F1=0.86 (precision=0.89, recall=0.83); with an optional camera, audio+video fusion raises F1 to 0.95 (precision=0.97, recall=0.93). Removing causal interaction history (Stage~3) reduced F1 from 0.95 to 0.57+/-0.03 in the audio+video configuration under our evaluation protocol. Among the tested components, this was the largest observed ablation effect, indicating that short-horizon interaction history carries substantial decision-relevant information in the evaluated setting. SAS runs fully on-device on ARM Cortex-A class hardware (<150 ms latency, <20 MB footprint). All results are from internal evaluation on a proprietary dataset evaluated primarily in English; a 5-hour evaluation subset may be shared for independent verification (Section 8.8).

Emergent misalignment can arise when a language model is fine-tuned on a narrowly scoped supervised objective: the model learns the target behavior, yet also develops undesirable out-of-domain behaviors. We investigate a mechanistic approach to preventing emergent misalignment by identifying a small set of internal features that reliably control the misaligned behavior and then discouraging the model from strengthening these features during fine-tuning. Across six fine-tuning domains, blocking (i.e., constraining) a fixed set of features achieves up to 95\% relative reduction in emergent misalignment with no degradation in model quality or target-task performance. We strengthen validity with disjoint selection/evaluation splits, multiple independent judges, multiple random seeds for key settings, quality metrics, and extensive ablations demonstrating that the reduction in misalignment is specific to the identified mechanism. We also characterize a limiting regime in which misalignment re-emerges under prolonged fine-tuning, present evidence consistent with rerouting through alternative features or layers, and evaluate modifications that partially restore the misalignment-blocking effect. Overall, our results show that targeted training-time constraints on internal mechanisms can mitigate emergent misalignment without degrading target-task performance.

Despite the advances in the abstractive summarization task using Large Language Models (LLM), there is a lack of research that asses their abilities to easily adapt to different domains. We evaluate the domain adaptation abilities of a wide range of LLMs on the summarization task across various domains in both fine-tuning and in-context learning settings. We also present AdaptEval, the first domain adaptation evaluation suite. AdaptEval includes a domain benchmark and a set of metrics to facilitate the analysis of domain adaptation. Our results demonstrate that LLMs exhibit comparable performance in the in-context learning setting, regardless of their parameter scale.

Accurate monitoring of forest disturbances is essential for understanding carbon dynamics and land management, yet traditional approaches typically rely on pixel-wise analysis of satellite time-series, ignoring spatial context. We present a deep learning framework that maps 38 years (1984-2022) of forest disturbance across the contiguous United States by modeling temporal trajectories and spatial neighborhoods simultaneously. By leveraging a vision transformer architecture, our approach effectively filters noise from weak supervision signals to produce spatially coherent disturbance maps. We perform exhaustive evaluations across multiple satellites (Landsat, Sentinel-1, Sentinel-2) and temporal windows (38 years and the more recent 6 years), validating performance against a novel, manually annotated validation dataset (n=300) and independent fire perimeter dataset (n=706). The results highlight the complexity of the task: while our spatio-temporal model demonstrates high precision (up to 98.2% for +-1 year detection on MTBS and up to 71.3% on the CONUS validation datasets, with F1-scores up to 75.8% and 47.3%, respectively) and effectively reduces spatial artifacts, it exhibits performance trade-offs across different disturbance regimes compared to pixel-wise baselines. Our method offers a promising foundation for consistent forest monitoring.

Large language models (LLMs) have shown impressive capabilities in real-world applications. The capability of in-context learning (ICL) allows us to adapt an LLM to downstream tasks by including input-label exemplars in the prompt without model fine-tuning. However, the quality of these exemplars in the prompt greatly impacts performance, highlighting the need for an effective automated exemplar selection method. Recent studies have explored retrieval-based approaches to select exemplars tailored to individual test queries, which can be undesirable due to extra test-time computation and an increased risk of data exposure. Moreover, existing methods fail to adequately account for the impact of exemplar ordering on the performance. On the other hand, the impact of the instruction, another essential component in the prompt given to the LLM, is often overlooked in existing exemplar selection methods. To address these challenges, we propose a novel method named EASE, which leverages the hidden embedding from a pre-trained language model to represent ordered sets of exemplars and uses a neural bandit algorithm to optimize the sets of exemplars while accounting for exemplar ordering. Our EASE can efficiently find an ordered set of exemplars that performs well for all test queries from a given task, thereby eliminating test-time computation. Importantly, EASE can be readily extended to jointly optimize both the exemplars and the instruction. Through extensive empirical evaluations (including novel tasks), we demonstrate the superiority of EASE over existing methods, and reveal practical insights about the impact of exemplar selection on ICL, which may be of independent interest. Our code is available at https://github.com/ZhaoxuanWu/EASE-Prompt-Optimization.

Digital signatures prove key possession, not authorship. An author who generates text with AI, constructs intermediate document states post-hoc, and signs each hash produces a signature chain indistinguishable from genuine composition. We address this gap between cryptographic integrity and process provenance. We introduce proof-of-process, a primitive category for evidence that a physical process, not merely a signing key, produced a digital artifact. Our construction, the jitter seal, injects imperceptible microsecond delays derived via HMAC from a session secret, keystroke ordinal, and cumulative document hash. Valid evidence requires that real keystrokes produced the document through those intermediate states. We propose the Adversarial Collapse Principle as an evaluation criterion: evidence systems should be judged by whether disputing them requires a conjunction of specific, testable allegations against components with independent trust assumptions. We present Witnessd, an architecture combining jitter seals with Verifiable Delay Functions, external timestamp anchors, dual-source keystroke validation, and optional hardware attestation. Each layer forces allegations at different capability levels; disputing authentic evidence requires coordinated claims across independent trust boundaries. The system does not prevent forgery: a kernel-level adversary can defeat it, and typing AI-generated content produces valid evidence. The contribution is converting vague doubt into falsifiable allegations. We evaluate across 31,000 verification trials with deterministic rejection of invalid proofs.

Esports, despite its expanding interest, lacks fundamental sports analytics resources such as accessible data or proven and reproducible analytical frameworks. Even Counter-Strike: Global Offensive (CSGO), the second most popular esport, suffers from these problems. Thus, quantitative evaluation of CSGO players, a task important to teams, media, bettors and fans, is difficult. To address this, we introduce (1) a data model for CSGO with an open-source implementation; (2) a graph distance measure for defining distances in CSGO; and (3) a context-aware framework to value players' actions based on changes in their team's chances of winning. Using over 70 million in-game CSGO events, we demonstrate our framework's consistency and independence compared to existing valuation frameworks. We also provide use cases demonstrating high-impact play identification and uncertainty estimation.

Face recognition templates are compact identity representations, yet they also encode rich semantic information about facial appearance. Prior work has shown that templates can be inverted to images or indirectly manipulated through image-editing pipelines, but direct semantic editing in template space remains largely unexplored. Existing interpretability methods for face recognition often rely on manual neuron inspection or predefined attribute labels, limiting scalability and semantic flexibility. To address this gap, we propose SCOUT (Semantic Concept Discovery for Open-VocabUlary Editing of Face Recognition Templates), an end-to-end framework for discovering and directly manipulating semantic concepts in face recognition templates using mechanistic interpretability. SCOUT learns sparse template representations, generates semantic hypotheses for latent features from natural-language descriptions, and validates their stability. The resulting features act as controllable semantic directions for direct editing, avoiding costly edit--re-encode pipelines. Experiments with face recognition models using CNN, ViT, and Swin backbones show that SCOUT discovers interpretable concepts beyond standard attribute labels and enables controllable, identity-aware template manipulation with negligible impact on identity matching. We further show that edited templates can subsequently be decoded with independent inversion models for visualization and evaluation.

Prompt optimization in compound AI systems is statistically indistinguishable from a coin flip: across 72 optimization runs on Claude Haiku 4.5 (6 methods times 4 tasks times 3 repeats), 49% score below zero-shot; on Amazon Nova Lite, the failure rate is even higher. Yet on one task, all six methods improve over zero-shot by up to +6.8 points. What distinguishes success from failure? We investigate with 18,000 grid evaluations and 144 optimization runs, testing two assumptions behind end-to-end optimization tools like TextGrad and DSPy, in the order they must be answered: (A) agent prompts interact, requiring joint rather than independent optimization, and (B) individual prompts are worth optimizing at all. Interaction effects are never significant (p > 0.52, all F < 1.0), and optimization helps only when the task has exploitable output structure: a format the model can produce but does not default to. We further give a mechanistic account: instruction-tuning compresses input phrasing into a narrow output distribution, eliminating the very phrasing-sensitivity that joint optimization assumes. We provide a two-stage diagnostic: an \$80 ANOVA pre-test for agent coupling, and a 10-minute headroom test that predicts whether optimization is worthwhile, turning a coin flip into an informed decision.

We present a reproducible pipeline for mapping Common Vulnerabilities and Exposures (CVEs) to MITRE ATT&CK Enterprise techniques from free-text vulnerability descriptions. Rather than relying on the CWE->CAPEC->ATT&CK derivation chain, whose table-expansion artifacts we quantify, we train a multi-label classifier on a curated gold dataset of 1,207 CVEs from expert MITRE Center for Threat-Informed Defense mappings. The resulting model approximately doubles recall@5 compared with a zero-shot embedding-similarity baseline and improves every ranking metric. We then investigate whether LLM-assisted labeling can extend the gold dataset. Initial experiments suggest contradictory conclusions: a single run indicates degraded performance, while averaging over five random seeds suggests a small gain. However, an independent replication and an expansion-size study (100--984 additional CVEs) show that the apparent improvement is an evaluation artifact. LLM-generated labels, with approximately 0.39 agreement with expert annotations, provide no reliable improvement at any expansion size and reduce rare-technique coverage at around 1,000 added CVEs (macro-F1 decreases by 0.04). The root cause is evaluation noise. Selecting checkpoints on a small test split effectively maximizes over many noisy evaluations, producing recall@5 differences of up to 0.05 between otherwise identical runs. Using a corrected protocol based on validation-split checkpoint selection, the gold-only model achieves recall@5 of (0.673 \pm 0.019), and repeating the decisive experiment confirms the null result for LLM expansion. A final scaling study shows that additional expert-curated data consistently improves performance, whereas LLM-labeled data does not, indicating that the classifier is limited by label quality rather than dataset size. All datasets, models, code, and training logs are publicly released.

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

This work introduces TopoBenchmarkX, a modular open-source library designed to standardize benchmarking and accelerate research in Topological Deep Learning (TDL). TopoBenchmarkX maps the TDL pipeline into a sequence of independent and modular components for data loading and processing, as well as model training, optimization, and evaluation. This modular organization provides flexibility for modifications and facilitates the adaptation and optimization of various TDL pipelines. A key feature of TopoBenchmarkX is that it allows for the transformation and lifting between topological domains. This enables, for example, to obtain richer data representations and more fine-grained analyses by mapping the topology and features of a graph to higher-order topological domains such as simplicial and cell complexes. The range of applicability of TopoBenchmarkX is demonstrated by benchmarking several TDL architectures for various tasks and datasets.

Large language models (LLMs) exhibiting test-time scaling behavior, such as extended reasoning traces and self-verification, have demonstrated remarkable performance on complex, long-term reasoning tasks. However, the robustness of these reasoning behaviors remains underexplored. To investigate this, we conduct a systematic evaluation of multiple reasoning models across three scenarios: (1) problems augmented with lengthy, irrelevant context; (2) multi-turn conversational settings with independent tasks; and (3) problems presented as a subtask within a complex task. We observe an interesting phenomenon: reasoning models tend to produce much shorter reasoning traces (up to 50%) for the same problem under different context conditions compared to the traces produced when the problem is presented in isolation. A finer-grained analysis reveals that this compression is associated with a decrease in self-verification and uncertainty management behaviors, such as double-checking. While this behavioral shift does not compromise performance on straightforward problems, it might affect performance on more challenging tasks. We hope our findings draw additional attention to both the robustness of reasoning models and the problem of context management for LLMs and LLM-based agents.

Agents, language model (LM)-based systems that are capable of reasoning, planning, and acting are becoming the dominant paradigm for real-world AI applications. Despite this widespread adoption, the principles that determine their performance remain underexplored, leaving practitioners to rely on heuristics rather than principled design choices. We address this gap by deriving quantitative scaling principles for agent systems. We evaluate this across four diverse benchmarks: Finance-Agent, BrowseComp-Plus, PlanCraft, and Workbench. Using five canonical architectures (Single, Independent, Centralized, Decentralized, Hybrid) instantiated across three LLM families, we perform a controlled evaluation spanning 180 configurations with standardized tools and token budgets. We derive a predictive model using empirical coordination metrics, including efficiency, overhead, error amplification, and redundancy, that achieves cross-validated R^2=0.513. We identify three dominant effects: (1) a tool-coordination trade-off: under fixed computational budgets, tool-heavy tasks suffer disproportionately from multi-agent overhead. (2) a capability saturation: coordination yields diminishing or negative returns (beta=-0.408, p<0.001) once single-agent baselines exceed ~45%. (3) topology-dependent error amplification: independent agents amplify errors 17.2x through unchecked propagation, while centralized coordination contains this to 4.4x. Centralized coordination improves performance by 80.9% on parallelizable tasks like financial reasoning, while decentralized coordination excels on dynamic web navigation (+9.2% vs. +0.2%). Yet for sequential reasoning tasks, all multi-agent variants degraded performance by 39-70%. The framework predicts the optimal coordination strategy for 87% of held-out configurations, providing a predictive principle of agentic scaling based on measurable task properties.

As large language model (LLM) agents evolve from isolated tool users into coordinated teams, reinforcement learning (RL) must optimize not only individual actions but also how work is spawned, delegated, communicated, aggregated, and stopped. This paper studies RL for LLM-based multi-agent systems through orchestration traces: temporal interaction graphs whose events include sub-agent spawning, delegation, communication, tool use, return, aggregation, and stopping decisions. Using this lens, we identify three technical axes. First, reward design spans eight families, including orchestration rewards for parallelism speedup, split correctness, and aggregation quality. Second, reward and credit signals attach to eight credit- or signal-bearing units from token to team; explicit counterfactual message-level credit remains especially sparse in our curated pool. Third, orchestration learning decomposes into five sub-decisions: when to spawn, whom to delegate to, how to communicate, how to aggregate, and when to stop. In our curated pool as of May 4, 2026, we found no explicit RL training method for the stopping decision. We connect academic methods to public industrial evidence from Kimi Agent Swarm, OpenAI Codex, and Anthropic Claude Code. The resulting scale gap is a gap between publicly reported deployment envelopes and open academic evaluation regimes, not independent verification of industrial training traces. We release the artifact at https://github.com/xxzcc/awesome-llm-mas-rl, including an 84-entry tagged paper pool, a 32-record exclusion log, scripted corpus statistics, and a minimal JSON schema for replayable orchestration traces.

Large language models (LLMs) excel at answering pre-specified questions, yet their ability to navigate the open-ended, pre-conclusion stage of discovery remains largely unmeasured. We introduce Prospective Hypothesis Discovery (PHD), which asks models to autonomously construct grounded, discriminative, and testable hypothesis spaces from inconclusive evidence, including anomalous observations and fragmented records, to guide subsequent investigation. To evaluate this capability, we introduce HypoArena, comprising HypoData, a benchmark of 988 cases across six scientific and analytical domains, and HypoEval, an evaluation framework for open-ended hypothesis sets. To construct HypoData at scale, we propose Retrospective Context Regression, a Forge--Audit pipeline that reconstructs pre-conclusion contexts from completed expert documents by removing explicit conclusions, target hypotheses, and retrospective causal attributions while preserving the factual substrate. Because PHD admits multiple valid outputs, HypoEval combines bidirectional pairwise judgments with Bradley--Terry--Davidson aggregation for ranking and six-dimensional rubric scoring for diagnosis. Experiments on 15 frontier LLMs reveal clear capability stratification and model-dependent effects of structured analytical skills, with gains for several lower-performing models on HypoArena but regressions for other systems, including a top-performing model. Compared with absolute rubric scoring, arena evaluation resolves finer-grained differences among models, with aggregated rankings showing strong agreement with human experts and an independent judge. Together, these results support treating PHD as a distinct target for evaluating how LLMs formulate investigative directions when final conclusions are withheld. Our code and data are publicly available at github.com/SKYLENAGE-AI/HypoArena and github.com/SKYLENAGE-AI/HypoArena.

Turn-level metrics are widely used to evaluate properties of multi-turn human-LLM conversations, from safety and sycophancy to dialogue quality. However, consecutive turns within a conversation are not statistically independent -- a fact that virtually all current evaluation pipelines fail to correct for in their statistical inference. We systematically characterize the autocorrelation structure of 66 turn-level metrics across 202 multi-turn conversations (11,639 turn pairs, 5 German-speaking users, 4 LLM platforms) and demonstrate that naive pooled analysis produces severely inflated significance estimates: 42% of associations that appear significant under standard pooled testing fail to survive cluster-robust correction. The inflation varies substantially across categories rather than scaling linearly with autocorrelation: three memoryless families (embedding velocity, directional, differential) aggregate to 14%, while the seven non-memoryless families (thermo-cycle, frame distance, lexical/structural, rolling windows, cumulative, interaction, timestamp) aggregate to 33%, with individual category rates ranging from 0% to 100% depending on per-family effect size. We present a two-stage correction framework combining Chelton (1983) effective degrees of freedom with conversation-level block bootstrap, and validate it on a pre-registered hold-out split where cluster-robust metrics replicate at 57% versus 30% for pooled-only metrics. We provide concrete design principles, a publication checklist, and open-source code for the correction pipeline. A survey of ~30 recent papers at major NLP and AI venues that compute turn-level statistics in LLM evaluations finds that only 4 address temporal dependence at all, and 26 do not correct for it.

Reinforcement Learning Fine-Tuning (RLFT) has achieved notable success in tasks with objectively verifiable answers (e.g., code generation, mathematical reasoning), yet struggles with open-ended subjective tasks like role-playing dialogue. Traditional reward modeling approaches, which rely on independent sample-wise scoring, face dual challenges: subjective evaluation criteria and unstable reward signals.Motivated by the insight that human evaluation inherently combines explicit criteria with implicit comparative judgments, we propose Comparative Policy Optimization (CPO). CPO redefines the reward evaluation paradigm by shifting from sample-wise scoring to comparative group-wise scoring.Building on the same principle, we introduce the CharacterArena evaluation framework, which comprises two stages:(1) Contextualized Multi-turn Role-playing Simulation, and (2) Trajectory-level Comparative Evaluation. By operationalizing subjective scoring via objective trajectory comparisons, CharacterArena minimizes contextual bias and enables more robust and fair performance evaluation. Empirical results on CharacterEval, CharacterBench, and CharacterArena confirm that CPO effectively mitigates reward ambiguity and leads to substantial improvements in dialogue quality.

Neutron/gamma discrimination has been intensively researched in recent years, due to its unique scientific value and widespread applications. With the advancement of detection materials and algorithms, nowadays we can achieve fairly good discrimination. However, further improvements rely on better utilization of detector raw signals, especially energy-independent pulse characteristics. We begin by discussing why figure-of-merit (FoM) is not a comprehensive criterion for high-precision neutron/gamma discriminators, and proposing a new evaluation method based on adversarial sampling. Inspired by frequency-domain analysis in existing literature, parametric linear/nonlinear models with minimum complexity are created, upon the discrete spectrum, with tunable parameters just as neural networks. We train the models on an open-source neutron/gamma dataset (CLYC crystals with silicon photomultipliers) preprocessed by charge normalization to discover and exploit energy-independent features. The performance is evaluated on different sampling rates and noise levels, in comparison with the frequency classification index and conventional methods. The frequency-domain parametric models show higher accuracy and better adaptability to variations of data integrity than other discriminators. The proposed method is also promising for online inference on economical hardware and portable devices.