大模型推理能力

PRIMT: Preference-based Reinforcement Learning with Multimodal Feedback and Trajectory Synthesis from Foundation Models

基于偏好强化学习的多模态反馈与轨迹合成：从基础模型出发

Ruiqi Wang, Dezhong Zhao, Ziqin Yuan, Tianyu Shao, Guohua Chen, Dominic Kao, Sungeun Hong, Byung-Cheol Min

机构 * Purdue University（普渡大学） ； Beijing University of Chemical Technology（北京化工大学） ； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； Sungkyunkwan University（成均馆大学） ； Indiana University Bloomington（印第安纳大学布卢明顿分校） 纠错

专题命中 逻辑推理 ：reasoning(abstract)

AI总结 PRIMT通过多模态反馈和轨迹合成，利用基础模型解决偏好强化学习中的查询模糊性和信用分配问题，提升机器人复杂行为的学习效率。

Encoding argumentation frameworks with set attackers to propositional logic systems

将带有集合攻击者的论证框架编码到命题逻辑系统中

Shuai Tang, Jiachao Wu, Ning Zhou

专题命中 逻辑推理 ：reasoning(abstract)

AI总结 本文提出将带有集合攻击者的论证框架编码到命题逻辑系统中，统一了高阶AFs和SETAFs，为AI和多智能体系统提供逻辑基础。

Comments 51 pages

VULSOLVER: Vulnerability Detection via LLM-Driven Constraint Solving

通过LLM驱动的约束求解进行漏洞检测：VULSOLVER

Xiang Li, Yueci Su, Jiahao Liu, Zhiwei Lin, Yuebing Hou, Peiming Gao, Yuanchao Zhang

专题命中 逻辑推理 ：reasoning(abstract)

AI总结 VULSOLVER通过LLM驱动的约束求解方法，实现高精度漏洞检测，准确率达97.85%

RB-FT: Rationale-Bootstrapped Fine-Tuning for Video Classification

RB-FT：基于理由的视频分类微调

Meilong Xu, Di Fu, Jiaxing Zhang, Gong Yu, Jiayu Zheng, Xiaoling Hu, Dongdi Zhao, Feiyang Li, Chao Chen, Yong Cao

机构 * Stony Brook University（石溪大学） ； ByteDance Inc.（字节跳动公司） ； Harvard Medical School（哈佛医学院） 纠错

专题命中 逻辑推理 ：reasoning(abstract)

AI总结 RB-FT通过自动生成的理由提升视频分类性能，无需额外标注，有效提升模型对领域特定视频内容的理解能力。

Comments 11 pages, 2 figures

Two Agents, One Prompt, and Your Weight

Elchanan Mossel, Amnon Schreiber

专题命中 逻辑推理 ：reasoning(abstract)

Comments Typos corrected

Revealing Adversarial Smart Contracts through Semantic Interpretation and Uncertainty Estimation

Yating Liu, Xing Su, Hao Wu, Sijin Li, Yuxi Cheng, Fengyuan Xu, Sheng Zhong

专题命中 逻辑推理 ：reasoning(abstract)

Towards Assume-Guarantee Verification of Abilities in Stochastic Multi-Agent Systems

Wojciech Jamroga, Damian Kurpiewski, Łukasz Mikulski

专题命中 逻辑推理 ：reasoning(abstract)

Comments technical report, work in progress

ReGen: Generative Robot Simulation via Inverse Design

Phat Nguyen, Tsun-Hsuan Wang, Zhang-Wei Hong, Erfan Aasi, Andrew Silva, Guy Rosman, Sertac Karaman, Daniela Rus

机构 * Massachusetts Institute of Technology（麻省理工学院） ； Toyota Research Institute（丰田研究机构） 纠错

专题命中 逻辑推理 ：reasoning(abstract)

LLM-Driven Adaptive Source-Sink Identification and False Positive Mitigation for Static Analysis

Shiyin Lin

专题命中 逻辑推理 ：reasoning(abstract)

PROPEX-RAG: Enhanced GraphRAG using Prompt-Driven Prompt Execution

Tejas Sarnaik, Manan Shah, Ravi Hegde

机构 * Indian Institute of Technology, Gandhinagar, Gujarat, India（印度理工学院冈丁加尔分校，古吉拉特邦，印度） 纠错

专题命中 逻辑推理 ：reasoning(abstract)

Comments Accepted in PReMI 2025

Stop Reducing Responsibility in LLM-Powered Multi-Agent Systems to Local Alignment

Jinwei Hu, Yi Dong, Shuang Ao, Zhuoyun Li, Boxuan Wang, Lokesh Singh, Guangliang Cheng, Sarvapali D. Ramchurn, Xiaowei Huang

专题命中 逻辑推理 ：reasoning(abstract)

Comments Updated manuscript of our previous version (arXiv:2502.01714). Under review

Efficient Symbolic Computation via Hash Consing

Bowen Zhu, Aayush Sabharwal, Songchen Tan, Yingbo Ma, Alan Edelman, Christopher Rackauckas

专题命中 逻辑推理 ：reasoning(abstract)

Frequency Domain Unlocks New Perspectives for Abdominal Medical Image Segmentation

Kai Han, Siqi Ma, Chengxuan Qian, Jun Chen, Chongwen Lyu, Yuqing Song, Zhe Liu

机构 * School of Computer Science and Communication Engineering, Jiangsu University（江苏大学计算机科学与通信工程学院） 纠错

专题命中 逻辑推理 ：planning(abstract)

The Mechanical Yes-Man: Emancipatory AI Pedagogy in Higher Education

Linda Rocco

专题命中 逻辑推理 ：reasoning(abstract)

Comments 7 pages, 2 figures. To be published in Concreta journal n. 26, 2025

Journal ref Concreta n. 26 (2025)

LogPilot: Intent-aware and Scalable Alert Diagnosis for Large-scale Online Service Systems

Zhihan Jiang, Jinyang Liu, Yichen Li, Haiyu Huang, Xiao He, Tieying Zhang, Jianjun Chen, Yi Li, Rui Shi, Michael R. Lyu

专题命中 逻辑推理 ：reasoning(abstract)

Comments Accepted by the 40th IEEE/ACM International Conference on Automated Software Engineering (ASE 2025)

Finetuning Large Language Model as an Effective Symbolic Regressor

Yingfan Hua, Ruikun Li, Jun Yao, Guohang Zhuang, Shixiang Tang, Bin Liu, Wanli Ouyang, Yan Lu

专题命中 逻辑推理 ：reasoning(abstract)

Lang2Morph: Language-Driven Morphological Design of Robotic Hands

Yanyuan Qiao, Kieran Gilday, Yutong Xie, Josie Hughes

机构 * CREATE Lab, Swiss Federal Institute of Technology Lausanne (EPFL)（瑞士联邦理工学院洛桑分校CREATE实验室） ； Computer Vision Department, Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)（马尔代夫比兹莱浙江大学人工智能大学计算机视觉部门） 纠错

专题命中 逻辑推理 ：reasoning(abstract)

SLICET5: Static Program Slicing using Language Models with Copy Mechanism and Constrained Decoding

Pengfei He, Shaowei Wang, Tse-Hsun Chen

专题命中 逻辑推理 ：reasoning(abstract)

Comments 3 tables, 6 Figures, 12 pages

MORepair: Teaching LLMs to Repair Code via Multi-Objective Fine-tuning

Boyang Yang, Haoye Tian, Jiadong Ren, Hongyu Zhang, Jacques Klein, Tegawendé F. Bissyandé, Claire Le Goues, Shunfu Jin

专题命中 逻辑推理 ：CoT(abstract)

Journal ref ACM Transactions on Software Engineering and Methodology, 2025

Shift-Left Techniques in Electronic Design Automation: A Survey

Xinyue Wu, Zixuan Li, Fan Hu, Ting Lin, Xiaotian Zhao, Runxi Wang, Xinfei Guo

专题命中 逻辑推理 ：planning(abstract)

Constraint-Compliant Network Optimization through Large Language Models

Youngjin Song, Wookjin Lee, Hong Ki Kim, Sang Hyun Lee

专题命中 逻辑推理 ：reasoning(abstract)

Presolving Convexified Optimal Power Flow with Mixtures of Gradient Experts

Shourya Bose, Kejun Chen, Yu Zhang

专题命中 逻辑推理 ：planning(abstract)

Comments Accepted in "Energy and AI"

WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent

Xinyu Geng, Peng Xia, Zhen Zhang, Xinyu Wang, Qiuchen Wang, Ruixue Ding, Chenxi Wang, Jialong Wu, Yida Zhao, Kuan Li, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou

专题命中 逻辑推理 ：reasoning(abstract)

QueryGenie: Making LLM-Based Database Querying Transparent and Controllable

Longfei Chen, Shenghan Gao, Shiwei Wang, Ken Lin, Yun Wang, Quan Li

专题命中 逻辑推理 ：reasoning(abstract)

Comments Accepted by The 38th Annual ACM Symposium on User Interface Software and Technology (UIST Adjunct '25), September 28-October 1, 2025, Busan, Republic of Korea

In-Context Iterative Policy Improvement for Dynamic Manipulation

Mark Van der Merwe, Devesh Jha

机构 * Department of Robotics, University of Michigan（机器人学系，密歇根大学） ； MERL 纠错

专题命中 逻辑推理 ：reasoning(abstract)

Comments 14 pages. Accepted at CoRL 2025

A Framework for FAIR and CLEAR Ecological Data and Knowledge: Semantic Units for Synthesis and Causal Modelling

Lars Vogt, Birgitta König-Ries, Tim Alamenciak, Joshua I. Brian, Carlos Alberto Arnillas, Lotte Korell, Robert Frühstückl, Tina Heger

专题命中 逻辑推理 ：reasoning(abstract)

SHIELDA: Structured Handling of Exceptions in LLM-Driven Agentic Workflows

Jingwen Zhou, Jieshan Chen, Qinghua Lu, Dehai Zhao, Liming Zhu

专题命中 逻辑推理 ：reasoning(abstract)

Solving Zero-Shot 3D Visual Grounding as Constraint Satisfaction Problems

Qihao Yuan, Kailai Li, Jiaming Zhang

机构 * Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen（格罗宁根大学伯努利学院） ； Computer Vision for Human-Computer Interaction Lab (cv:hci), Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院人机交互计算机视觉实验室） 纠错

专题命中 逻辑推理 ：reasoning(abstract)

Improved Obstacle Avoidance for Autonomous Robots with ORCA-FLC

Justin London

机构 * Dept. of Electrical Engineering and Computer Science（电气工程与计算机科学系） ； University of North Dakota（北达科他大学） 纠错

专题命中 逻辑推理 ：planning(abstract)

AquaChat++: LLM-Assisted Multi-ROV Inspection for Aquaculture Net Pens with Integrated Battery Management and Thruster Fault Tolerance

Abdelhaleem Saad, Waseem Akram, Irfan Hussain

机构 * Khalifa University Center for Autonomous Robotic Systems (KUCARS), Khalifa University, United Arab Emirates（卡利法大学自主机器人系统中心（KUCARS）、卡利法大学、阿拉伯联合酋长国） 纠错

专题命中 逻辑推理 ：planning(abstract)