大模型推理能力

From Large to Small: Transferring CUDA Optimization Expertise via Reasoning Graph

Junfeng Gong, Zhiyi Wei, Junying Chen, Cheng Liu, Huawei Li

机构 * Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所） ； University of Chinese Academy of Sciences（中国科学院大学） ； South China University of Technology（华南理工大学） 纠错

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

MATRIX: Multimodal Agent Tuning for Robust Tool-Use Reasoning

Tajamul Ashraf, Umair Nawaz, Abdelrahman M. Shaker, Rao Anwer, Philip Torr, Fahad Shahbaz Khan, Salman Khan

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

Comments We have come across a recent approach that has not been properly attributed at the time of submission and compared in a fair setting. Therefore, we would like to withdraw the paper to address these concerns

VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents

Kangrui Wang, Pingyue Zhang, Zihan Wang, Yaning Gao, Linjie Li, Qineng Wang, Hanyang Chen, Chi Wan, Yiping Lu, Zhengyuan Yang, Lijuan Wang, Ranjay Krishna, Jiajun Wu, Li Fei-Fei, Yejin Choi, Manling Li

机构 * Northwestern University（西北大学） ； University of Washington（华盛顿大学） ； Stanford University（斯坦福大学） ； Microsoft（微软） ； University of Wisconsin-Madison（威斯康星大学麦迪逊分校） ； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

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

Comments Accepted to NeurIPS 2025

Flex-Judge: Text-Only Reasoning Unleashes Zero-Shot Multimodal Evaluators

Jongwoo Ko, Sungnyun Kim, Sungwoo Cho, Se-Young Yun

机构 * Microsoft（微软公司） ； KAIST AI（韩国科学技术院人工智能研究所） 纠错

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

Comments NeurIPS 2025

Whose Journey Matters? Investigating Identity Biases in Large Language Models (LLMs) for Travel Planning Assistance

Ruiping Ren, Yingwei, Xu, Xing Yao, Shu Cole, Haining Wang

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

Reasoning-Enhanced Large Language Models for Molecular Property Prediction

Jiaxi Zhuang, Yaorui Shi, Jue Hou, Yunong He, Mingwei Ye, Mingjun Xu, Yuming Su, Linfeng Zhang, Ying Qian, Linfeng Zhang, Guolin Ke, Hengxing Cai

机构 * DP Technology（DP技术公司） ； Shanghai Jiao Tong University（上海交通大学） ； East China Normal University（华东师范大学） 纠错

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

FinHEAR: Human Expertise and Adaptive Risk-Aware Temporal Reasoning for Financial Decision-Making

Jiaxiang Chen, Mingxi Zou, Zhuo Wang, Qifan Wang, Dongning Sun, Chi Zhang, Zenglin Xu

机构 * Fudan University（复旦大学） ； Tensorpacific ； Peng Cheng Laboratory（鹏城实验室） ； Meta AI ； Shanghai Academy of AI for Science (SAIS)（上海人工智能科学研究院） 纠错

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

An Efficient Rubric-based Generative Verifier for Search-Augmented LLMs

Linyue Ma, Yilong Xu, Xiang Long, Zhi Zheng

机构 * ModelBest Inc.（ModelBest公司） ； Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所） 纠错

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

WebThinker: Empowering Large Reasoning Models with Deep Research Capability

Xiaoxi Li, Jiajie Jin, Guanting Dong, Hongjin Qian, Yongkang Wu, Ji-Rong Wen, Yutao Zhu, Zhicheng Dou

机构 * Renmin University of China（中国人民大学） ； BAAI（北京人工智能研究院） ； Huawei Poisson Lab（华为Poisson实验室） 纠错

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

Comments Accepted by NeurIPS 2025

Spatiotemporal Forecasting as Planning: A Model-Based Reinforcement Learning Approach with Generative World Models

Hao Wu, Yuan Gao, Xingjian Shi, Shuaipeng Li, Fan Xu, Fan Zhang, Zhihong Zhu, Weiyan Wang, Xiao Luo, Kun Wang, Xian Wu, Xiaomeng Huang

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

The Cognitive Bandwidth Bottleneck: Shifting Long-Horizon Agent from Planning with Actions to Planning with Schemas

Baixuan Xu, Tianshi Zheng, Zhaowei Wang, Hong Ting Tsang, Weiqi Wang, Tianqing Fang, Yangqiu Song

机构 * The Hong Kong University of Science and Technology（香港科学与技术大学） 纠错

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

Comments 22 pages

Distilling On-device Language Models for Robot Planning with Minimal Human Intervention

Zachary Ravichandran, Ignacio Hounie, Fernando Cladera, Alejandro Ribeiro, George J. Pappas, Vijay Kumar

机构 * University of Pennsylvania（宾夕法尼亚大学） 纠错

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

Comments Accepted to the Conference on Robot Learning (CoRL) 2025

COSMIR: Chain Orchestrated Structured Memory for Iterative Reasoning over Long Context

Naman Gupta, Shreeyash Gowaikar, Arun Iyer, Kirankumar Shiragur, Ramakrishna B Bairi, Rishikesh Maurya, Ritabrata Maiti, Sankarshan Damle, Shachee Mishra Gupta

机构 * Microsoft（微软） 纠错

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

Language Agents Mirror Human Causal Reasoning Biases. How Can We Help Them Think Like Scientists?

Anthony GX-Chen, Dongyan Lin, Mandana Samiei, Doina Precup, Blake A. Richards, Rob Fergus, Kenneth Marino

机构 * New York University（纽约大学） ； McGill University（麦吉尔大学） ； Mila - Quebec Artificial Intelligence Institute（魁北克人工智能研究所） ； CIFAR Learning in Machines and Brains Program（CIFAR 机器与大脑学习计划） ； The University of Utah（犹他大学） 纠错

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

Comments Conference on Language Modelling (COLM) 2025, Camera Ready

ViReSkill: Vision-Grounded Replanning with Skill Memory for LLM-Based Planning in Lifelong Robot Learning

Tomoyuki Kagaya, Subramanian Lakshmi, Anbang Ye, Thong Jing Yuan, Jayashree Karlekar, Sugiri Pranata, Natsuki Murakami, Akira Kinose, Yang You

机构 * Panasonic Connect Co., Ltd.（松下电器（株式会社）） ； Panasonic R&D Center（松下研发中心） ； National University of Singapore（新加坡国立大学） 纠错

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

Memory Transfer Planning: LLM-driven Context-Aware Code Adaptation for Robot Manipulation

Tomoyuki Kagaya, Subramanian Lakshmi, Yuxuan Lou, Thong Jing Yuan, Jayashree Karlekar, Sugiri Pranata, Natsuki Murakami, Akira Kinose, Yang You

机构 * Panasonic Connect Co., Ltd.（松下电器（控股）公司） ； Panasonic R&D Center（松下研发中心） ； National University of Singapore（新加坡国立大学） 纠错

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

Understanding and Enhancing the Planning Capability of Language Models via Multi-Token Prediction

Qimin Zhong, Hao Liao, Siwei Wang, Mingyang Zhou, Xiaoqun Wu, Rui Mao, Wei Chen

机构 * College of Computer Science and Software Engineering, Shenzhen University（计算机科学与软件工程学院，深圳大学） ； Microsoft Research Asia（微软亚洲研究院） 纠错

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

Reasoning Isn't Enough: Examining Truth-Bias and Sycophancy in LLMs

Emilio Barkett, Olivia Long, Madhavendra Thakur

机构 * Columbia University（哥伦比亚大学） 纠错

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

Comments Published at the ICML 2025 Workshop on Models of Human Feedback for AI Alignment

VLN-Zero: Rapid Exploration and Cache-Enabled Neurosymbolic Vision-Language Planning for Zero-Shot Transfer in Robot Navigation

Neel P. Bhatt, Yunhao Yang, Rohan Siva, Pranay Samineni, Daniel Milan, Zhangyang Wang, Ufuk Topcu

机构 * University of Texas at Austin（德克萨斯大学奥斯汀分校） 纠错

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

Comments Codebase, datasets, and videos for VLN-Zero are available at: https://vln-zero.github.io/

Towards Bio-Inspired Robotic Trajectory Planning via Self-Supervised RNN

Miroslav Cibula, Kristína Malinovská, Matthias Kerzel

机构 * Faculty of Mathematics, Physics and Informatics, Comenius University Bratislava（数学、物理与信息学系，科门尼乌斯大学布拉迪斯拉发分校） ； Department of Informatics, University of Hamburg（信息学系，汉堡大学） 纠错

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

Comments 12 pages, 4 figures, 2 tables. To be published in 2025 International Conference on Artificial Neural Networks (ICANN) proceedings. This research was funded by the Horizon Europe project TERAIS, GA no. 101079338, and in part by the Slovak Grant Agency for Science (VEGA), project 1/0373/23. The code can be found at https://doi.org/10.5281/zenodo.17127997

Journal ref In Artificial Neural Networks and Machine Learning. ICANN 2025 International Workshops and Special Sessions (pp. 149--160). Springer Nature Switzerland

OnePiece: Bringing Context Engineering and Reasoning to Industrial Cascade Ranking System

Sunhao Dai, Jiakai Tang, Jiahua Wu, Kun Wang, Yuxuan Zhu, Bingjun Chen, Bangyang Hong, Yu Zhao, Cong Fu, Kangle Wu, Yabo Ni, Anxiang Zeng, Wenjie Wang, Xu Chen, Jun Xu, See-Kiong Ng

机构 * Renmin University of China（中国人民大学） ； Shopee ； University of Science and Technology of China（中国科学技术大学） ； National University of Singapore（新加坡国立大学） 纠错

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

Comments OnePiece Technical Report; Applied in Shopee

Dynamic Speculative Agent Planning

Yilin Guan, Qingfeng Lan, Sun Fei, Dujian Ding, Devang Acharya, Chi Wang, William Yang Wang, Wenyue Hua

机构 * Johns Hopkins University（约翰霍普金斯大学） ； University of Alberta（阿尔伯塔大学） ； University of British Columbia（不列颠哥伦比亚大学） ； Avey Research Center（艾维研究中心） ； Google DeepMind（谷歌DeepMind） ； University of California（加州大学） 纠错

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

Comments 19 pages, 11 figures

InteGround: On the Evaluation of Verification and Retrieval Planning in Integrative Grounding

Cheng Jiayang, Qianqian Zhuang, Haoran Li, Chunkit Chan, Xin Liu, Lin Qiu, Yangqiu Song

机构 * The Hong Kong University of Science and Technology（香港科学与技术大学） ； Shanghai Jiaotong University（上海交通大学） 纠错

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

Comments Accepted to EMNLP 2025 Findings

A Data-Driven Discretized CS:GO Simulation Environment to Facilitate Strategic Multi-Agent Planning Research

Yunzhe Wang, Volkan Ustun, Chris McGroarty

机构 * USC Institute for Creative Technologies（USC创意技术研究所） ； Dept. of Computer Science University of Southern California（计算机科学系大学南加州大学） ； U.S. Army Combat Capabilities Development Command（美国陆军作战能力发展指挥部） 纠错

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

Comments Accepted at the Winter Simulation Conference 2025, December, Seattle USA

Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning

Yaorui Shi, Sihang Li, Chang Wu, Zhiyuan Liu, Junfeng Fang, Hengxing Cai, An Zhang, Xiang Wang

机构 * University of Science and Technology of China（中国科学技术大学） ； National University of Singapore（新加坡国立大学） ； DP Technology（DP技术） 纠错

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

A learning-driven automatic planning framework for proton PBS treatments of H&N cancers

Qingqing Wang, Liqiang Xiao, Chang Chang

机构 * Department of Radiation Medicine and Applied Sciences, University of California at San Diego（放射医学与应用科学系，加州大学圣地亚哥分校） ； Amazon Inc.（亚马逊公司） ； California Protons Cancer Therapy Center（加利福尼亚质子癌症治疗中心） 纠错

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

Comments 27 pages, 4 figures

SFR-DeepResearch: Towards Effective Reinforcement Learning for Autonomously Reasoning Single Agents

Xuan-Phi Nguyen, Shrey Pandit, Revanth Gangi Reddy, Austin Xu, Silvio Savarese, Caiming Xiong, Shafiq Joty

机构 * Salesforce AI Research（Salesforce AI研究院） 纠错

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

Comments Technical Report

Scaling Laws of Motion Forecasting and Planning -- Technical Report

Mustafa Baniodeh, Kratarth Goel, Scott Ettinger, Carlos Fuertes, Ari Seff, Tim Shen, Cole Gulino, Chenjie Yang, Ghassen Jerfel, Dokook Choe, Rui Wang, Benjamin Charrow, Vinutha Kallem, Sergio Casas, Rami Al-Rfou, Benjamin Sapp, Dragomir Anguelov

机构 * Waymo LLC（Waymo公司） 纠错

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

Efficient Virtuoso: A Latent Diffusion Transformer Model for Goal-Conditioned Trajectory Planning

Antonio Guillen-Perez

机构 * Independent Researcher（独立研究者） 纠错

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

Intelligent Assistants for the Semiconductor Failure Analysis with LLM-Based Planning Agents

Aline Dobrovsky, Konstantin Schekotihin, Christian Burmer

机构 * University of the Bundeswehr Munich（联邦国防军大学慕尼黑） ； University Klagenfurt（克雷格弗尔特大学） ； Infineon Technologies AG（英飞凌科技） 纠错

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

Comments This technical report provides evaluation details of the experiments presented in the paper accepted to ISTFA 2025