大模型推理能力 - arXivDaily 专题

2510.13095 2025-10-22 cs.IR 75%

Retrieval-in-the-Chain: Bootstrapping Large Language Models for Generative Retrieval

Yingchen Zhang, Ruqing Zhang, Jiafeng Guo, Wenjun Peng, Sen Li, Fuyu Lv

专题命中规划推理：reasoning(abstract)；chain-of-thought(abstract)；CoT(abstract)

2503.23204 2025-10-22 cs.CL cs.AI cs.LG 75%

The Challenge of Achieving Attributability in Multilingual Table-to-Text Generation with Question-Answer Blueprints

Aden Haussmann

机构 * The University of Edinburgh（爱丁堡大学）

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

2509.25810 2025-10-14 cs.LG cs.AI cs.CL stat.ML 75%

Learning to Reason as Action Abstractions with Scalable Mid-Training RL

Shenao Zhang, Donghan Yu, Yihao Feng, Bowen Jin, Zhaoran Wang, John Peebles, Zirui Wang

机构 * Apple（苹果公司）； Northwestern University（西北大学）

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

2505.15182 2025-09-30 cs.CL cs.AI cs.LG 75%

ReflAct: World-Grounded Decision Making in LLM Agents via Goal-State Reflection

Jeonghye Kim, Sojeong Rhee, Minbeom Kim, Dohyung Kim, Sangmook Lee, Youngchul Sung, Kyomin Jung

机构 * KAIST（韩国科学技术院）； Seoul National University（首尔国立大学）

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

Comments Accepted to EMNLP 2025 (Main Conference)

2405.14314 2025-09-30 cs.AI cs.CL cs.LG cs.MA cs.RO 75%

Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration

Yang Zhang, Shixin Yang, Chenjia Bai, Fei Wu, Xiu Li, Zhen Wang, Xuelong Li

机构 * Tsinghua University（清华大学）； Northwestern Polytechnical University（西北工业大学）； Institute of Artificial Intelligence (TeleAI)（人工智能研究所）； China Telecom（中国电信）； Zhejiang University（浙江大学）； Shenzhen Research Institute of Northwestern Polytechnical University（西北工业大学深圳研究院）

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

Comments accepted by ACL'2025

2509.21482 2025-09-29 cs.CL cs.AI cs.LG 75%

Learning to Reason with Mixture of Tokens

Adit Jain, Brendan Rappazzo

机构 * Machine Learning Research, Morgan Stanley, New York, NY（机器学习研究部，摩根士丹利，纽约，纽约）； School of Electrical and Computer Engineering, Cornell University, Ithaca, NY（电气与计算机工程学院，康奈尔大学，伊萨卡，纽约）

专题命中规划推理：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 30 page

2509.09674 2025-09-12 cs.RO cs.AI cs.CL cs.LG 75%

SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

Haozhan Li, Yuxin Zuo, Jiale Yu, Yuhao Zhang, Zhaohui Yang, Kaiyan Zhang, Xuekai Zhu, Yuchen Zhang, Tianxing Chen, Ganqu Cui, Dehui Wang, Dingxiang Luo, Yuchen Fan, Youbang Sun, Jia Zeng, Jiangmiao Pang, Shanghang Zhang, Yu Wang, Yao Mu, Bowen Zhou, Ning Ding

机构 * Shanghai Jiao Tong University（上海交通大学）； Peking University（北京大学）； The University of Hong Kong（香港大学）； Shanghai AI Lab（上海人工智能实验室）

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

2502.04227 2025-09-12 cs.CR 75%

Can LLMs Hack Enterprise Networks? Autonomous Assumed Breach Penetration-Testing Active Directory Networks

Andreas Happe, Jürgen Cito

专题命中规划推理：reasoning(abstract)；planning(abstract)；self-correction(abstract)

2507.05259 2025-07-08 cs.CV 75%

Beyond Simple Edits: X-Planner for Complex Instruction-Based Image Editing

Chun-Hsiao Yeh, Yilin Wang, Nanxuan Zhao, Richard Zhang, Yuheng Li, Yi Ma, Krishna Kumar Singh

机构 * UC Berkeley（伯克利大学）； HKU（香港大学）； Adobe（Adobe公司）

专题命中规划推理：reasoning(abstract)；chain-of-thought(abstract)；planning(abstract)

Comments Project page: https://danielchyeh.github.io/x-planner/

2507.01599 2025-07-03 cs.DB cs.AI cs.CL cs.LG 75%

Data Agent: A Holistic Architecture for Orchestrating Data+AI Ecosystems

Zhaoyan Sun, Jiayi Wang, Xinyang Zhao, Jiachi Wang, Guoliang Li

机构 * Department of Computer Science, Tsinghua University（计算机科学系，清华大学）

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

2408.14505 2025-06-24 cs.LG cs.AI cs.CL 75%

RePST: Language Model Empowered Spatio-Temporal Forecasting via Semantic-Oriented Reprogramming

Hao Wang, Jindong Han, Wei Fan, Leilei Sun, Hao Liu

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））； The Hong Kong University of Science and Technology（香港科学与技术大学）； Shandong University（山东大学）； Oxford University（牛津大学）； Beihang University（北航大学）

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

2505.15517 2025-06-23 cs.RO cs.AI cs.CL cs.LG 75%

Robo2VLM: Visual Question Answering from Large-Scale In-the-Wild Robot Manipulation Datasets

Kaiyuan Chen, Shuangyu Xie, Zehan Ma, Pannag R Sanketi, Ken Goldberg

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

2505.23450 2025-06-12 cs.RO 75%

Agentic Robot: A Brain-Inspired Framework for Vision-Language-Action Models in Embodied Agents

Zhejian Yang, Yongchao Chen, Xueyang Zhou, Jiangyue Yan, Dingjie Song, Yinuo Liu, Yuting Li, Yu Zhang, Pan Zhou, Hechang Chen, Lichao Sun

机构 * Jilin University（吉林大学）； Harvard University（哈佛大学）； Massachusetts Institute of Technology（麻省理工学院）； Huazhong University of Science and Technology（华中科技大学）； Southern University of Science and Technology（南方科技大学）； Lehigh University（莱斯大学）； Shanghai Jiao Tong University（上海交通大学）

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

Comments 20 pages, 8 figures

2503.02197 2025-06-06 cs.CL cs.AI cs.LG 75%

ATLaS: Agent Tuning via Learning Critical Steps

Zhixun Chen, Ming Li, Yuxuan Huang, Yali Du, Meng Fang, Tianyi Zhou

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

Comments ACL2025, Camera-ready

2506.04252 2025-06-06 cs.AI cs.CL cs.LG 75%

A Graph-Retrieval-Augmented Generation Framework Enhances Decision-Making in the Circular Economy

Yang Zhao, Chengxiao Dai, Dusit Niyato, Chuan Fu Tan, Keyi Xiang, Yueyang Wang, Zhiquan Yeo, Daren Tan Zong Loong, Jonathan Low Zhaozhi, Eugene H. Z. HO

机构 * Singapore Institute of Manufacturing Technology (SIMTech)（新加坡制造技术研究所）； Agency for Science, Technology and Research (A*STAR)（科学、技术及研究局）； The University of Sydney（悉尼大学）； Nanyang Technological University（南洋理工大学）； National University of Singapore（国立新加坡大学）

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

2505.22290 2025-05-29 cs.AI cs.CL cs.LG 75%

Rethinking the Unsolvable: When In-Context Search Meets Test-Time Scaling

Fanzeng Xia, Yidong Luo, Tinko Sebastian Bartels, Yaqi Xu, Tongxin Li

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

2505.19964 2025-05-27 cs.LG cs.AI cs.CL cs.GT 75%

The Limits of Preference Data for Post-Training

Eric Zhao, Jessica Dai, Pranjal Awasthi

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

2501.12432 2025-05-27 cs.LG cs.AI cs.CL 75%

Divide-Then-Aggregate: An Efficient Tool Learning Method via Parallel Tool Invocation

Dongsheng Zhu, Weixian Shi, Zhengliang Shi, Zhaochun Ren, Shuaiqiang Wang, Lingyong Yan, Dawei Yin

机构 * Baidu Inc.（百度公司）； Shandong University（山东大学）； Leiden University（莱顿大学）

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

Comments Accepted to ACL 2025

2505.15332 2025-05-22 cs.CV 75%

Towards Zero-Shot Differential Morphing Attack Detection with Multimodal Large Language Models

Ria Shekhawat, Hailin Li, Raghavendra Ramachandra, Sushma Venkatesh

机构 * Norwegian University of Science and Technology (NTNU)（挪威科学与技术大学）； MOBAI AS（MOBAI公司）

专题命中规划推理：reasoning(abstract)；chain-of-thought(abstract)；CoT(abstract)

Comments Accepted at IEEE International Conference on Automatic Face and Gesture Recognition (FG 2025)

2504.11336 2025-04-25 cs.LG cs.AI cs.CL 75%

Looking beyond the next token

Abitha Thankaraj, Yiding Jiang, J. Zico Kolter, Yonatan Bisk

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

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

2504.06593 2025-04-10 cs.RO cs.HC 75%

A Multi-Modal Interaction Framework for Efficient Human-Robot Collaborative Shelf Picking

Abhinav Pathak, Kalaichelvi Venkatesan, Tarek Taha, Rajkumar Muthusamy

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

2410.02810 2025-04-09 cs.AI cs.CL cs.LG 75%

StateAct: Enhancing LLM Base Agents via Self-prompting and State-tracking

Nikolai Rozanov, Marek Rei

专题命中规划推理：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 9 pages, 5 pages appendix, 7 figures, 5 tables

2503.00179 2025-03-04 cs.IR cs.AI cs.CL cs.LG 75%

Zero-Shot and Efficient Clarification Need Prediction in Conversational Search

Lili Lu, Chuan Meng, Federico Ravenda, Mohammad Aliannejadi, Fabio Crestani

专题命中规划推理：chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL、cs.AI、cs.LG

2502.15990 2025-02-27 cs.IR cs.AI cs.CL cs.LG 75%

Automated Query-Product Relevance Labeling using Large Language Models for E-commerce Search

Jayant Sachdev, Sean D Rosario, Abhijeet Phatak, He Wen, Swati Kirti, Chittaranjan Tripathy

专题命中规划推理：chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL、cs.AI、cs.LG

2502.15214 2025-02-24 cs.LG cs.AI cs.CL 75%

The Evolving Landscape of LLM- and VLM-Integrated Reinforcement Learning

Sheila Schoepp, Masoud Jafaripour, Yingyue Cao, Tianpei Yang, Fatemeh Abdollahi, Shadan Golestan, Zahin Sufiyan, Osmar R. Zaiane, Matthew E. Taylor

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

Comments 9 pages, 4 figures

2502.06589 2025-02-11 cs.CL cs.AI cs.LG 75%

Hephaestus: Improving Fundamental Agent Capabilities of Large Language Models through Continual Pre-Training

Yuchen Zhuang, Jingfeng Yang, Haoming Jiang, Xin Liu, Kewei Cheng, Sanket Lokegaonkar, Yifan Gao, Qing Ping, Tianyi Liu, Binxuan Huang, Zheng Li, Zhengyang Wang, Pei Chen, Ruijie Wang, Rongzhi Zhang, Nasser Zalmout, Priyanka Nigam, Bing Yin, Chao Zhang

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

Comments Accepted to NAACL 2025 main conference

2501.16411 2025-01-30 cs.CV cs.AI cs.CL cs.LG cs.RO 75%

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Wei Chow, Jiageng Mao, Boyi Li, Daniel Seita, Vitor Guizilini, Yue Wang

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

Comments ICLR 2025. Project page: https://physbench.github.io/ Dataset: https://huggingface.co/datasets/USC-GVL/PhysBench

2408.12574 2025-01-24 cs.AI cs.CL cs.CV cs.LG 75%

MuMA-ToM: Multi-modal Multi-Agent Theory of Mind

Haojun Shi, Suyu Ye, Xinyu Fang, Chuanyang Jin, Leyla Isik, Yen-Ling Kuo, Tianmin Shu

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

Comments AAAI-25 (Oral). Project website: https://scai.cs.jhu.edu/projects/MuMA-ToM/ Code: https://github.com/SCAI-JHU/MuMA-ToM

2412.21154 2024-12-31 cs.AI cs.CL cs.LG 75%

Aviary: training language agents on challenging scientific tasks

Siddharth Narayanan, James D. Braza, Ryan-Rhys Griffiths, Manu Ponnapati, Albert Bou, Jon Laurent, Ori Kabeli, Geemi Wellawatte, Sam Cox, Samuel G. Rodriques, Andrew D. White

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

2412.18770 2024-12-30 cs.IR 75%

Attack-in-the-Chain: Bootstrapping Large Language Models for Attacks Against Black-box Neural Ranking Models

Yu-An Liu, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke, Yixing Fan, Xueqi Cheng

专题命中规划推理：reasoning(abstract)；chain-of-thought(abstract)；CoT(abstract)

Comments Accepted by AAAI25

1. 规划推理 11047 篇

Retrieval-in-the-Chain: Bootstrapping Large Language Models for Generative Retrieval

The Challenge of Achieving Attributability in Multilingual Table-to-Text Generation with Question-Answer Blueprints

Learning to Reason as Action Abstractions with Scalable Mid-Training RL

ReflAct: World-Grounded Decision Making in LLM Agents via Goal-State Reflection

Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration

Learning to Reason with Mixture of Tokens

SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

Can LLMs Hack Enterprise Networks? Autonomous Assumed Breach Penetration-Testing Active Directory Networks

Beyond Simple Edits: X-Planner for Complex Instruction-Based Image Editing

Data Agent: A Holistic Architecture for Orchestrating Data+AI Ecosystems

RePST: Language Model Empowered Spatio-Temporal Forecasting via Semantic-Oriented Reprogramming

Robo2VLM: Visual Question Answering from Large-Scale In-the-Wild Robot Manipulation Datasets

Agentic Robot: A Brain-Inspired Framework for Vision-Language-Action Models in Embodied Agents

ATLaS: Agent Tuning via Learning Critical Steps

A Graph-Retrieval-Augmented Generation Framework Enhances Decision-Making in the Circular Economy

Rethinking the Unsolvable: When In-Context Search Meets Test-Time Scaling

The Limits of Preference Data for Post-Training

Divide-Then-Aggregate: An Efficient Tool Learning Method via Parallel Tool Invocation

Towards Zero-Shot Differential Morphing Attack Detection with Multimodal Large Language Models

Looking beyond the next token

A Multi-Modal Interaction Framework for Efficient Human-Robot Collaborative Shelf Picking

StateAct: Enhancing LLM Base Agents via Self-prompting and State-tracking

Zero-Shot and Efficient Clarification Need Prediction in Conversational Search

Automated Query-Product Relevance Labeling using Large Language Models for E-commerce Search

The Evolving Landscape of LLM- and VLM-Integrated Reinforcement Learning

Hephaestus: Improving Fundamental Agent Capabilities of Large Language Models through Continual Pre-Training

PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

MuMA-ToM: Multi-modal Multi-Agent Theory of Mind

Aviary: training language agents on challenging scientific tasks

Attack-in-the-Chain: Bootstrapping Large Language Models for Attacks Against Black-box Neural Ranking Models