Tool-Augmented Language Model Agents

Overview

Tool-augmented language model agents decide when and how to use tools such as web search, code interpreters, and application APIs, then incorporate the results into multi-step tasks. Common approaches include retrieval and filtering of tool menus, planning and memory, structured tool-call interfaces, and supervised fine-tuning or reinforcement learning in executable environments. Benchmarks such as BFCL, τ²-bench, and AppWorld test tool selection, argument accuracy, and task completion, while newer evaluations examine long-horizon workflows and failures in stateful settings. A central challenge is making tool use reliable and efficient: tools can improve answers, but unnecessary calls, faulty outputs, and mismatches between models and agent harnesses can undermine performance.

Latest papers

CardsList

175 papers11 papers in the last four weeks, down 31% on the four weeks before. 0.1% of all new papers.

  1. ARCHER: From Rationale Imitation to Executable Reasoning in Small Language Models

    Nov 13, 2026Dhruv Dixit, Khushi Patel, Congcong Xu +1LLM ReasoningStructured Reasoning in Language Models

  2. Lost in Delegation: Studying the Effectiveness of Task Orchestration in Generative Search

    Nov 12, 2026Tamara Stojanovska, Elisabeth Kirsten, Leon Swazinna +1Tool-Augmented Language Model AgentsLLM Agent Orchestration

  3. OverServe: Resource Amplification Attacks on SaaS Agents via Tool--Prompt Co-Design

    Nov 10, 2026Ruiheng Yu, Oteo Mamo, Siyu Gan +2LLM Agent SecurityTool-Augmented Language Model Agents

  4. Mechanical Engineering Skills: An Open Library of Agent Skills for Design, Analysis and Manufacturing

    Nov 3, 2026Achuth Chandrasekhar, Jesse Barkley, Peter Pak +3Tool-Augmented Language Model Agents

  5. NEIGHBOR: Aligning Service Behaviour and Evidence Use in an LLM Agent for Community Resident Services

    Nov 1, 2026Zongyou Yang, Yinghan Hou, Xiaokun YangLLM Agent TrainingTool-Augmented Language Model Agents

  6. SimXAI: A Simple Drop-in Layer Increases Interaction Quality and Understanding in Conversational XAI

    Oct 30, 2026Van Bach Nguyen, Qianli Wang, Nils Feldhus +2Explainable Artificial IntelligenceTool-Augmented Language Model Agents

  7. Matched Capabilities, Different Behaviors: A Controlled Study of MCP and CLI Interfaces for Language Agents

    Oct 25, 2026Zhenning Shi, Liang Pang, Yongqi LiTool-Augmented Language Model AgentsLLM Tool Use

  8. MedCaseAgent: From Multimodal Clinical Evidence to Rare Disease Case Reports

    Oct 23, 2026Hongkang Chu, Yifan Shen, Tianjiao Yu +4Medical Report GenerationMedical LLMs

  9. Robust Function Calling for LLM Agents Under Interface Drift

    Oct 16, 2026Aniruddha Chattopadhyay, Kanishka Halder, Partha Sarathi RoyTool-Augmented Language Model AgentsLLM Agent Reliability

  10. Terrarium: Growing Personal Assistants via Scalable Synthesis of App Worlds

    Oct 10, 2026Mengzhou Wu, Yuzhe Guo, Jiawen Tao +9LLM Agent TrainingSynthetic Data Generation for Language Models

  11. Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success Rate but 65% Fewer Tokens

    Oct 1, 2026Ruiyang Si, Jianxin Bi, Shunyu Yang +12Vision-Language-Action ModelsTool-Augmented Language Model Agents

  12. Finding the Right Fit: Model-Harness Interactions across Agent Tasks

    Oct 1, 2026Yixuan Li, Yiyun Zhou, Yao Long Teng +6Tool-Augmented Language Model AgentsLLM Agent Evaluation

  13. TMCS: Tool-Grounded Multi-Agent Reasoning for Compositional Chemical Problem Solving

    Sep 28, 2026Shengqin Wang, Jie Jin, Yu Cheng +4Molecular OptimizationTool-Augmented Language Model Agents

  14. AgentHop: A Diagnostic Benchmark for Agentic Multi-Hop Question Answering over Scientific Citation Graphs

    Sep 28, 2026Chanhee Park, Jeongho Yoon, Sungbin Han +2Multi-Hop QATool-Augmented Language Model Agents

  15. On Device Agentic Operation Caches -- Classifier-Centric NL-to-Action Generation

    Sep 27, 2026Moghis Fereidouni, Anthony Arnold, Sumit Gulwani +2LLM Inference EfficiencyTool-Augmented Language Model Agents

  16. SkillGym: Internalizing Human Skills into LLMs for Real-World Problem Solving

    Sep 23, 2026Zhilong Ge, Yuting Shao, Yutao Yang +6Tool-Augmented Language Model AgentsLLM Agent Skill Learning

  17. Toolcompass: Guiding Tool Trialing, Not Suppressing It

    Sep 22, 2026Junlin Fang, Chong Zhang, Do Nguyen-Thanh +3Representation LearningTool-Augmented Language Model Agents

  18. Qwen-Audio-3.1-Realtime: Towards Reliable Agentic Voice Interaction

    Sep 21, 2026Lujia Bao, Qian Chen, Luyao Cheng +15Tool-Augmented Language Model AgentsSpeech Foundation Models

  19. Lookahead-R: Budget-Aware Tool Retrieval via Execution-Centric Planning

    Sep 20, 2026Zongze Wu, Yani Guo, Runnan LiLLM Tool UseTool-Augmented Language Model Agents