AI Agent - arXivDaily 专题

2411.01114 2024-11-05 cs.AI cs.CL 81%

Infant Agent: A Tool-Integrated, Logic-Driven Agent with Cost-Effective API Usage

Bin Lei, Yuchen Li, Yiming Zeng, Tao Ren, Yi Luo, Tianyu Shi, Zitian Gao, Zeyu Hu, Weitai Kang, Qiuwu Chen

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

2410.14255 2024-10-29 cs.AI cs.CL 81%

Nova: An Iterative Planning and Search Approach to Enhance Novelty and Diversity of LLM Generated Ideas

Xiang Hu, Hongyu Fu, Jinge Wang, Yifeng Wang, Zhikun Li, Renjun Xu, Yu Lu, Yaochu Jin, Lili Pan, Zhenzhong Lan

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

2409.06949 2024-09-12 cs.CL cs.AI 81%

You Have Thirteen Hours in Which to Solve the Labyrinth: Enhancing AI Game Masters with Function Calling

Jaewoo Song, Andrew Zhu, Chris Callison-Burch

专题命中工具调用：function calling(title,abstract)；分类 cs.AI、cs.CL

Comments Wordplay Workshop @ ACL 2024

2409.00135 2024-09-04 cs.CL cs.AI 81%

HoneyComb: A Flexible LLM-Based Agent System for Materials Science

Huan Zhang, Yu Song, Ziyu Hou, Santiago Miret, Bang Liu

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

Comments Under Review on EMNLP 2024

2407.00942 2024-07-02 cs.IR cs.AI cs.CL 81%

ProductAgent: Benchmarking Conversational Product Search Agent with Asking Clarification Questions

Jingheng Ye, Yong Jiang, Xiaobin Wang, Yinghui Li, Yangning Li, Hai-Tao Zheng, Pengjun Xie, Fei Huang

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

Comments 17 pages, 13 tables, 6 figures. Under review

2310.07075 2024-06-05 cs.CL cs.AI 81%

Don't Fine-Tune, Decode: Syntax Error-Free Tool Use via Constrained Decoding

Kexun Zhang, Hongqiao Chen, Lei Li, William Wang

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

2402.10466 2024-05-31 cs.CL cs.AI 81%

Large Language Models as Zero-shot Dialogue State Tracker through Function Calling

Zekun Li, Zhiyu Zoey Chen, Mike Ross, Patrick Huber, Seungwhan Moon, Zhaojiang Lin, Xin Luna Dong, Adithya Sagar, Xifeng Yan, Paul A. Crook

专题命中工具调用：function calling(title,abstract)；分类 cs.AI、cs.CL

Comments ACL 2024 Main. Code available at: https://github.com/facebookresearch/FnCTOD

2405.17438 2024-05-29 cs.PL cs.AI cs.LG 81%

An LLM-Tool Compiler for Fused Parallel Function Calling

Simranjit Singh, Andreas Karatzas, Michael Fore, Iraklis Anagnostopoulos, Dimitrios Stamoulis

专题命中工具调用：function calling(title,abstract)；分类 cs.AI、cs.LG

2402.18487 2024-02-29 cs.RO cs.AI cs.HC cs.LG 81%

Human-Centric Aware UAV Trajectory Planning in Search and Rescue Missions Employing Multi-Objective Reinforcement Learning with AHP and Similarity-Based Experience Replay

Mahya Ramezani, Jose Luis Sanchez-Lopez

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

2402.06360 2024-02-12 cs.IR cs.AI cs.CL 81%

CoSearchAgent: A Lightweight Collaborative Search Agent with Large Language Models

Peiyuan Gong, Jiamian Li, Jiaxin Mao

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

Comments 4 pages, demo

2312.03664 2023-12-15 cs.AI cs.CL 81%

Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordia

Alexander Sasha Vezhnevets, John P. Agapiou, Avia Aharon, Ron Ziv, Jayd Matyas, Edgar A. Duéñez-Guzmán, William A. Cunningham, Simon Osindero, Danny Karmon, Joel Z. Leibo

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

Comments 32 pages, 5 figures

2310.10158 2023-12-15 cs.CL cs.AI 81%

Character-LLM: A Trainable Agent for Role-Playing

Yunfan Shao, Linyang Li, Junqi Dai, Xipeng Qiu

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

Comments To appear at EMNLP 2023; Repo at https://github.com/choosewhatulike/trainable-agents

2310.12819 2023-11-30 cs.AI cs.LG 81%

Hybrid Search for Efficient Planning with Completeness Guarantees

Kalle Kujanpää, Joni Pajarinen, Alexander Ilin

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

Comments NeurIPS 2023 Poster

2309.01868 2023-09-06 cs.CL cs.AI 81%

On the Planning, Search, and Memorization Capabilities of Large Language Models

Yunhao Yang, Anshul Tomar

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

Comments 13 pages, 2 figures

2304.02233 2023-04-06 cs.CL cs.AI 81%

Ericson: An Interactive Open-Domain Conversational Search Agent

Zihao Wang, Ali Ahmadvand, Jason Choi, Payam Karisani, Eugene Agichtein

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

Comments pre-print

2102.06808 2023-03-16 cs.AI cs.LG 81%

Planning and Learning Using Adaptive Entropy Tree Search

Piotr Kozakowski, Mikołaj Pacek, Piotr Miłoś

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

2303.03394 2023-03-08 cs.LG cs.AI cs.MA 81%

Agent-based Collaborative Random Search for Hyper-parameter Tuning and Global Function Optimization

Ahmad Esmaeili, Zahra Ghorrati, Eric T. Matson

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

1907.09620 2022-10-12 cs.AI cs.LG cs.RO 81%

Rapid trial-and-error learning with simulation supports flexible tool use and physical reasoning

Kelsey R. Allen, Kevin A. Smith, Joshua B. Tenenbaum

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

Comments This manuscript is in press at PNAS. It is an extended version of a paper "Rapid Trial-and-Error Learning in Physical Problem Solving" accepted for oral presentation at the 41st Annual Meeting of the Cognitive Science Society (2019). It represents ongoing work on the part of the authors

2202.11847 2022-02-25 cs.CL cs.AI cs.CV 81%

CAISE: Conversational Agent for Image Search and Editing

Hyounghun Kim, Doo Soon Kim, Seunghyun Yoon, Franck Dernoncourt, Trung Bui, Mohit Bansal

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

Comments AAAI 2022 (11 pages)

2012.04700 2020-12-10 cs.RO cs.AI cs.LG cs.NE 81%

Emergence of Different Modes of Tool Use in a Reaching and Dragging Task

Khuong Nguyen, Yoonsuck Choe

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

Comments 11 pages, 10 figures, 14 pdf-embedded animations

2010.09832 2020-10-21 cs.LG cs.AI 81%

Dream and Search to Control: Latent Space Planning for Continuous Control

Anurag Koul, Varun V. Kumar, Alan Fern, Somdeb Majumdar

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

Comments Preprint

1905.13341 2020-06-02 cs.LG cs.AI stat.ML 81%

On Value Functions and the Agent-Environment Boundary

Nan Jiang

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

Comments 16 pages

2004.05363 2020-04-14 cs.SE cs.HC cs.LG cs.SI 81%

WES: Agent-based User Interaction Simulation on Real Infrastructure

John Ahlgren, Maria Eugenia Berezin, Kinga Bojarczuk, Elena Dulskyte, Inna Dvortsova, Johann George, Natalija Gucevska, Mark Harman, Ralf Lämmel, Erik Meijer, Silvia Sapora, Justin Spahr-Summers

专题命中工具调用：agent(title,abstract)；分类 cs.LG、cs.SE

Comments Author order is alphabetical. Correspondence to Mark Harman (markharman@fb.com). This paper appears in GI 2020: 8th International Workshop on Genetic Improvement

1908.10125 2019-08-28 cs.RO cs.AI cs.HC cs.LG 81%

Proactive Intention Recognition for Joint Human-Robot Search and Rescue Missions through Monte-Carlo Planning in POMDP Environments

Dimitri Ognibene, Lorenzo Mirante, Letizia Marchegiani

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

1907.02050 2019-07-04 cs.NE cs.AI cs.LG 81%

Reasoning and Generalization in RL: A Tool Use Perspective

Sam Wenke, Dan Saunders, Mike Qiu, Jim Fleming

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

Comments 13 pages, 5 figures

1802.06225 2018-02-20 cs.LG cs.AI 81%

A Deep Q-Learning Agent for the L-Game with Variable Batch Training

Petros Giannakopoulos, Yannis Cotronis

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

1702.08628 2018-02-20 cs.LG cs.AI cs.IT math.IT 81%

Analysis of Agent Expertise in Ms. Pac-Man using Value-of-Information-based Policies

Isaac J. Sledge, Jose C. Principe

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

Comments IEEE Transactions on Computational Intelligence and Artificial Intelligence in Games

2606.21553 2026-06-23 cs.CL cs.IR 新提交 80%

Dissecting Agentic RAG: A Component Ablation for Multi-Hop QA with a Local 7B Model

解析智能体RAG：基于本地7B模型的多跳问答组件消融研究

Sheroz Shaikh

机构 * Independent Researcher（独立研究员）

专题命中工具调用：agentic(title,abstract)；分类 cs.CL

AI总结通过消融实验，发现固定混合检索和短检索循环对多跳问答贡献最大，自适应路由和深度循环并非必要。

Comments 8 pages, 4 figures, 4 tables. Code: https://github.com/sherozshaikh/agentic-rag-eval

2412.15606 2025-02-04 cs.AI cs.CV 80%

Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage

Zhi Gao, Bofei Zhang, Pengxiang Li, Xiaojian Ma, Tao Yuan, Yue Fan, Yuwei Wu, Yunde Jia, Song-Chun Zhu, Qing Li

专题命中工具调用：agent(title,abstract)；分类 cs.AI

Comments ICLR 2025, https://mat-agent.github.io/

2604.23993 2026-08-04 cs.CL cs.AI cs.DB cs.LG cs.MA 80%

EPM-RL: Reinforcement Learning for On-Premise Product Mapping in E-Commerce

EPM-RL：电商产品映射的强化学习方法

Minhyeong Yu, Wonduk Seo

机构 * AI Research, Enhans（AI研究，Enhans）

专题命中工具调用：agent(abstract)；agentic(abstract)；multi-agent(abstract)；分类 cs.AI、cs.CL、cs.LG

AI总结本文提出EPM-RL框架，通过强化学习提升电商产品映射的准确性和效率，解决传统方法依赖外部API和高成本的问题，实现私有部署和低成本运营。

Comments preprint

Journal ref Proceedings of the AAAI Symposium Series, vol. 9, no. 1, p. 227, 2026

1. 工具调用 5014 篇

Infant Agent: A Tool-Integrated, Logic-Driven Agent with Cost-Effective API Usage

Nova: An Iterative Planning and Search Approach to Enhance Novelty and Diversity of LLM Generated Ideas

You Have Thirteen Hours in Which to Solve the Labyrinth: Enhancing AI Game Masters with Function Calling

HoneyComb: A Flexible LLM-Based Agent System for Materials Science

ProductAgent: Benchmarking Conversational Product Search Agent with Asking Clarification Questions

Don't Fine-Tune, Decode: Syntax Error-Free Tool Use via Constrained Decoding

Large Language Models as Zero-shot Dialogue State Tracker through Function Calling

An LLM-Tool Compiler for Fused Parallel Function Calling

Human-Centric Aware UAV Trajectory Planning in Search and Rescue Missions Employing Multi-Objective Reinforcement Learning with AHP and Similarity-Based Experience Replay

CoSearchAgent: A Lightweight Collaborative Search Agent with Large Language Models

Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordia

Character-LLM: A Trainable Agent for Role-Playing

Hybrid Search for Efficient Planning with Completeness Guarantees

On the Planning, Search, and Memorization Capabilities of Large Language Models

Ericson: An Interactive Open-Domain Conversational Search Agent

Planning and Learning Using Adaptive Entropy Tree Search

Agent-based Collaborative Random Search for Hyper-parameter Tuning and Global Function Optimization

Rapid trial-and-error learning with simulation supports flexible tool use and physical reasoning

CAISE: Conversational Agent for Image Search and Editing

Emergence of Different Modes of Tool Use in a Reaching and Dragging Task

Dream and Search to Control: Latent Space Planning for Continuous Control

On Value Functions and the Agent-Environment Boundary

WES: Agent-based User Interaction Simulation on Real Infrastructure

Proactive Intention Recognition for Joint Human-Robot Search and Rescue Missions through Monte-Carlo Planning in POMDP Environments

Reasoning and Generalization in RL: A Tool Use Perspective

A Deep Q-Learning Agent for the L-Game with Variable Batch Training

Analysis of Agent Expertise in Ms. Pac-Man using Value-of-Information-based Policies

Dissecting Agentic RAG: A Component Ablation for Multi-Hop QA with a Local 7B Model

Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage

EPM-RL: Reinforcement Learning for On-Premise Product Mapping in E-Commerce