大模型推理能力

MathReal: We Keep It Real! A Real Scene Benchmark for Evaluating Math Reasoning in Multimodal Large Language Models

Jun Feng, Zixin Wang, Zhentao Zhang, Yue Guo, Zhihan Zhou, Xiuyi Chen, Zhenyang Li, Dawei Yin

专题命中 数学推理 ：reasoning(title,abstract)；math reasoning(title)

Comments 29 pages, 16 figures

Hypothesis-Driven Theory-of-Mind Reasoning for Large Language Models

Hyunwoo Kim, Melanie Sclar, Tan Zhi-Xuan, Lance Ying, Sydney Levine, Yang Liu, Joshua B. Tenenbaum, Yejin Choi

机构 * NVIDIA（NVIDIA公司） ； University of Washington（华盛顿大学） ； MIT（麻省理工学院） ； Harvard University（哈佛大学） ； Amazon（亚马逊公司） ； Stanford University（斯坦福大学） 纠错

专题命中 数学推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Comments COLM 2025. For code and data, see https://hyunw.kim/thought-tracing

AALC: Large Language Model Efficient Reasoning via Adaptive Accuracy-Length Control

Ruosen Li, Ziming Luo, Quan Zhang, Ruochen Li, Ben Zhou, Ali Payani, Xinya Du

机构 * University of Texas at Dallas（德克萨斯大学达拉斯分校） ； Arizona State University（亚利桑那州立大学） ； Cisco Research（思科研究） 纠错

专题命中 数学推理 ：reasoning(title,abstract)；分类 cs.CL

Mitigating Think-Answer Mismatch in LLM Reasoning Through Noise-Aware Advantage Reweighting

Si Shen, Peijun Shen, Wenhua Zhao, Danhao Zhu

专题命中 数学推理 ：reasoning(title,abstract)；分类 cs.LG

Structural Reformation of Large Language Model Neuron Encapsulation for Divergent Information Aggregation

Denis Bakushev, Gideon Boultinghouse, Harriet Oppenheimer, Sebastian Gillingwater, Valentina Ashington, Wilfred Stanborough

专题命中 数学推理 ：reasoning(abstract)；logical reasoning(abstract)；分类 cs.CL

Comments arXiv admin note: This paper has been withdrawn by arXiv due to disputed and unverifiable authorship

Don't Forget Imagination!

Evgenii E. Vityaev, Andrei Mantsivoda

机构 * Sobolev Institute of mathematics SD RAS（索洛维耶夫数学研究所（SD RAS）） ； Irkutsk State University（伊尔库茨克州立大学） 纠错

专题命中 数学推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

Comments 14 pages, 2 figures

Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future

Yidong Wang, Xin Wang, Cunxiang Wang, Junfeng Fang, Qiufeng Wang, Jianing Chu, Xuran Meng, Shuxun Yang, Libo Qin, Yue Zhang, Wei Ye, Shikun Zhang

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments 12 pages, 5 figures

Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Rosie Zhao, Alexandru Meterez, Sham Kakade, Cengiz Pehlevan, Samy Jelassi, Eran Malach

机构 * Harvard University（哈佛大学） ； Kempner Institute（凯普纳研究所） 纠错

专题命中 数学推理 ：reasoning(abstract)；分类 cs.LG

Comments COLM 2025

CodeARC: Benchmarking Reasoning Capabilities of LLM Agents for Inductive Program Synthesis

Anjiang Wei, Tarun Suresh, Jiannan Cao, Naveen Kannan, Yuheng Wu, Kai Yan, Thiago S. F. X. Teixeira, Ke Wang, Alex Aiken

机构 * Stanford University（斯坦福大学） ； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； MIT（麻省理工学院） ； Intel（英特尔） ； Nanjing University（南京大学） 纠错

专题命中 代码与定理证明 ：reasoning(title,abstract)；self-correction(abstract)；分类 cs.CL、cs.AI、cs.LG

Position: Intelligent Coding Systems Should Write Programs with Justifications

Xiangzhe Xu, Shiwei Feng, Zian Su, Chengpeng Wang, Xiangyu Zhang

机构 * Purdue University（普渡大学） 纠错

专题命中 代码与定理证明 ：reasoning(abstract)；分类 cs.CL、cs.LG

Comments The first two authors contributed equally to this work

Street View Sociability: Interpretable Analysis of Urban Social Behavior Across 15 Cities

Kieran Elrod, Katherine Flanigan, Mario Bergés

机构 * Carnegie Mellon University（卡内基梅隆大学） 纠错

专题命中 代码与定理证明 ：planning(abstract)

Code-as-Symbolic-Planner: Foundation Model-Based Robot Planning via Symbolic Code Generation

Yongchao Chen, Yilun Hao, Yang Zhang, Chuchu Fan

机构 * Massachusetts Institute of Technology（麻省理工学院） ； Harvard University（哈佛大学） ； MIT-IBM Watson AI Lab（MIT-IBM沃森人工智能实验室） 纠错

专题命中 规划推理 ：planning(title,abstract)；reasoning(abstract)；分类 cs.CL、cs.AI

Comments 7 pages, 7 figures, 3 tables

Journal ref 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'2025)

Society of Mind Meets Real-Time Strategy: A Hierarchical Multi-Agent Framework for Strategic Reasoning

Daechul Ahn, San Kim, Jonghyun Choi

机构 * Seoul National University（首尔国立大学） 纠错

专题命中 规划推理 ：reasoning(title)；分类 cs.AI

Comments COLM 2025

Self-Steering Language Models

Gabriel Grand, Joshua B. Tenenbaum, Vikash K. Mansinghka, Alexander K. Lew, Jacob Andreas

专题命中 规划推理 ：reasoning(abstract)；planning(abstract)；分类 cs.CL、cs.AI

Comments Accepted to COLM 2025

Optimizing Prompt Sequences using Monte Carlo Tree Search for LLM-Based Optimization

Fei Xu Yu, Gina Adam, Nathaniel D. Bastian, Tian Lan

机构 * The George Washington University（乔治·华盛顿大学） ； United States Military Academy（美国军事学院） 纠错

专题命中 规划推理 ：reasoning(abstract)；planning(abstract)；分类 cs.LG

Flow-Based Task Assignment for Large-Scale Online Multi-Agent Pickup and Delivery

Yue Zhang, Zhe Chen, Daniel Harabor, Pierre Le Bodic, Peter J. Stuckey

专题命中 规划推理 ：reasoning(abstract)；planning(abstract)

Automated Creation of the Legal Knowledge Graph Addressing Legislation on Violence Against Women: Resource, Methodology and Lessons Learned

Claudia dAmato, Giuseppe Rubini, Francesco Didio, Donato Francioso, Fatima Zahra Amara, Nicola Fanizzi

机构 * Computer Science Department, University of Bari Aldo Moro（巴里阿尔多·莫罗大学计算机科学系） 纠错

专题命中 规划推理 ：reasoning(abstract)；分类 cs.AI

LLMs for Resource Allocation: A Participatory Budgeting Approach to Inferring Preferences

Sankarshan Damle, Boi Faltings

机构 * Artificial Intelligence Laboratory (LIA), EPFL（人工智能实验室（LIA），瑞士联邦理工学院） 纠错

专题命中 规划推理 ：reasoning(abstract)；分类 cs.AI

Comments Published in the Proceedings of the 28th European Conference on Artificial Intelligence (ECAI 2025)

DAM: A Universal Dual Attention Mechanism for Multimodal Timeseries Cryptocurrency Trend Forecasting

Yihang Fu, Mingyu Zhou, Luyao Zhang

机构 * Duke Kunshan University（杜克昆山大学） 纠错

专题命中 规划推理 ：planning(abstract)；分类 cs.CL

Journal ref Proc. IEEE Int. Conf. Metaverse Computing Networking and Applications (MetaCom), pp. 73-80, 2024

Open-Source Agentic Hybrid RAG Framework for Scientific Literature Review

Aditya Nagori, Ricardo Accorsi Casonatto, Ayush Gautam, Abhinav Manikantha Sai Cheruvu, Rishikesan Kamaleswaran

机构 * Department of Surgery, Department of Anesthesiology, Duke University School of Medicine Durham North Carolina United States ； Faculty of Technology, University of Brasilia Brasilia Federal District Brazil ； Indian Institute of Technology Goa Goa India ； Birla Institute of Technology \& Science Pilani Hyderabad India ； Department of Electrical ； Computer Engineering, Duke University Pratt School of Engineering Department of Surgery, Department of Anesthesiology, Duke University School of Medicine Durham North Carolina United States ； Department of Surgery, Department of Anesthesiology, Duke University School of Medicine ； Faculty of Technology, University of Brasilia ； Indian Institute of Technology Goa ； Birla Institute of Technology \& Science Pilani ； Computer Engineering, Duke University Pratt School of Engineering 纠错

专题命中 规划推理 ：reasoning(abstract)；分类 cs.AI

A Multimodal Framework for Understanding Collaborative Design Processes

Maurice Koch, Nelusa Pathmanathan, Daniel Weiskopf, Kuno Kurzhals

专题命中 规划推理 ：planning(abstract)

Comments Accepted to IEEE VIS 2025

RoboTron-Nav: A Unified Framework for Embodied Navigation Integrating Perception, Planning, and Prediction

Yufeng Zhong, Chengjian Feng, Feng Yan, Fanfan Liu, Liming Zheng, Lin Ma

机构 * Meituan（美团） 纠错

专题命中 视觉空间推理 ：planning(title,abstract)

Comments ICCV 2025

Rank1: Test-Time Compute for Reranking in Information Retrieval

Orion Weller, Kathryn Ricci, Eugene Yang, Andrew Yates, Dawn Lawrie, Benjamin Van Durme

机构 * Johns Hopkins University（约翰霍普金斯大学） 纠错

专题命中 测试时计算 ：test-time compute(title,abstract)；reasoning(abstract)；分类 cs.CL、cs.LG

Comments Published at CoLM 2025

AURA: Affordance-Understanding and Risk-aware Alignment Technique for Large Language Models

Sayantan Adak, Pratyush Chatterjee, Somnath Banerjee, Rima Hazra, Somak Aditya, Animesh Mukherjee

专题命中 测试时计算 ：reasoning(abstract)；分类 cs.CL

SuperRL: Reinforcement Learning with Supervision to Boost Language Model Reasoning

Yihao Liu, Shuocheng Li, Lang Cao, Yuhang Xie, Mengyu Zhou, Haoyu Dong, Xiaojun Ma, Shi Han, Dongmei Zhang

机构 * Peking University（北京大学） ； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； Microsoft（微软公司） 纠错

专题命中 复杂问题求解 ：reasoning(title,abstract)；分类 cs.AI

M2IO-R1: An Efficient RL-Enhanced Reasoning Framework for Multimodal Retrieval Augmented Multimodal Generation

Zhiyou Xiao, Qinhan Yu, Binghui Li, Geng Chen, Chong Chen, Wentao Zhang

专题命中 复杂问题求解 ：reasoning(title,abstract)

SC-Captioner: Improving Image Captioning with Self-Correction by Reinforcement Learning

Lin Zhang, Xianfang Zeng, Kangcong Li, Gang Yu, Tao Chen

机构 * College of Future Information Technology, Fudan University（复旦大学未来信息科技学院） ； StepFun ； Shanghai Innovation Institute（上海创新研究院） 纠错

专题命中 复杂问题求解 ：self-correction(title)

Comments ICCV 2025

A Framework for Inherently Safer AGI through Language-Mediated Active Inference

Bo Wen

机构 * IBM T.J. Watson Research Center（IBM T.J. Watson研究院） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.AI、cs.LG

HySemRAG: A Hybrid Semantic Retrieval-Augmented Generation Framework for Automated Literature Synthesis and Methodological Gap Analysis

Alejandro Godinez

专题命中 复杂问题求解 ：self-correction(abstract)；分类 cs.AI、cs.LG

Comments 47 pages, 10 figures. Code: https://github.com/agodinezmm2007/docling_mod. Demo: https://youtu.be/ZCy5ESJ1gVE?si=K8CttwgTj7yGrWjn. ETL+multi-agent RAG framework for literature synthesis, 35.1% improvement over PDF chunking. Real application: reduced 17,400 papers to 24 relevant ones (99.86%) in 10 minutes for wastewater epidemiology review

Show, Don't Tell: Uncovering Implicit Character Portrayal using LLMs

Brandon Jaipersaud, Zining Zhu, Frank Rudzicz, Elliot Creager

专题命中 复杂问题求解 ：chain-of-thought(abstract)；分类 cs.CL、cs.AI

Journal ref NeurIPS 2024 Creativity and Generative AI Workshop