让下一篇重要论文，不再错过。

新论文 · v1arXiv:2611.02988

更新于 2026-11-02

Can You Predict the Next Mind? Toward Multi-Turn Multi-Party Mental World Modeling

Jiahao Huang, Zheng Lian

原文摘要

While multimodal foundation models have achieved remarkable progress in physical world modeling, generation, and embodied reasoning, their capacity for dynamic mental world modeling remains underexplored. Existing benchmarks predominantly focus on static mental state perception or short-horizon decision-making, overlooking the dynamic mental trajectories inherent in multi-party, multi-turn interactions. To bridge this gap, we introduce M$^3$WME-Bench, a benchmark designed to evaluate mental world modeling conditioned on the evolving actions of interactants. Specifically, models are tasked with forecasting a target subject's future mental states and behaviors over extended social interactions. In addition to the benchmark suite, we construct M$^3$WME-23K, a dedicated training dataset, and establish a competitive baseline named MindNext-7B. Extensive evaluations across four representative paradigms (general MLLMs, emotion-specialized MLLMs, agentic frameworks, and World Foundation Models) reveal that current systems consistently struggle to anticipate forward-looking mental states. Mechanistic analyses further reveal that existing architectures fundamentally lack forward mental state transition dynamics. Our findings highlight a pivotal challenge in advancing agents from physical to mental world modeling, charting new directions for socially adaptive AI.

cs.HC

版本更新 · v2arXiv:2610.35252

更新于 2026-11-02

Labference: Benchmarking the Reasoning-Action Connection in Robotic Laboratories

Shitong Liu, Xu Yang, Jingwei Zhang, Sheng Lian, Xinyu Zhuang, Kaiwen Guo, Quan Liu, Chunhai Zhao 等 21 位作者

原文摘要

Realizing Embodied AI for Science requires robots to translate experimental goals into reliable physical procedures, reducing hazardous and repetitive human work while generating evidence for scientific discovery. Although language-based planning and learned manipulation provide complementary capabilities, their integration requires robots to adapt subsequent operations to actual execution outcomes. For example, an unsuccessful placement changes what must be done next, even when the experimental goal remains unchanged. Existing benchmarks assess planning, manipulation, and laboratory workflows through task completion and reasoning or execution metrics; however, aggregate performance leaves the connection between outcome-dependent choices and physical execution unresolved. To address this evaluation gap, we introduce Labference, a benchmark for evaluating how observed physical outcomes guide subsequent choices and how those choices translate into robotic laboratory actions. Its evaluation protocol is designed to test outcome-dependent behavioral adaptation through controlled evidence variations, while independently measuring operation selection, physical execution, and task completion. Matched Oracle-assisted continuations from shared checkpoints then assess which forms of support improve subsequent choices and task completion. Initial weighing evaluations reveal target-selection errors in the tested VLA policies despite successful object transfers, whereas GPT-driven control achieves correct selection but encounters execution failures and substantial computation costs. Together, these findings highlight the need to connect task-appropriate reasoning with reliable, timely action. By making this connection measurable and diagnosable, Labference supports targeted improvements toward autonomous experimentation for Embodied AI for Science.

cs.RO

新论文 · v1arXiv:2611.01484

更新于 2026-11-01

CrossSWE: Benchmarking Cross-Repository Joint Development for Coding Agents

Silin Chen, Yuling Shi, Heng Lian, Zihan Zhang, Xiaodong Gu, Haotian Lin, Zhensu Sun

原文摘要

As coding agents achieve increasingly high success rates on software engineering benchmarks, recent efforts have sought to increase task complexity through longer horizons and more extensive code modifications. However, real-world software development often spans multiple interdependent repositories, introducing additional challenges in dependency reasoning, change propagation, and interface consistency. Rather than further increasing complexity within individual repositories, we introduce CrossSWE, a benchmark for cross-repository joint development comprising 171 real-world instances spanning 165 repositories, 20 technical domains, and 13 programming languages. CrossSWE verifies the necessity of coordinated changes by testing whether partial repository modifications are insufficient to achieve the intended behavior. Our evaluation of five LLMs reveals substantial challenges, with the strongest model, GPT-6.1 Sol, achieving only 58.48% Pass@1. Furthermore, cross-repository inconsistencies emerge as the most prevalent failure mode (44.2%), highlighting the difficulty of maintaining consistency across interdependent repositories.

cs.SE

版本更新 · v2arXiv:2605.30058

更新于 2026-10-27

HEART-Bench: Do LLMs Make Persona-Consistent Decisions?

Weihan Peng, Chenxu Zhang, Qianao Wang, Yuling Shi, Heng Lian, Qihong Mao, Jiahao Pang, Chunliang Feng 等 10 位作者

原文摘要

LLM agents in interactive entertainment and social applications, including companions, role-play characters, and persona clones, need decisions grounded in personality and past experiences. We introduce HEART-Bench to evaluate memory-grounded persona-consistent response selection. The benchmark combines 11 Big Five-anchored synthetic characters, each with 1,000 autobiographical memories, and 64 DIAMONDS-guided decision scenarios into 673 multiple-choice questions. Domain experts independently compare candidate responses, with a senior expert resolving disagreements and revising responses when needed; other characters' adjudicated responses to the same scenario serve as distractors. In the main evaluation, models receive character IDs and occupations, scenarios, and options, with retrieved memories added in memory-augmented settings. Detailed personality-and-value profiles are withheld. We evaluate 16 LLMs under No-Retrieval, Naive-RAG, Mem0, and PersonaDB. Accuracy without memories stays near the 25% chance level, and the best memory-augmented configuration reaches 64.9%. On a matched 150-item subset, human annotators reach 80.8%, compared with 64.0% for the best model. Memory-content ablations show the importance of retrieving experiences that match both the target character and the decision context.

cs.CL

版本更新 · v2arXiv:2605.06126

更新于 2026-10-27

AffectGPT-RL: Revealing Roles of Reinforcement Learning in Open-Vocabulary Emotion Recognition

Zheng Lian, Fan Zhang, Lan Chen, Yazhou Zhang, Rui Liu, Jinyang Wu, Haoyu Chen, Xiaobai Li 等 11 位作者

原文摘要

Open-Vocabulary Multimodal Emotion Recognition (OV-MER) aims to predict emotions without being constrained by predefined label spaces, thereby enabling fine-grained emotion understanding. Unlike traditional discriminative methods, OV-MER leverages generative models to capture the full spectrum of emotions and employs emotion wheels (EWs) for metric calculation. Previous approaches primarily rely on token-level loss during training. However, this objective is misaligned with the metrics used in OV-MER, and these metrics cannot be directly optimized via gradient backpropagation. To address this limitation, we turn our attention to reinforcement learning, as this strategy can optimize non-differentiable objectives. We term this framework AffectGPT-RL. Furthermore, we conduct extensive experiments to elucidate the role of reinforcement learning in this task, revealing the necessity of the reasoning process, the impact of different rewards, and the generalizability to other emotion tasks such as sentiment analysis and basic emotion recognition. Experimental results demonstrate that AffectGPT-RL yields significant performance improvements on OV-MER. Beyond this task, we also achieve remarkable performance gains on basic emotion recognition, attaining state-of-the-art results on MER-UniBench. To the best of our knowledge, this is the pioneering work exploring the role of reinforcement learning in OV-MER, providing valuable guidance for subsequent researchers. Our code is provided at: https://github.com/zeroQiaoba/AffectGPT/tree/master/AffectGPT-RL.

cs.HC

新论文 · v1arXiv:2610.36210

更新于 2026-10-27

Diagnosing and Correcting Bias in MLLM for Long Video Understanding

Xusheng Liang, Jianqiao Sun, Hao Zhang, Yulei Niu, Hengshuang Zhao, Jiawei Ma

原文摘要

Long-video question answering is challenging since the answer often hinges on a few decisive moments scattered throughout the video, while memory constraints force Multimodal Large Language Models (MLLMs) to sample frames at extremely low rates, resulting in sparsity that risks omitting key evidence. Though aggressively enlarging the context size is intuitive, we argue that performance remains fundamentally constrained by the bias, \emph{i.e.}, the misleading cues caused by spurious \textit{linguistic} correlations and salient yet irrelevant \textit{visual} observations. In this paper, we first introduce {S-MME}, a benchmark designed to systematically diagnose shortcut-biased behavior in MLLMs. To mitigate this failure, we further propose a training-free framework, Counterfactual Long-video Evidence-Aware Reasoning (CLEAR). By treating the full video-question pair as a complete view, CLEAR estimates bias effects via augmented views by only keeping the question or locally salient visual clips. Then, we intervene hidden states to mitigate the discrepancy at inference such that the correct answer can be predicted confidently. With experimental studies across five benchmarks, we show that our method is generalizable and can be integrated in different MLLMs, yielding consistent gains in prediction and robustness. We hope CLEAR can offer a complementary direction in test-time scaling for long-video understanding.

cs.CV

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.135ACL Anthology · ACL 2026

来源日期 2026-07-01（仅到月份）

Beyond Examples: Towards Automated Thought-level In-Context Reasoning for Large Language Models

Jinyang Wu Tsinghua University, Mingkuan Feng Tsinghua University, Shuai Zhang, Feihu Che, Zhengqi Wen Tsinghua University, Chonghua Liao, Ling Yang Princeton University, Haoran Luo Nanyang Technological University 等 10 位作者

原文摘要

In-context learning (ICL) leverages demonstrations to enhance the performance of large language models (LLMs). However, traditional ICL struggles with complex reasoning mainly due to superficial, example-level implicit imitation. To address these limitations, we introduce ThoughtICR, an automated Thought-level In-Context Reasoning paradigm that shifts from surface-level examples to more guidance-oriented thought patterns. Specifically, we first define atomic reasoning actions and construct thought patterns on small-scale seed data using Monte Carlo Tree Search (MCTS). During inference, we dynamically select appropriate thought patterns based on target problem attributes, providing explicit guidance for model reasoning. Thanks to its automated and strategic design, our method enables seamless plug-and-play integration with various post-training techniques. Experimental results demonstrate that our method improves performance across different model sizes and generalizes effectively across reasoning domains. Using only small-scale seed data, we achieve 80.6% accuracy on MATH and 62.5% on AMC, surpassing GPT-4o’s 77.2% and 57.5%, respectively. Moreover, compared to test-time scaling methods, our approach reduces computational costs by over 10. Our code is available at https://github.com/jinyangwu/ThoughtICR.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1535ACL Anthology · ACL 2026

来源日期 2026-07-01（仅到月份）

ChemReason-Bench: Benchmarking Large Language Models for Procedural Reasoning in Experimental Chemistry

Jinwei Zhang, Xucheng Liang University of Southern California, Yu Zhang, Ruijie Yu, Xiaokang Yang Shanghai Jiaotong University, Yaohui Jin Shanghai Jiaotong University, Yanyan Xu Shanghai Jiaotong University

原文摘要

Experimental protocols in organic synthesis specify not only the intended transformation but also an executable sequence of operations and conditions. While recent language models show strong chemistry knowledge, widely used evaluations remain less diagnostic of procedure-level decision making. In this setting, correctness requires consistent step ordering, feasibility under stated conditions, faithful entity-role grounding, and schema-parseable outputs that can be automatically validated against operational constraints. We present ChemReason-Bench, a human-validated benchmark for verifiable experimental procedure reasoning built on a structured representation with explicit placeholders and a unified schema, enabling automatic checks of many operational constraints. From 500 reactions, we instantiate 7306 benchmark tasks across six complementary formats: ordering, step validation, condition validation, schema-constrained completion, contrastive choice, and evidence-grounded rationalization. We further release a large-scale instantiation of the same templates for downstream adaptation studies, kept disjoint from the evaluation set. Using a unified evaluation protocol, we benchmark diverse open-source, proprietary, and domain-specific models and observe clear variation across the capability surface. We also report controlled adaptation experiments in the appendix, where supervised fine-tuning improves small models, preference optimization adds limited gains in our setting, and a gap remains to the strongest evaluated systems.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1985ACL Anthology · ACL 2026

来源日期 2026-07-01（仅到月份）

ARES: Adaptive Red-Teaming and End-to-End Repair of Policy-Reward System

Jiacheng Liang, Yao Ma, Tharindu Kumarage, Satyapriya Krishna, Rahul Gupta, Kai-Wei Chang University of California, Los Angeles and Amazon, Aram Galstyan Information Sciences Institute, University of Southern California and Amazon Alexa, Charith Peris Amazon

原文摘要

Reinforcement Learning from Human Feedback (RLHF) is central to aligning Large Language Models (LLMs), yet it introduces a critical vulnerability: an imperfect Reward Model (RM) can become a single point of failure when it fails to penalize unsafe behaviors. While existing red-teaming approaches primarily target policy-level weaknesses, they overlook what we term systemic weaknesses cases where both the core LLM and the RM fail in tandem.We present ARES, a framework that systematically discovers and mitigates such dual vulnerabilities. ARES employs a “Safety Mentor” that dynamically composes semantically coherent adversarial prompts by combining structured component types (topics, personas, tactics, goals) and generates corresponding malicious and safe responses. This dual-targeting approach exposes weaknesses in both the core LLM and the RM simultaneously. Using the vulnerabilities gained, ARES implements a two-stage repair process: first fine-tuning the RM to better detect harmful content, then leveraging the improved RM to optimize the core model. Experiments across multiple adversarial safety benchmarks demonstrate that ARES substantially enhances safety robustness while preserving model capabilities, establishing a new paradigm for comprehensive RLHF safety alignment.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1988ACL Anthology · ACL 2026

来源日期 2026-07-01（仅到月份）

AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models

Jiacheng Liang, Tanqiu Jiang State University of New York at Stony Brook, Yuhui Wang State University of New York at Stony Brook, Rongyi Zhu Stony Brook University, State University of New York at Stony Brook, Fenglong Ma Pennsylvania State University, Ting Wang State University of New York at Stony Brook

原文摘要

This paper presents AutoRAN, the first framework to automate the hijacking of internal safety reasoning in large reasoning models (LRMs). At its core, AutoRAN pioneers an execution simulation paradigm that leverages a weaker but less-aligned model to simulate execution reasoning for initial hijacking attempts and iteratively refine attacks by exploiting reasoning patterns leaked through the target LRM’s refusals. This approach steers the target model to bypass its own safety guardrails and elaborate on harmful instructions. We evaluate AutoRAN against state-of-the-art LRMs, including GPT-o3/o4-mini and Gemini-2.5-Flash, across multiple benchmarks (AdvBench, HarmBench, and StrongReject). Results show that AutoRAN achieves approaching 100% success rate within one or few turns, effectively neutralizing reasoning-based defenses even when evaluated by robustly aligned external models. This work reveals that the transparency of the reasoning process itself creates a critical and exploitable attack surface, highlighting the urgent need for new defenses that protect models’ reasoning traces rather than merely their final outputs.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表