Tool-Using Agents

Ask about this topic

Overview

Tool-using agents are language-model-based systems that choose and invoke external tools—such as search, code, databases, or graphical interfaces—and use the results to pursue goals over multiple steps. Research develops tool selection and retrieval, planning and decomposition, memory and reusable skills, and training with supervised trajectories or reinforcement learning; runtime harnesses add state tracking, verification, permissions, and recovery. Evaluation is shifting from isolated function calls and final answers toward stateful workflows, measuring task completion alongside cost, policy adherence, robustness to errors, and intermediate actions across web, terminal, office, and domain-specific tasks. A central tension is that broader autonomy and longer tool chains expand capability but also amplify grounding errors, stale state, unsafe side effects, and hidden tool failures, so reliable execution and calibrated stopping remain open problems.

Latest papers

CardsList

289 papers54 papers in the last four weeks, up 74% on the four weeks before. 0.3% of all new papers.

  1. When Agents Look the Same: Quantifying Distillation-Induced Similarity in Tool-Use Behaviors

    Apr 23, 2026Chenghao Yang, Yuning Zhang, Zhoufutu Wen +4Tool-Augmented Language Model AgentsLLM Agent Evaluation

    School of Cyber Science and Technology, USTC · Anhui Province Key Laboratory of Digital Security · 3M-A-P +1

  2. ClawEnvKit: Automatic Environment Generation for Claw-Like Agents

    Apr 20, 2026Xirui Li, Ming Li, Ion Stoica +2Agent EvaluationAI Agent Benchmarks

    University of Maryland · 5Mohamed bin Zayed University of Artificial Intelligence · 2Arena +2

  3. Architectural Design Decisions in AI Agent Harnesses

    Apr 20, 2026Hu WeiLLM Agent OrchestrationTool-Using Agents

  4. ReCoQA: A Benchmark for Tool-Augmented and Multi-Step Reasoning in Real Estate Question and Answering

    Apr 20, 2026Yindong Zhang, Wenmian Yang, Yiquan Zhang +1LLM Agent OrchestrationAI Agent Benchmarks

    Hong Kong Baptist University · Beijing Normal-Hong Kong Baptist University · Beijing Normal University

  5. Agents Explore but Agents Ignore: LLMs Lack Environmental Curiosity

    Apr 19, 2026Leon Engländer, Sophia Althammer, Ahmet Üstün +2LLM Agent EvaluationTool-Using Agents

    Cohere · Poolside

  6. Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories

    Apr 19, 2026Ivan Bercovich, Ivgeni Segal, Kexun Zhang +3Reward HackingAI Agent Security Benchmarks

    1Fewshot Corp · *Independent Researcher · 2Carnegie Mellon University

  7. Complete Cyclic Subtask Graphs for Tool-Using LLM Agents: Flexibility, Cost, and Bottlenecks in Multi-Agent Workflows

    Apr 17, 2026Luay Gharzeddine, Samer SaabMulti-Agent CoordinationMulti-Agent Orchestration

    1Dept of Computer Science, Lebanese American University. · 2*Dept of Electrical and Computer Engineering, Lebanese American University.

  8. VoxMind: An End-to-End Agentic Spoken Dialogue System

    Apr 17, 2026Tianle Liang, Yifu Chen, Shengpeng Ji +7Multi-Agent LLM SystemsSpoken Dialogue Systems

    Zhejiang University · China University of Petroleum-Beijing at Karamay · Xiamen University

  9. El Agente Forjador: Task-Driven Agent Generation for Quantum Simulation

    Apr 16, 2026Zijian Zhang, Aiwei Yin, Amaan Baweja +4Multi-Agent LLM SystemsAI for Science

    Department of Computer Science, University of Toronto, 40 St George St., Toronto, ON M5S 2E4, Canada · Vector Institute for Artificial Intelligence, W1140-108 College St., Schwartz Reisman Innovation2026 Campus, Toronto, ON M5G 0C6, Canada · NVIDIA, 431 King St W #6th, Toronto, ON M5V 1K4, Canada +5

  10. CocoaBench: Evaluating Unified Digital Agents in the Wild

    Apr 13, 2026CocoaBench Team, Shibo Hao, Zhining Zhang +29AI Agent BenchmarksComputer-Use Agent Evaluation

  11. Semantic Feature Analysis: Improving Agents Without Searching Over Rollouts

    Apr 12, 2026Yuval David, Fabiana Fournier, Lior Limonad +1LLM Agent Self-ImprovementTool-Using Agents

    IBM Software Innovation Lab Haifa, Israel

  12. Authoring for Living Worlds: Tool-Constrained LLM Agents for Executable Multi-Actor Scenarios

    Apr 11, 2026Nicolae Cudlenco, Mihai Masala, Marius LeordeanuLLM Agent OrchestrationTool-Using Agents

    Institute of Mathematics of the Romanian Academy, Bucharest, Romania · Büchi Labortechnik AG, Flawil, Switzerland · National University of Science and Technology Politehnica Bucharest, Romania

  13. The Amazing Agent Race: Strong Tool Users, Weak Navigators

    Apr 11, 2026Zae Myung Kim, Dongseok Lee, Jaehyung Kim +2LLM Agent EvaluationAI Agent Benchmarks

    University of Minnesota Twin Cities · Yonsei University · Grammarly

  14. AnomalyAgent: Agentic Industrial Anomaly Synthesis via Tool-Augmented Reinforcement Learning

    Apr 9, 2026Jiaming Su, Tengchao Yang, Ruikang Zhang +3Synthetic Anomaly GenerationTool-Using Agents

    Shanghai Jiao Tong University Shanghai, China · Tongji University Shanghai, China · Fudan University Shanghai, China

  15. VisionClaw: Always-On AI Agents through Smart Glasses

    Apr 3, 2026Xiaoan Liu, DaeHo Lee, Eric J Gonzalez +2Multimodal AgentsTool-Using Agents

    University of Colorado Boulder, Boulder, Colorado, USA · Gwangju Institute of Science and Technology, Gwangju, Republic of Korea · Google, Seattle, Washington, USA

  16. ToolMisuseBench: An Offline Deterministic Benchmark for Tool Misuse and Recovery in Agentic Systems

    Apr 2, 2026Akshey Sigdel, Rista BaralTool-Use EvaluationTool-Using Agents

    Independent Researcher

  17. Agentic Tool Use in Large Language Models

    Apr 1, 2026Jinchao Hu, Meizhi Zhong, Kehai Chen +2LLM Agent EvaluationTool-Using Agents

    School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China · Independent Researcher, China

  18. Beyond Task Completion: A Verification-vs.-Conformance Gap in Tool-Evolving Agents

    Apr 1, 2026Alibek Kaliyev, Artem MaryanskyyAI Agent ReliabilityTool-Use Evaluation

    The University of Texas at Austin · Austin, Texas, USA · Uber +1

  19. Open, Reliable, and Collective: A Community-Driven Framework for Tool-Using AI Agents

    Mar 31, 2026Hy Dang, Quang Dao, Meng JiangTool-Using AgentsLLM Agent Reliability

    University of Notre Dame · Rose-Hulman Institute of Technology

  20. Cognitive Friction: A Decision-Theoretic Framework for Bounded Deliberation in Tool-Using Agents

    Mar 31, 2026Davide Di GioiaTool-Using AgentsCognitive Architectures for AI Agents

  21. Formal Semantics for Agentic Tool Protocols: A Process Calculus Approach

    Mar 25, 2026Andreas SchlapbachAgent Communication ProtocolsFormal Verification

    Swiss Federal Railways (SBB) SBB IT Berne, Switzerland

  22. Empirical Comparison of Agent Communication Protocols for Task Orchestration

    Mar 24, 2026Ivan DobrovolskyiAgent Communication ProtocolsLLM Agent Orchestration

    Independent Researcher, Sunnyvale, CA, USA

  23. AgenticRec: A Recommendation-Oriented Agentic Framework with Progressive Tool-Integrated Reasoning Optimization

    Mar 23, 2026Tianyi Li, Zixuan Wang, Guidong Lei +2Recommender SystemsLarge Language Model-Based Recommendation

    Xiamen University, Xiamen, China

  24. LiveClawBench: Benchmarking LLM Agents on Complex, Real-World Assistant Tasks

    Mar 20, 2026Xiang Long, Li Du, Yilong Xu +11Computer-Use Agent BenchmarksTool-Augmented Language Model Agents

    Samsung Research, Beijing, China · HKUST (Guangzhou) · City University of Hong Kong +1

  25. EvoGuard: An Extensible Agentic RL-based Framework for Practical and Evolving AI-Generated Image Detection

    Mar 18, 2026Chenyang Zhu, Maorong Wang, Jun Liu +2Ensemble LearningTool-Using Agents

    The University of Tokyo Tokyo, Japan · National Institute of Informatics Tokyo, Japan

  26. AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents

    Mar 15, 2026Shengda Fan, Xuyan Ye, Yupeng Huo +9LLM Agent EvaluationProcess-Based Agent Evaluation

    Renmin University of China Beijing, China · Beijing Jiaotong University Beijing, China · Shanghai Jiao Tong University Shanghai, China +1

  27. Bridging Protocol and Production: Design Patterns for Deploying AI Agents with Model Context Protocol

    Mar 12, 2026Vasundra SrinivasanTool-Using AgentsAI Agent Reliability

  28. ToolRosella: Translating Code Repositories into Standardized Tools for Scientific Agents

    Mar 10, 2026Shimin Di, Xujie Yuan, Hanghui Guo +10LLM Tool UseTool-Using Agents

    Southeast University, Nanjing, China. · Sun Yat-sen University, Zhuhai, China. · Rensselaer Polytechnic Institute, Troy, USA. +1

  29. Test-Driven AI Agent Definition (TDAD): Compiling Tool-Using Agents from Behavioral Specifications

    Mar 9, 2026Tzafrir RehanTool-Using AgentsAI Agent Evaluation

    Fiverr Labs

  30. Conversational Demand Response: Bidirectional Aggregator-Prosumer Coordination through Agentic AI

    Mar 6, 2026Reda El Makroum, Sebastian Zwickl-Bernhard, Lukas Kranzl +1Demand ResponseMulti-Agent Coordination

    Energy Economics Group, TU Wien, Gußhausstraße 25–29, Vienna, Austria · Industrial Economics and Technology Management, NTNU, Trondheim, Norway