AI Agent

DiLA: Enhancing LLM Tool Learning with Differential Logic Layer

Yu Zhang, Hui-Ling Zhen, Zehua Pei, Yingzhao Lian, Lihao Yin, Mingxuan Yuan, Bei Yu

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

Comments arXiv admin note: text overlap with arXiv:2305.12295 by other authors

Where to Search: Measure the Prior-Structured Search Space of LLM Agents

Zhuo-Yang Song

机构 * School of Physics, Peking University（物理学院，北京大学） 纠错

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

Comments 11 pages, 4 figures, 1 table

TreeIRL: Safe Urban Driving with Tree Search and Inverse Reinforcement Learning

Momchil S. Tomov, Sang Uk Lee, Hansford Hendrago, Jinwook Huh, Teawon Han, Forbes Howington, Rafael da Silva, Gianmarco Bernasconi, Marc Heim, Samuel Findler, Xiaonan Ji, Alexander Boule, Michael Napoli, Kuo Chen, Jesse Miller, Boaz Floor, Yunqing Hu

机构 * Motional 纠错

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

Learning Heuristics for Transit Network Design and Improvement with Deep Reinforcement Learning

Andrew Holliday, Ahmed El-Geneidy, Gregory Dudek

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

Comments The version of this work presented here is a post-peer-review, pre-copyedit version. The final post-copyedit version that appears in Transportmetrica B is available under open access on the publisher's website: https://www.tandfonline.com/doi/full/10.1080/21680566.2025.2561863

Journal ref Transportmetrica B: Transport Dynamics, 13(1) (2025)

Declarative Techniques for NL Queries over Heterogeneous Data

Elham Khabiri, Jeffrey O. Kephart, Fenno F. Heath, Srideepika Jayaraman, Fateh A. Tipu, Yingjie Li, Dhruv Shah, Achille Fokoue, Anu Bhamidipaty

机构 * IBM Research（IBM研究院） 纠错

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

PAFT: Prompt-Agnostic Fine-Tuning

Chenxing Wei, Yao Shu, Mingwen Ou, Ying Tiffany He, Fei Richard Yu

机构 * College of Computer Science and Software Engineering, Shenzhen University, China（深圳大学计算机科学与软件工程学院） ； Tsinghua Shenzhen International Graduate School, Tsinghua University, China（清华大学深圳国际研究生院） ； Guangdong Lab of AI and Digital Economy (SZ), China（广东人工智能与数字经济实验室（深圳）） ； Hong Kong University of Science and Technology (Guangzhou), China（香港科技大学（广州）） ； School of Information Technology, Carleton University, Canada（卡尔顿大学信息科技学院） 纠错

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

Comments 24 pages, 9 figures

Generating Fair Consensus Statements with Social Choice on Token-Level MDPs

Carter Blair, Kate Larson

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

CodeWatcher: IDE Telemetry Data Extraction Tool for Understanding Coding Interactions with LLMs

Manaal Basha, Aimeê M. Ribeiro, Jeena Javahar, Cleidson R. B. de Souza, Gema Rodríguez-Pérez

机构 * University of British Columbia（不列颠哥伦比亚大学） ； Federal University of Pará（帕拉联邦大学） 纠错

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

Comments ICSME 2025 Tool Demonstration Track

Beyond the limitation of a single query: Train your LLM for query expansion with Reinforcement Learning

Shu Zhao, Tan Yu, Anbang Xu

机构 * NVIDIA（英伟达） ； Pennsylvania State University（宾夕法尼亚州立大学） 纠错

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

Hypothesis Hunting with Evolving Networks of Autonomous Scientific Agents

Tennison Liu, Silas Ruhrberg Estévez, David L. Bentley, Mihaela van der Schaar

机构 * DAMTP, University of Cambridge（剑桥大学 DAMTP 部门） ； School of Medicine, University of Colorado（科罗拉多大学医学院） 纠错

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

Building Resource-Constrained Language Agents: A Korean Case Study on Chemical Toxicity Information

Hojun Cho, Donghu Kim, Soyoung Yang, Chan Lee, Hunjoo Lee, Jaegul Choo

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

Comments EMNLP 2025 Industry track

OpenJAI-v1.0: An Open Thai Large Language Model

Pontakorn Trakuekul, Attapol T. Rutherford, Jullajak Karnjanaekarin, Narongkorn Panitsrisit, Sumana Sumanakul

机构 * Jasmine Technology Solution（贾斯敏科技解决方案） 纠错

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

ClaimCheck: Real-Time Fact-Checking with Small Language Models

Akshith Reddy Putta, Jacob Devasier, Chengkai Li

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

DeepCodeSeek: Real-Time API Retrieval for Context-Aware Code Generation

Esakkivel Esakkiraja, Denis Akhiyarov, Aditya Shanmugham, Chitra Ganapathy

机构 * ServiceNow, Inc.（ServiceNow公司） 纠错

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

Comments Retrieval-Augmented Generation, API Prediction, Context-Aware Code Generation, Enterprise Code Completion, Reinforcement Learning, ServiceNow, Real-Time Code Search, Query Enhancement, Fine-Tuning, Embedding, Reranker

Video models are zero-shot learners and reasoners

Thaddäus Wiedemer, Yuxuan Li, Paul Vicol, Shixiang Shane Gu, Nick Matarese, Kevin Swersky, Been Kim, Priyank Jaini, Robert Geirhos

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

Comments Project page: https://video-zero-shot.github.io/

Dynamic ReAct: Scalable Tool Selection for Large-Scale MCP Environments

Nishant Gaurav, Adit Akarsh, Ankit Ranjan, Manoj Bajaj

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

Automating Modelica Module Generation Using Large Language Models: A Case Study on Building Control Description Language

Hanlong Wan, Xing Lu, Yan Chen, Karthik Devaprasad, Laura Hinkle

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

Comments This is the pre-peer-review version of a journal paper; the repo is available at: https://github.com/pnnl/prompt2control

MillStone: How Open-Minded Are LLMs?

Harold Triedman, Vitaly Shmatikov

机构 * Cornell Tech（康奈尔科技） 纠错

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

Comments 19 pages, 7 tables, 7 figures

Automated Creation and Enrichment Framework for Improved Invocation of Enterprise APIs as Tools

Prerna Agarwal, Himanshu Gupta, Soujanya Soni, Rohith Vallam, Renuka Sindhgatta, Sameep Mehta

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

TransZero: Parallel Tree Expansion in MuZero using Transformer Networks

Emil Malmsten, Wendelin Böhmer

机构 * Delft University of Technology, The Netherlands（代尔夫特理工大学，荷兰） 纠错

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

Comments Submitted to BNAIC/BeNeLearn 2025. 15 pages, 4 figures

Quantum Architecture Search for Solving Quantum Machine Learning Tasks

Michael Kölle, Simon Salfer, Tobias Rohe, Philipp Altmann, Claudia Linnhoff-Popien

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

Enhancing FKG.in: automating Indian food composition analysis

Saransh Kumar Gupta, Lipika Dey, Partha Pratim Das, Geeta Trilok-Kumar, Ramesh Jain

机构 * Ashoka University（阿什oka大学） ； Institute of Future Health（未来健康研究所） ； UC Irvine 纠错

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

Comments 15 pages, 5 figures, 30 references, International Conference on Pattern Recognition 2024 - Multimedia Assisted Dietary Management Workshop

CAD-Assistant: Tool-Augmented VLLMs as Generic CAD Task Solvers

Dimitrios Mallis, Ahmet Serdar Karadeniz, Sebastian Cavada, Danila Rukhovich, Niki Foteinopoulou, Kseniya Cherenkova, Anis Kacem, Djamila Aouada

机构 * SnT, University of Luxembourg（斯诺特研究所，卢森堡大学） ； Artec3D, Luxembourg（Artec3D，卢森堡） 纠错

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

CO-Bench: Benchmarking Language Model Agents in Algorithm Search for Combinatorial Optimization

Weiwei Sun, Shengyu Feng, Shanda Li, Yiming Yang

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

Ranking over Regression for Bayesian Optimization and Molecule Selection

Gary Tom, Stanley Lo, Samantha Corapi, Alan Aspuru-Guzik, Benjamin Sanchez-Lengeling

机构 * University of Toronto（多伦多大学） ； Vector Institute for Artificial Intelligence（向量人工智能研究所） ； CIFAR Lebovic Fellow（CIFAR 莱博维奇 Fellow） ； Canada（加拿大） ； Chair, Director of Acceleration Consortium（150 职位，加速联盟主任） 纠错

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

Comments 14 + 4 pages, 5 + 3 figures

Journal ref APL Machine Learning, Volume 3, pg. 036113 (2025)

Search-Time Data Contamination

Ziwen Han, Meher Mankikar, Julian Michael, Zifan Wang

机构 * Scale AI 纠错

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

AutoGeTS: Knowledge-based Automated Generation of Text Synthetics for Improving Text Classification

Chenhao Xue, Yuanzhe Jin, Adrian Carrasco-Revilla, Joyraj Chakraborty, Min Chen

机构 * FabLab, Inetum（FabLab，Inetum） 纠错

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

FinSage: A Multi-aspect RAG System for Financial Filings Question Answering

Xinyu Wang, Jijun Chi, Zhenghan Tai, Tung Sum Thomas Kwok, Muzhi Li, Zhuhong Li, Hailin He, Yuchen Hua, Peng Lu, Suyuchen Wang, Yihong Wu, Jerry Huang, Jingrui Tian, Fengran Mo, Yufei Cui, Ling Zhou

机构 * 1SimpleWay.AI 2McGill University 3University of Toronto 4University of California, Los Angeles 5The Chinese University of Hong Kong 6Duke University 7Universit\'e de Montr\'eal 8Mila - Quebec AI Institute 9Noah's Ark Lab 10CG Matrix Technology Limited ； 1SimpleWay.AI 2McGill University 3University of Toronto 4University of California, Los Angeles ； 5The Chinese University of Hong Kong 6Duke University 7Universit\'e de Montr\'eal 8Mila - Quebec AI Institute ； 9Noah's Ark Lab 10CG Matrix Technology Limited 纠错

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

Comments Accepted at the 34th ACM International Conference on Information and Knowledge Management (CIKM2025)

Chemist-aligned retrosynthesis by ensembling diverse inductive bias models

Krzysztof Maziarz, Guoqing Liu, Hubert Misztela, Austin Tripp, Junren Li, Aleksei Kornev, Piotr Gaiński, Holger Hoefling, Mike Fortunato, Rishi Gupta, Marwin Segler

机构 * Microsoft Research AI for Science（微软研究院人工智能与科学研究中心） ； Novartis Biomedical Research（诺华生物医学研究） ； University of Cambridge（剑桥大学） ； Jagiellonian University（雅盖隆大学） 纠错

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

GeMuCo: Generalized Multisensory Correlational Model for Body Schema Learning

Kento Kawaharazuka, Kei Okada, Masayuki Inaba

机构 * Department of Mechano-Informatics, Graduate School of Information Science and Technology, The University of Tokyo（机械信息学系，信息科学和技术研究生院，东京大学） 纠错

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

Comments Accepted at IEEE Robotics and Automation Magazine