Omni-modal large language models are increasingly evaluated on clean text–vision–audio inputs, where every channel is present, synchronized, and readily interpretable. Such scores are often taken as evidence of robust cross-modal fusion, but clean evaluation cannot tell whether success depends on stable cross-modal structure or on cues sufficient only in intact inputs. To address this gap, we define a modality fault line: a boundary at which model behavior becomes unstable when a modality remains present and human-interpretable, but its internal evidence structure is perturbed. We introduce SCEval (Structure-Corruption Evaluation) a diagnostic evaluation protocol that keeps the question, answer space, and modality channels fixed while applying controlled structural corruptions to text, vision, and audio individually and jointly. Built from 273 human-verified tri-modal examples from Social-IQ, OmniBench, and VALOR, SCEval evaluates 15 proprietary and open-source omni-modal systems. The results show that structural corruption lowers clean accuracy, text–vision damage forms the most stable shared fault line, and multi-modal degradation is non-additive rather than a simple function of the number of corrupted modalities. Clean omni-modal accuracy therefore does not establish that a model will remain reliable when cross-modal evidence becomes structurally unreliable.

Large language models (LLMs) excel at semantic understanding, yet their ability to reconstruct internal structure from scrambled inputs remains underexplored. Sentence-level restoration is difficult to evaluate automatically because scrambled sentences often admit multiple valid reorderings. We introduce OrderProbe, a deterministic benchmark for structural reconstruction using fixed four-character expressions in Chinese, Japanese, and Korean, which have a unique canonical order and thus support exact-match scoring. We further propose a diagnostic framework that evaluates models beyond recovery accuracy, including Semantic Accuracy, Logical Validity, Structural Consistency, Robustness, and Information Density. Experiments on twelve widely used LLMs show that structural reconstruction remains difficult even for frontier systems: zero-shot recovery frequently falls below 35%. We also observe a consistent gap between meaning-oriented generation and exact structural reconstruction, suggesting that structural robustness is not an automatic byproduct of semantic competence.

LLM-based agentic systems have shown remarkable capabilities in complex domains, while suffering from cascading errors and difficulty in debugging. Critical error detection aims to locate the earliest error step in a failed trajectory that is responsible for the final failure. However, progress faces two main challenges. First, long trajectories make it difficult to identify individual errors, since the evidence for judging a step may be scattered across distant instructions, observations, and prior context. Second, failed trajectories often contain multiple local errors with different downstream effects, only some of which remain responsible for the final failure. In this work, we propose TrajDebug, an error-lifecycle tracing framework that addresses long-trajectory error discovery with multi-granularity history compression and evidence-based error identification, and supports critical attribution by tracing each error’s resolution status and terminal impact. We further construct TrajErrBench, a benchmark of 486 manually annotated failed trajectories from and SWE-Bench Pro, covering realistic tool-use and coding scenarios. Experiments across diverse agent benchmarks show that TrajDebug achieves the best overall performance over existing baselines, and application studies further demonstrate that its diagnoses provide actionable feedback for improving downstream agent success. We will release the codes and data to facilitate further research.

The core of knowledge distillation lies in transferring the teacher’s rich ’dark knowledge’—subtle probabilistic patterns that reveal how classes are related and the distribution of uncertainties. While this idea is well established, teachers trained with conventional cross-entropy often fail to preserve such signals. Their distributions appear decisive but are in fact brittle, offering little beyond the hard label. This overconfidence is especially problematic in high-cardinality tasks, where subtle distinctions among many plausible classes are crucial for guiding compact students. To address this limitation, we revisit distillation from a distributional perspective and propose Calibrated Uncertainty Distillation (CUD), a framework that makes dark knowledge more faithfully accessible. Instead of uncritically inheriting the teacher’s overconfidence, CUD encourages the teacher to expose informative uncertainty and guides the student to learn from calibrated targets instead of overly sharpened predictions. By shaping the teacher’s predictive distribution before transfer, our approach balances accuracy and calibration, allowing students to benefit from both confident signals on easy cases and structured uncertainty on hard ones.

Multimodal Large Language Models (MLLMs) have increasingly supported omni-modal processing across text, vision, and speech. However, existing evaluation frameworks for such models suffer from critical limitations, including modality shortcuts and biased reasoning paths. To address these challenges, we propose OMHBench, a novel benchmark designed to rigorously evaluate omni-modal multi-hop reasoning. It consists of 6,144 questions with balanced reasoning paths that are jointly grounded across all three modalities. Extensive evaluation of 13 state-of-the-art models reveals that (1) a large performance gap exists between proprietary and open-source MLLMs and (2) even proprietary models exhibit high sensitivity to reasoning path variations, resulting in asymmetric omni-modal grounding. Notably, models struggle when processing the speech modality, underscoring the need for balanced, multi-hop evaluation of omni-modal intelligence.

Rubric-based scoring has become a widely used paradigm in model evaluation, typically with LLM-as-a-Judge (LaaJ) for rubric scoring. However, the reliability of LaaJ for rubric scoring remains underexplored. This concern is especially pronounced in agentic scenarios, where long, complex outputs further challenge reliable scoring. To address this, we conduct a systematic meta-evaluation of LaaJ reliability for rubric verification. We introduce RuVerBench, the first benchmark for assessing LaaJ reliability in rubric verification for agentic scenarios. RuVerBench covers two prevalent agentic domains, deep research and agentic coding, with 2,458 instances, each containing a model-generated output, a rubric, and a human-annotated label indicating whether the output satisfies the rubric. Using RuVerBench, we evaluate numerous frontier LLMs and find that even the most advanced models achieve strong performance but still exhibit substantial noise. We further analyze the impact of key LaaJ strategies, including prompt design, batching, and majority voting, on rubric verification. We find that weaker models are more sensitive to prompt variations, batched verification presents a trade-off between accuracy and efficiency, and majority voting yields effective but diminishing returns. We have released our dataset and code to facilitate future research: https://github.com/THU-KEG/RuVerBench.

Criminal judgment prediction requires models to infer statutory articles, charges, and sentencing outcomes from case facts. Unlike standard classification tasks, it involves a structured reasoning process in which statutes should be matched with facts, charges should be justified by statutes, and sentencing outcomes should remain consistent with charges. Existing approaches optimize final labels, and while some have attempted to evaluate reasoning quality, their evaluations are indirect, often relying on LLM-generated rubrics that reflect model-internal preferences rather than the inherent logical structure of legal adjudication. We propose Juris Policy Optimization (JPO), a post-training framework for structured legal reasoning in Chinese criminal judgment prediction. JPO first uses teacher-generated rationales to supervise a standardized four-step reasoning process, and then applies reinforcement learning with a composite reward over legal prediction quality, reasoning structure completeness, and cross-step consistency. JPO further introduces token-level advantage reweighting and adaptive clipping for legally salient reasoning segments. Experiments on multiple open-source language models and three Chinese legal benchmarks show that JPO consistently improves both judgment prediction and reasoning quality over supervised fine-tuning and reinforcement learning baselines.

The rapid advancement of large language models (LLMs) has not been matched by their evaluation in low-resource languages, especially Southeast Asian languages like Lao. To fill this gap, we introduce LaoBench, the first large-scale, high-quality, and multidimensional benchmark for assessing LLM language understanding and reasoning in Lao. LaoBench contains 17,000+ expert-curated samples across three dimensions: culturally grounded knowledge application, curriculum-aligned K12 education, and bilingual translation among Lao, Chinese, and English. It includes open-source and held-out subsets, where the held-out portion enables secure black-box evaluation via a controlled service to improve fairness and data security. We construct LaoBench with a hybrid pipeline that combines expert authoring with agent-assisted verification, ensuring linguistic accuracy, cultural relevance, and educational validity. We evaluate diverse state-of-the-art open-source and closed-source LLMs, and find that even strong multilingual models lag behind human experts, particularly in culturally grounded reasoning and translation fidelity. We hope LaoBench will catalyze research on Lao and other underrepresented Southeast Asian languages for more inclusive multilingual evaluation.

Idioms have long posed a challenge due to their unique linguistic properties, which set them apart from other common expressions. While recent studies have leveraged large language models (LLMs) to handle idioms across various tasks, e.g., idiom-containing sentence generation and idiomatic machine translation, little is known about the underlying mechanisms of idiom processing in LLMs, particularly in multilingual settings. To this end, we introduce MIDAS, a new large-scale dataset of idioms in six languages, each paired with its corresponding meaning. Leveraging this resource, we conduct a comprehensive evaluation of LLMs’ idiom processing ability, identifying key factors that influence their performance. Our findings suggest that LLMs rely not only on memorization, but also adopt a hybrid approach that integrates contextual cues and reasoning, especially when processing compositional idioms. This implies that idiom understanding in LLMs emerges from an interplay between internal knowledge retrieval and reasoning-based inference.

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, with a demonstration video available at https://youtu.be/L7EtacjoM0k.

We introduce FlagEval-Arena, an evaluation platform for side-by-side comparisons of large language models and text-driven AIGC systems.Compared with the well-known LM Arena (LMSYS Chatbot Arena), we reimplement our own framework with the flexibility to introduce new mechanisms or features. Our platform enables side-by-side evaluation not only for language models or vision-language models, but also text-to-image or text-to-video synthesis. We specifically target at Chinese audience with a more focus on the Chinese language, more models developed by Chinese institutes, and more general usage beyond the technical community. As a result, we currently observe very interesting differences from usual results presented by LM Arena. Our platform is available via this URL: https://flageval.baai.org/#/arena.

Chinese Spelling Check (CSC) aims to detect and correct potentially misspelled characters in Chinese sentences. Naturally, it involves the detection and correction subtasks, which interact with each other dynamically. Such interactions are bi-directional, i.e., the detection result would help reduce the risk of over-correction and under-correction while the knowledge learnt from correction would help prevent false detection. Current CSC approaches are of two types: correction-only or single-directional detection-to-correction interactive frameworks. Nonetheless, they overlook the bi-directional interactions between detection and correction. This paper aims to fill the gap by proposing a Bi-directional Detector-Corrector framework for CSC (Bi-DCSpell). Notably, Bi-DCSpell contains separate detection and correction encoders, followed by a novel interactive learning module facilitating bi-directional feature interactions between detection and correction to improve each other’s representation learning. Extensive experimental results demonstrate a robust correction performance of Bi-DCSpell on widely used benchmarking datasets while possessing a satisfactory detection ability.