Large Language Models (LLMs) exhibit strong general reasoning but struggle in molecular science due to the lack of explicit priors required for precise chemical reasoning. Current solutions inject priors into parameters, but this static coupling hinders rapid knowledge updates and often compromises the model’s general capabilities. To address this, we introduce REAP, a training-free framework that equips LLMs with an external knowledge base, enabling them to reason over retrieved chemical priors dynamically. REAP implements a structured reasoning pipeline that autonomously selects relevant priors from our constructed atom-level knowledge base, retrieves analogue exemplars, and synthesizes these information to guide the LLM’s decision-making. This architecture ensures interpretability and adaptability while preserving the LLM’s intrinsic general intelligence. Experiments show that REAP outperforms current reasoning methods and rivals state-of-the-art training-based models, demonstrating the effectiveness of our framework.
论文检索
输入标题、作者或关键词，从 100,903 篇学术成果中精准定位
MTMCS-Bench: Evaluating Contextual Safety of Multimodal Large Language Models in Multi-Turn Dialogues
PDF ↗Multimodal large language models (MLLMs) are increasingly deployed as assistants that interact through text and images, making it crucial to evaluate contextual safety when risk depends on both the visual scene and the evolving dialogue. Existing contextual safety benchmarks are mostly single-turn and often miss how malicious intent can emerge gradually or how the same scene can support both benign and exploitative goals. We introduce the Multi-Turn Multimodal Contextual Safety Benchmark (MTMCS-Bench), a benchmark of realistic images and multi-turn conversations that evaluates contextual safety in MLLMs under two complementary settings, escalation-based risk and context-switch risk. MTMCS-Bench offers paired safe and unsafe dialogues with structured evaluation. It contains over 30 thousand multimodal (image+text) and unimodal (text-only) samples, with metrics that separately measure contextual intent recognition, safety-awareness on unsafe cases, and helpfulness on benign ones. Across eight open-source and seven proprietary MLLMs, we observe persistent trade-offs between contextual safety and utility, with models tending to either miss gradual risks or over-refuse benign dialogues. Finally, we evaluate five current guardrails and find that they mitigate some failures but do not fully resolve multi-turn contextual risks.
Agentic Reinforcement Learning (Agentic RL) has achieved notable success in enabling agents to perform complex reasoning and tool use. However, most methods still relies on sparse outcome-based reward for training. Such feedback fails to differentiate intermediate reasoning quality, leading to suboptimal training results. In this paper, we introduce Agent Reasoning Reward Model (Agent-RRM), a multi-faceted reward model that produces structured feedback for agentic trajectories, including (1) an explicit reasoning trace , (2) a focused critique that provides refinement guidance by highlighting reasoning flaws, and (3) an overall score that evaluates process performance. Leveraging these signals, we systematically investigate three integration strategies: Reagent-C (text-augmented refinement), Reagent-R (reward-augmented guidance), and Reagent-U (unified feedback integration). Extensive evaluations across 12 diverse benchmarks demonstrate that Reagent-U yields substantial performance leaps, achieving 43.7% on GAIA and 46.2% on WebWalkerQA, validating the effectiveness of our reasoning reward model and training schemes. Code, models, and datasets will be released to facilitate future research.
Beyond Token Length: Step Pruner for Efficient and Accurate Reasoning in Large Language Models
PDF ↗Large Reasoning Models (LRMs) demonstrate strong performance on complex tasks but often suffer from excessive verbosity, known as "overthinking." Existing solutions via reinforcement learning (RL) typically penalize generated tokens to promote conciseness. However, these methods encounter two challenges: responses with fewer tokens do not always correspond to fewer reasoning steps, and models may develop hacking behavior in later stages of training by discarding reasoning steps to minimize token usage. In this work, we introduce Step Pruner (SP), an RL framework that steers LRMs toward more efficient reasoning by favoring compact reasoning steps. Our step-aware reward function prioritizes correctness while imposing penalties for redundant steps, and withholds rewards for incorrect responses to prevent the reinforcement of erroneous reasoning. Moreover, we propose a dynamic stopping mechanism to prevent hacking behavior caused by step merging. Extensive experiments across four reasoning benchmarks demonstrate that SP achieves state-of-the-art accuracy while significantly reducing response length. For instance, on AIME24, SP reduces token usage by 69.7%.
Large language models (LLMs) have driven major advances across domains, yet their massive size hinders deployment in resource-constrained settings. Low-rank factorization addresses this challenge by compressing models to effectively reduce their computation and memory consumption while maintaining accuracy. While these compressed models boast benign performance and system-level advantages, their trustworthiness implications remain poorly understood. In this paper, we present the first comprehensive study of how low-rank factorization affects LLM trustworthiness across privacy, adversarial robustness, ethics, and fairness, complemented by an explainability-driven analysis of the internal mechanisms behind these trust-related changes. We evaluate multiple LLMs of different sizes and architectures compressed with various low-rank factorization algorithms, revealing key insights: (1) low-rank factorization preserves training data privacy but weakens the protection of personally identifiable information during conversations; (2) adversarial robustness is generally enhanced under compression; (3) ethics degrades in zero-shot prompting but partially recovers in few-shot prompting; (4) fairness declines under compression. Beyond compression, we investigate how model scale and fine-tuning affect trustworthiness. Additionally, to move beyond black-box analysis, we employ a gradient-based attribution to identify which layers of LLMs contribute most to adversarial robustness.
Static Models, Dynamic World: A Unified Perspective on Temporal Perception in Large Language Models
PDF ↗Large language models are trained on static corpora but deployed in a dynamic world, leading to systematic temporal failures—from mis-anchored expressions and inconsistent timelines to hallucinated future events, stale world knowledge, and related issues. Existing surveys on temporal knowledge graphs, retrieval-augmented generation, hallucination, and knowledge editing cover only isolated fragments of this space: they are typically task-centric and do not offer a holistic theoretical account of how frozen LLMs represent and reason about time. This survey provides a unified perspective on temporal reasoning in LLMs. We formalize temporal queries in an information-theoretic framework based on the parametric reachability of temporal premises and answers, which induces four temporal information regimes corresponding to internal reasoning, answer recency, premise anchoring, and genuine world indeterminacy. Under this lens, we delineate the landscape of temporal failure modes, consolidate methodologies for diagnosing temporal deficiencies, and synthesize mitigation approaches into a coherent design space. Together, these contributions provide a systematic roadmap toward reliable time-aware large language models.
Lil: Less is Less When Applying Post-Training Sparse-Attention Algorithms in Long-Decode Stage
PDF ↗Large language models (LLMs) demonstrate strong capabilities across a wide range of complex tasks and are increasingly deployed at scale, placing significant demands on inference efficiency. Prior work typically decomposes inference into prefill and decode stages, with the decode stage dominating total latency. To reduce time and memory complexity in the decode stage, a line of work introduces sparse-attention algorithms. In this paper, we show, both empirically and theoretically, that sparse attention can paradoxically increase end-to-end complexity: information loss often induces significantly longer sequences, a phenomenon we term “Less is Less” (Lil). To mitigate the Lil problem, we propose an early-stopping algorithm that detects the threshold where information loss exceeds information gain during sparse decoding. Our early-stopping algorithm reduces token consumption by up to 90% with a marginal accuracy degradation of less than 2% across reasoning-intensive benchmarks.
Recent advancements in Spatial Intelligence (SI) have predominantly relied on Vision-Language Models (VLMs), yet a critical question remains: does spatial understanding originate from visual encoders or the fundamental reasoning backbone? Inspired by this question, we introduce **SiT-Bench**, a novel benchmark designed to evaluate the SI performance of Large Language Models (LLMs) without pixel-level input, comprises over 3,800 expert-annotated items across five primary categories and 17 subtasks, ranging from egocentric navigation and perspective transformation to fine-grained robotic manipulation. By converting single/multi-view scenes into high-fidelity, coordinate-aware textual descriptions, we challenge LLMs to perform symbolic textual reasoning rather than visual pattern matching. Evaluation results of state-of-the-art (SOTA) LLMs reveals that while models achieve proficiency in localized semantic tasks, a significant "spatial gap" remains in global consistency. Notably, we find that explicit spatial reasoning significantly boosts performance, suggesting that LLMs possess latent world-modeling potential. Our proposed dataset SiT-Bench serves as a foundational resource to foster the development of spatially-grounded LLM backbones for future VLMs and embodied agents.
Multi-hop Knowledge Graph Question Answering (KGQA) requires coherent reasoning across relational paths, yet existing methods often treat each reasoning step independently and fail to effectively leverage experience from prior explorations, leading to fragmented reasoning and redundant exploration. To address these challenges, we propose Trajectoryaware Reasoning with Adaptive Context and Exploration priors (TRACE), an experiential framework that unifies LLM-driven contextual reasoning with exploration prior integration to enhance the coherence and robustness of multihop KGQA. Specifically, TRACE dynamically translates evolving reasoning paths into natural language narratives to maintain semantic continuity, while abstracting prior exploration trajectories into reusable experiential priors that capture recurring exploration patterns. A dualfeedback re-ranking mechanism further integrates contextual narratives with exploration priors to guide relation selection during reasoning. Extensive experiments on multiple KGQA benchmarks demonstrate that TRACE consistently outperforms state-of-the-art baselines.
A Multilingual Dataset and Empirical Validation for the Mutual Reinforcement Effect in Information Extraction
PDF ↗The Mutual Reinforcement Effect (MRE) describes a phenomenon in information extraction where word-level and sentence-level tasks can mutually improve each other when jointly modeled. While prior work has reported MRE in Japanese, its generality across languages and task settings has not been empirically validated, largely due to the lack of multilingual MRE datasets. To address this limitation, we introduce the Multilingual MRE Mix dataset (MMM), which consists of 21 sub-datasets covering English, Japanese, and Chinese. We propose an LLM-assisted dataset translation and alignment framework that significantly reduces manual annotation effort while preserving the structural requirements of MRE tasks. Building on MMM, we adopt a unified input-output framework to train an open-domain information extraction model and conduct extensive empirical studies, including full fine-tuning ablations and the construction of knowledgeable verbalizers based on MRE-mix data. Experimental results show that 76 percent of the MMM sub-datasets consistently exhibit the Mutual Reinforcement Effect across languages. These findings provide systematic empirical validation of MRE in multilingual settings and demonstrate its practical value for information extraction.
Role-playing models (RPMs) are widely used in real-world applications but underperform when deployed in the wild. This degradation can be attributed to distribution shifts, including user, character, and dialogue compositional shifts. Existing methods like LLM-as-a-judge fall short in providing a fine-grained diagnosis of how these shifts affect RPM generalization, and thus there lack formal frameworks to characterize RPM generalization behaviors. To bridge these gaps, we introduce an information-theoretic metric, named reasoning-based effective mutual information difference (R-EMID), to measure RPM performance degradation in an interpretable way. We also derive an upper bound on R-EMID to predict the worst-case generalization performance of RPMs and theoretically reveal how various shifts contribute to the RPM performance degradation. Moreover, we propose a co-evolving reinforcement learning framework to adaptively model the connection among user, character, and dialogue context and thus enhance the estimation of dialogue response generation probability, which is critical for calculating R-EMID. Finally, we evaluate the generalization performance of various RPMs using R-EMID, finding that user shift poses the highest risk among all shifts and reinforcement learning is the most effective approach for enhancing RPM generalization. Code and data are available at https://github.com/AlibabaResearch/DAMO-ConvAI/tree/main/RPM-Generalization.
Large language models (LLMs) increasingly rely on external tools to complete complex tasks, yet their ability to recognize and correct their own tool-use mistakes remains underexplored. Existing benchmarks primarily evaluate planning and execution success, overlooking the self-reflective dimension of tool use. To address this gap, we present ReflecTool-Bench, the first benchmark designed to assess LLMs’ self-reflective reasoning in tool-augmented multi-turn dialogues. ReflecTool-Bench covers 10 domains with 88 distinct APIs and 968 annotated dialogues, systematically injecting diverse error types arising from both user and assistant behavior. The benchmark defines two complementary evaluation setups: the Critique task, where models diagnose errors in third-party dialogues, and the Self-Reflection Task, where models must detect and repair their own prior tool-use mistakes. We introduce fine-grained metrics for error detection, error classification, correction accuracy, and explanation quality, enabling a holistic assessment of reflective reasoning. Evaluations across 12 state-of-the-art models, including both API-based closed source models and open source models, reveal that while models can reliably identify user-originated errors, they struggle with assistant-originated ones, and performance drops sharply when moving from critique to self-reflection.
Rethinking Research on Stereotypes: An Analysis through Social Psychological and Computational Perspectives
PDF ↗Stereotypes are social constructs shaping human perception and behavior that can produce harmful outcomes under specific conditions. Recent work shows that large language models (LLMs) may inherit and amplify such social harms. However, most existing research often focuses only upon stereotypical biases and overlooks stereotypes and the rich social psychological literature on them, resulting in resource wastage and slowed progress in stereotype research.We argue that meaningful progress in mitigating stereotypes in LLMs requires tighter integration between social psychology and computational research. To address this gap, we review core social psychological theories and frameworks and analyze their computational operationalization, highlighting substantial open opportunities.We also analyze computational progress across media narratives, body imaging, and multilingual, multicultural, and multimodal contexts, identifying key gaps and limitations in each domain.We also present a unified analysis of challenges in stereotype research.We further discuss implications for responsible AI, highlighting stereotypes as a major source of downstream harms, and briefly examine the limitations of current mitigation approaches along with potential improvements via explainability and interpretability. We frame stereotypes in AI as socio-technical phenomena and urge further research in responsible AI, informed by the perspectives and future directions presented in this paper.
BV-Blend: Uncertainty-Weighted Historical Baselines for Stable Critic-Free RL with Verifiable Rewards
PDF ↗Critic-free reinforcement learning with verifiable rewards (RLVR), exemplified by Group Relative Policy Optimization (GRPO), avoids training a value function (critic) and reduces memory and compute overhead relative to critic-based PPO pipelines for aligning large language models. However, GRPO-style advantage estimation depends on prompt-local (within-prompt-group) reward statistics and can be unstable. In particular, when all rollouts in a prompt group receive identical rewards, the within-group reward variance becomes zero, and group normalization yields *zero* advantages for that group, impeding learning in cold-start regimes with binary verifiers. We introduce **BV-Blend**, a critic-free framework that stabilizes advantage estimation by combining prompt-local on-policy statistics with semantic-cluster-conditioned historical moments. BV-Blend maintains EMA-tracked reward moments for each cluster, derives a confidence weight from a standard error of the mean (SEM) proxy, and uses this weight to blend historical and prompt-local baseline and variance statistics into a standardized advantage for PPO-style clipped updates. Experiments on verifiable reasoning benchmarks show that BV-Blend improves training stability and performance, and remains robust in regimes where group-normalized methods may stall.
Lunar-Bench: Towards Evaluating Task-Oriented Reasoning of LLMs in Lunar Exploration Scenarios
PDF ↗The increasing complexity of lunar exploration calls for intelligent systems capable of supporting autonomous operations and scientific decision-making under uncertain and resource-limited conditions. Advances in large language models (LLMs) create new opportunities for mission planning, but their reliability in dynamic, safety-critical environments remains insufficiently evaluated. Existing benchmarks focus on static, context-independent reasoning tasks and fail to capture the constraints and dependencies of lunar missions. To address this gap, we introduce Lunar-Bench, a benchmark designed to assess the task-oriented reasoning and decision-making performance of LLMs through 3,000 tasks derived from mission procedures and documentation. We further propose the Environmental Scenario Indicators, a process-based framework that evaluates safety, efficiency, integrity, and alignment beyond conventional accuracy. Experiments on 36 representative models show that the best achieves 47.8% accuracy compared with 65.1% for human experts. Lunar-Bench and ESI together provide a principled foundation for developing reliable systems for future missions.
Infinity-Parser: Layout-Aware Reinforcement Learning with High-quality Document Parsing Dataset
PDF ↗Document parsing from scanned images into structured formats remains a significant challenge due to its complexly intertwined elements such as text paragraphs, figures, formulas, and tables. Existing supervised fine-tuning methods often struggle to generalize across diverse document types, leading to poor performance, particularly on out-of-distribution data. This issue is further exacerbated by the limited availability of high-quality training data for layout-aware parsing tasks. To address these challenges, we introduce layoutRL, a reinforcement learning framework that optimizes layout understanding through composite rewards integrating normalized edit distance, paragraph count accuracy, and reading order preservation. To support this training, we construct the Infinity-Doc-400K dataset, which we use to train Infinity-Parser, a vision-language model demonstrating robust generalization across various domains. Extensive evaluations on benchmarks including OmniDocBench, olmOCR-Bench, PubTabNet, and FinTabNet show that Infinity-Parser consistently achieves state-of-the-art performance across a broad range of document types, languages, and structural complexities, substantially outperforming both specialized document parsing systems and general-purpose vision-language models. We will release our code, dataset, and model to facilitate reproducible research in document parsing.
Recent Long-Context Language Models (LCLMs) can process hundreds of thousands of tokens in a single prompt, enabling new opportunities for knowledge-intensive multi-hop reasoning by integrating large sets of retrieved documents or, in some cases, directly all necessary information. However, simply feeding more documents into the context window fails to capture how evidence should be connected. We address this gap with thought templates, reusable reasoning patterns derived from prior problem solving that structure how evidence is combined and guide multi-hop inference alongside factual documents. To keep these templates effective, we propose an update strategy that iteratively refines templates derived from training data through natural-language feedback. Across diverse benchmarks and LCLM families, our approach delivers consistent gains over strong baselines in both retrieval-based and retrieval-free settings. Furthermore, we show that optimized templates can be distilled into relatively smaller open-source models, demonstrating its broad applicability. We refer to our framework as Thought Template Augmented LCLMs (ToTAL).
Code-mixing involves the seamless integration of linguistic elements from multiple languages within a single discourse, reflecting natural multilingual communication patterns. Despite its prominence in informal interactions such as social media, chat messages and instant-messaging exchanges, there has been a lack of publicly available corpora that are author-labeled and suitable for modeling human conversations and relationships. This study introduces the first labeled and general-purpose corpus for understanding code-mixing in context while maintaining rigorous privacy and ethical standards. It includes over 355,641 messages spanning various code-mixing patterns, with a primary focus on English, Mandarin, and other languages. We expect the Codemix Corpus to serve as a foundational dataset for research in computational linguistics, sociolinguistics, and NLP applications.
Transformer architecture gradually dominates the LLM field. Recent advances in training optimization for Transformer-based large language models (LLMs) primarily focus on architectural modifications or optimizer adjustments. However, these approaches lack systematic optimization of weight patterns during training. Weight pattern refers to the distribution and relative magnitudes of weight parameters in a neural network. To address this issue, we propose a Weight Scaling method called WISCA to enhance training efficiency and model quality by strategically improving neural network weight patterns—without changing network structures. By rescaling weights while preserving model outputs, WISCA indirectly optimizes the model’s training trajectory. Experiments demonstrate that WISCA significantly improves convergence quality (measured by generalization capability and loss reduction), particularly in LLMs with Grouped Query Attention (GQA) architectures and LoRA fine-tuning tasks. Empirical results show 5.6% average improvement on zero-shot validation tasks and 2.12% average reduction in training perplexity across multiple architectures.
Large Language Models (LLMs) excel at natural language understanding and generation, yet their reliance on static pre-training corpora may lead to outdated knowledge, hallucinations, and limited adaptability. Retrieval-Augmented Generation (RAG) mitigates these issues by grounding model outputs with external retrieval, but conventional RAG remains constrained by a fixed retrieve-then-generate routine and struggles with multi-step reasoning and tool calls. **Agentic RAG** addresses these limitations by enabling LLM agents to actively decompose tasks, issue exploratory queries, and refine evidence through iterative retrieval. Despite growing interest, the development of Agentic RAG is impeded by *data scarcity*: unlike traditional RAG, it requires challenging tasks that require planning, retrieval, and multiple reasoning decisions, and corresponding rich, interactive agent trajectories. This survey presents the first data-centric overview of Agentic RAG, framing its data lifecycle—data collecting, data preprocessing and task formulation, task construction, data for evaluation, and data enhancement for training—and cataloging representative training datasets and benchmarks in different domains (e.g. question answering, web, software engineering). From data perspectives, we aim to guide the creation of scalable, high-quality datasets for the next generation of adaptive, knowledge-seeking LLM agents. The project page is at https://github.com/fatty-belly/Awesome-AgenticRAG-Data/.