AI Agent

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search

Zeren Luo, Zifan Peng, Yule Liu, Zhen Sun, Mingchen Li, Jingyi Zheng, Xinlei He

专题命中 工具调用 ：agent(abstract)；分类 cs.AI、cs.LG

Traceable LLM-based validation of statements in knowledge graphs

Daniel Adam, Tomáš Kliegr

专题命中 工具调用 ：workflow(abstract)；分类 cs.AI、cs.LG

Journal ref Information Processing & Management 62 (2025): 104128

LLM-First Search: Self-Guided Exploration of the Solution Space

Nathan Herr, Tim Rocktäschel, Roberta Raileanu

专题命中 工具调用 ：planning(abstract)；分类 cs.AI、cs.CL

Comments 9 main pages, 2 figures, 2 tables, 36 appendix pages

Standard Benchmarks Fail -- Auditing LLM Agents in Finance Must Prioritize Risk

Zichen Chen, Jiaao Chen, Jianda Chen, Misha Sra

专题命中 工具调用 ：workflow(abstract)；分类 cs.AI、cs.CL

Comments 46 pages, 2 figures, 2 tables

syftr: Pareto-Optimal Generative AI

Alexander Conway, Debadeepta Dey, Stefan Hackmann, Matthew Hausknecht, Michael Schmidt, Mark Steadman, Nick Volynets

机构 * DataRobot 纠错

专题命中 工具调用 ：agentic(abstract)；分类 cs.AI、cs.LG

Comments International Conference on Automated Machine Learning (AutoML) 2025

Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models

Zhengliang Shi, Yuhan Wang, Lingyong Yan, Pengjie Ren, Shuaiqiang Wang, Dawei Yin, Zhaochun Ren

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

专题命中 工具调用 ：tool-use(abstract)；分类 cs.AI、cs.CL

Comments ACL 2025. Code: https://github.com/mangopy/tool-retrieval-benchmark

ReGUIDE: Data Efficient GUI Grounding via Spatial Reasoning and Search

Hyunseok Lee, Jeonghoon Kim, Beomjun Kim, Jihoon Tack, Chansong Jo, Jaehong Lee, Cheonbok Park, Sookyo In, Jinwoo Shin, Kang Min Yoo

机构 * KAIST（韩国科学技术院） ； NAVER Cloud（NAVER云） 纠错

专题命中 工具调用 ：autonomous agent(abstract)；分类 cs.CL、cs.LG

An Empirical Study on Reinforcement Learning for Reasoning-Search Interleaved LLM Agents

Bowen Jin, Jinsung Yoon, Priyanka Kargupta, Sercan O. Arik, Jiawei Han

专题命中 工具调用 ：agent(abstract)；分类 cs.AI、cs.CL

Comments 22 pages

NExT-Search: Rebuilding User Feedback Ecosystem for Generative AI Search

Sunhao Dai, Wenjie Wang, Liang Pang, Jun Xu, See-Kiong Ng, Ji-Rong Wen, Tat-Seng Chua

机构 * Gaoling School of Artificial Intelligence（光明人工智能学院） ； Renmin University of China（中国人民大学） ； University of Science and Technology of China（中国科学技术大学） ； CAS Key Laboratory of AI Safety（中国科学院人工智能安全重点实验室） ； Institute of Computing Technology（计算技术研究所） ； Chinese Academy of Sciences（中国科学院） ； National University of Singapore（新加坡国立大学） 纠错

专题命中 工具调用 ：agent(abstract)；分类 cs.AI、cs.CL

Comments SIGIR 2025 Perspective Paper

Guided Search Strategies in Non-Serializable Environments with Applications to Software Engineering Agents

Karina Zainullina, Alexander Golubev, Maria Trofimova, Sergei Polezhaev, Ibragim Badertdinov, Daria Litvintseva, Simon Karasik, Filipp Fisin, Sergei Skvortsov, Maksim Nekrashevich, Anton Shevtsov, Boris Yangel

专题命中 工具调用 ：agentic(abstract)；分类 cs.CL、cs.SE

Comments ICML

Automating Intervention Discovery from Scientific Literature: A Progressive Ontology Prompting and Dual-LLM Framework

Yuting Hu, Dancheng Liu, Qingyun Wang, Charles Yu, Chenhui Xu, Qingxiao Zheng, Heng Ji, Jinjun Xiong

机构 * University at Buffalo（布法罗大学） ； University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

专题命中 工具调用 ：agent(abstract)；分类 cs.AI、cs.CL

Comments Accepted by IJCAI2025

An approach based on class activation maps for investigating the effects of data augmentation on neural networks for image classification

Lucas M. Dorneles, Luan Fonseca Garcia, Joel Luís Carbonera

机构 * Department of Computer Science（计算机科学系） ； Federal University of Rio Grande do Sul（里约格兰德杜斯尔大学） 纠错

专题命中 工具调用 ：tool use(abstract)；分类 cs.AI、cs.LG

Monte Carlo Beam Search for Actor-Critic Reinforcement Learning in Continuous Control

Hazim Alzorgan, Abolfazl Razi

机构 * School of Computing, Clemson University（计算学院，克莱姆森大学） 纠错

专题命中 工具调用 ：agent(abstract)；分类 cs.AI、cs.LG

Enhancing Reinforcement Learning for the Floorplanning of Analog ICs with Beam Search

Sandro Junior Della Rovere, Davide Basso, Luca Bortolussi, Mirjana Videnovic-Misic, Husni Habal

机构 * University of Trieste（特里埃斯特大学） ； Infineon Technologies AT（英飞凌科技AT） ； Infineon Technologies AG（英飞凌科技AG） 纠错

专题命中 工具调用 ：agent(abstract)；分类 cs.AI、cs.LG

Comments Published in Proceedings of the 21st International Conference on Synthesis, Modeling, Analysis and Simulation Methods, and Applications to Circuit Design (SMACD 2025). 4 pages, 3 figures

Enhancing Differential Testing With LLMs For Testing Deep Learning Libraries

Meiziniu Li, Dongze Li, Jianmeng Liu, Jialun Cao, Yongqiang Tian, Shing-Chi Cheung

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

专题命中 工具调用 ：workflow(abstract)；分类 cs.AI、cs.SE

Comments This work has been accepted by ACM TOSEM. Manuscript under final preparation

DocSpiral: A Platform for Integrated Assistive Document Annotation through Human-in-the-Spiral

Qiang Sun, Sirui Li, Tingting Bi, Du Huynh, Mark Reynolds, Yuanyi Luo, Wei Liu

机构 * The University of Western Australia（西澳大学） ； Murdoch University（莫纳什大学） ； The University of Melbourne（墨尔本大学） ； Sinograin Chengdu Storage Research Institute Co., Ltd.（中粮成都仓储研究院有限公司） 纠错

专题命中 工具调用 ：workflow(abstract)；分类 cs.AI、cs.SE

Learning Efficiency Meets Symmetry Breaking

Yingbin Bai, Sylvie Thiebaux, Felipe Trevizan

专题命中 工具调用 ：planning(abstract)；分类 cs.AI、cs.LG

RILe: Reinforced Imitation Learning

Mert Albaba, Sammy Christen, Thomas Langarek, Christoph Gebhardt, Otmar Hilliges, Michael J. Black

机构 * ETH Zürich（苏黎世联邦理工学院） ； Max Planck Institute for Intelligent Systems（智能系统马克斯·普朗克研究所） 纠错

专题命中 工具调用 ：agent(abstract)；分类 cs.AI、cs.LG

MCP Safety Audit: LLMs with the Model Context Protocol Allow Major Security Exploits

Brandon Radosevich, John Halloran

专题命中 工具调用 ：agentic(abstract)；分类 cs.AI、cs.LG

Comments 27 pages, 21 figures, and 2 Tables. Cleans up the TeX source

Hyperparameter Optimisation with Practical Interpretability and Explanation Methods in Probabilistic Curriculum Learning

Llewyn Salt, Marcus Gallagher

专题命中 工具调用 ：agent(abstract)；分类 cs.AI、cs.LG

ER-RAG: Enhance RAG with ER-Based Unified Modeling of Heterogeneous Data Sources

Yikuan Xia, Jiazun Chen, Yirui Zhan, Suifeng Zhao, Weipeng Jiang, Chaorui Zhang, Wei Han, Bo Bai, Jun Gao

专题命中 工具调用 ：agent(abstract)；分类 cs.AI、cs.CL

DirectMultiStep: Direct Route Generation for Multistep Retrosynthesis

Yu Shee, Anton Morgunov, Haote Li, Victor S. Batista

专题命中 工具调用 ：planning(abstract)；分类 cs.AI、cs.LG

AI in radiological imaging of soft-tissue and bone tumours: a systematic review evaluating against CLAIM and FUTURE-AI guidelines

Douwe J. Spaanderman, Matthew Marzetti, Xinyi Wan, Andrew F. Scarsbrook, Philip Robinson, Edwin H. G. Oei, Jacob J. Visser, Robert Hemke, Kirsten van Langevelde, David F. Hanff, Geert J. L. H. van Leenders, Cornelis Verhoef, Dirk J. Gruühagen, Wiro J. Niessen, Stefan Klein, Martijn P. A. Starmans

专题命中 工具调用 ：workflow(abstract)；分类 cs.AI、cs.LG

Comments 25 pages, 6 figures, 8 supplementary figures

Journal ref eBioMedicine(2025), Volume 114, 105642

LLMs as Debate Partners: Utilizing Genetic Algorithms and Adversarial Search for Adaptive Arguments

Prakash Aryan

专题命中 工具调用 ：planning(abstract)；分类 cs.AI、cs.CL

FastFT: Accelerating Reinforced Feature Transformation via Advanced Exploration Strategies

Tianqi He, Xiaohan Huang, Yi Du, Qingqing Long, Ziyue Qiao, Min Wu, Yanjie Fu, Yuanchun Zhou, Meng Xiao

专题命中 工具调用 ：workflow(abstract)；分类 cs.AI、cs.LG

Comments 14 pages, Accepted by ICDE 2025

Open Deep Search: Democratizing Search with Open-source Reasoning Agents

Salaheddin Alzubi, Creston Brooks, Purva Chiniya, Edoardo Contente, Chiara von Gerlach, Lucas Irwin, Yihan Jiang, Arda Kaz, Windsor Nguyen, Sewoong Oh, Himanshu Tyagi, Pramod Viswanath

专题命中 工具调用 ：agent(abstract)；分类 cs.CL、cs.LG

Comments 27 pages, 8 figures, 4 tables

Browsing Lost Unformed Recollections: A Benchmark for Tip-of-the-Tongue Search and Reasoning

Sky CH-Wang, Darshan Deshpande, Smaranda Muresan, Anand Kannappan, Rebecca Qian

专题命中 工具调用 ：tool use(abstract)；分类 cs.AI、cs.CL

The case for delegated AI autonomy for Human AI teaming in healthcare

Yan Jia, Harriet Evans, Zoe Porter, Simon Graham, John McDermid, Tom Lawton, David Snead, Ibrahim Habli

专题命中 工具调用 ：tool use(abstract)；分类 cs.AI、cs.LG

From Commands to Prompts: LLM-based Semantic File System for AIOS

Zeru Shi, Kai Mei, Mingyu Jin, Yongye Su, Chaoji Zuo, Wenyue Hua, Wujiang Xu, Yujie Ren, Zirui Liu, Mengnan Du, Dong Deng, Yongfeng Zhang

专题命中 工具调用 ：agent(abstract)；分类 cs.AI、cs.LG

Comments Accepted by International Conference on Learning Representations 2025(ICLR2025)

Kanana: Compute-efficient Bilingual Language Models

Kanana LLM Team, Yunju Bak, Hojin Lee, Minho Ryu, Jiyeon Ham, Seungjae Jung, Daniel Wontae Nam, Taegyeong Eo, Donghun Lee, Doohae Jung, Boseop Kim, Nayeon Kim, Jaesun Park, Hyunho Kim, Hyunwoong Ko, Changmin Lee, Kyoung-Woon On, Seulye Baeg, Junrae Cho, Sunghee Jung, Jieun Kang, EungGyun Kim, Eunhwa Kim, Byeongil Ko, Daniel Lee, Minchul Lee, Miok Lee, Shinbok Lee, Gaeun Seo

专题命中 工具调用 ：function calling(abstract)；分类 cs.CL、cs.LG

Comments 40 pages, 15 figures