LLM Tool Use

LLM: Large Language Model

Overview

Large language model tool use examines how models decide when tools are needed, choose among them, provide valid arguments, and use returned results to complete tasks. Common approaches include prompting frameworks such as ReAct, supervised fine-tuning and reinforcement learning on tool-call trajectories, retrieval and filtering for large tool catalogs, and planning with execution feedback or memory. Benchmarks such as BFCL, AppWorld, and MCP-based evaluations test structured calls, multi-step workflows, and real-world tool interactions. A central challenge is making tool use reliable and efficient: tools can improve computation and access to current information, but unnecessary calls, bad arguments, misleading results, and failures in long-horizon reasoning can make performance worse.

Latest papers

CardsList

313 papers21 papers in the last four weeks, down 59% on the four weeks before. 0.2% of all new papers.

  1. System 1 agents: a method for local, reliable and fast agentic AI

    Nov 16, 2026Eleftherios Tzanis, Michail E. KlontzasLLM Agent ReliabilityLLM Tool Use

  2. Weight-Space Programming Changes How an LLM Uses Python for Computational Biology

    Nov 16, 2026Makoto SatoLanguage Model EditingLLM Tool Use

  3. Do Rule-Based Tools Help LLMs Translate Endangered Uralic Languages in the Prompt or over MCP?

    Nov 14, 2026Iaroslav Chelombitko, Mika HämäläinenMachine TranslationLLM Tool Use

  4. ToolTurns: Benchmarking LLM Agents in Multi-Turn Dialogue

    Nov 11, 2026Milad Gholami, Brendan King, Jeffrey FlaniganTool-Use EvaluationLLM Agent Evaluation

  5. Deletion Sensitivity Is a Property of the Model: A Three-Condition Measurement over 72 Valid Experimental Cells

    Nov 9, 2026Yiran Li, Hanzhang Jia, Liheng Zeng +2LLM Tool UseMulti-Turn Language Model Reasoning

  6. DM-Call: Decision-Model-Guided Function Calling with Cumulative Verification Feedback

    Nov 7, 2026Minhyeong Yu, Wonduk Seo, Seunghyun LeeLLM Tool UseTool Use

  7. Computation, not weight access: large language models as auditors of clinical prediction networks

    Nov 5, 2026Zhiyu Liu, Xinyu YangLLM AuditingLLM Evaluation

  8. ToolSpace: Scaling Tool-Centric Environment Synthesis for Long-Horizon Agents

    Nov 3, 2026Guanting Dong, Zhichao Sun, Xinyu Yang +22LLM Tool UseLong-Horizon LLM Agents

  9. LLMs Depend on Specialist Tools for Out-of-Distribution Generalization in MS/MS Structural Elucidation

    Nov 2, 2026Gabriel Asher, Cailum M. K. Stienstra, Tomo Oga +3Chemical Reasoning in LLMsMass Spectrometry

  10. Axion 1.0: Open Agent Foundation Models, Simplified

    Nov 2, 2026Yuqi Jia, Yunjie Tian, Jiayu Zheng +4LLM AgentsLLM Agent Training

  11. TAC-CoT: Tool-Empowered Implicit Chain-of-Thought via Interleaving Explicit Tokens

    Nov 1, 2026Juseon Do, Sangmin Bae, Jeesu Jung +1Implicit Reasoning in Language ModelsAdaptive Reasoning in Language Models

  12. A Tool in the Forward Pass: Frozen Tape Modules as Layers of a Small Language Model

    Oct 31, 2026Michael Granitzer, Saber Zerhoudi, Mohammad Al-Maamari +2LLM Tool UseEfficient Language Model Inference

  13. How Much Can Tool Calls Reveal About You? Privacy Leakage from Tool-Call Traces

    Oct 30, 2026Donghang Duan, Qingyu Liu, Yifei Liu +3User Attribute Inference AttacksLLM Agent Security

  14. Saidzoda-Tajik-LFM-2.6B: Adapting a 2.6B Hybrid Model to Tajik Tool Calling, and What Continued Pretraining Takes Away

    Oct 30, 2026Tohir Saidzoda, Nekruz Maxudov, Bedil Karimov +5LLM Tool UseFine-Tuning Language Models

  15. RTL-Interact: Training EDA-Interactive Models for Multi-Task RTL Design

    Oct 30, 2026Wenxuan Shi, Yaoyu Zhu, Di Huang +13LLM Tool UseElectronic Design Automation

  16. Context Is a Pipeline, Not a Window: Information Attrition in LLM Agent Harnesses

    Oct 26, 2026Yuvraj Sehgal, Mahsa Panahandeh, Naser Ezzati-JivanLLM Context ManagementLLM Agent Harnesses

  17. 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

  18. Prompt Sensitivity in Tool-Augmented Model Comparisons

    Oct 22, 2026Mateusz Modrzejewski, Tomasz RadzikowskiLLM EvaluationPrompt Sensitivity

  19. Before the Ticket: Grounding HPC User Support in Documentation and Resolved Tickets with an Agentic LLM Assistant

    Oct 21, 2026Elham J. Barezi, Primus C Kabuo, Niveditha NerellaQuestion AnsweringDocument QA

  20. Measure First, Then Allocate: Calibrated Rollout Budgets for MCP Agents in Reinforcement Learning

    Oct 20, 2026Hieu Tran, Zonghai Yao, Sunjae Kwon +1RL for LLM AgentsRL for Language Models

  21. Same Simulation, Different Evidence: Where Retrieved Tool Output Costs LLM Agents Accuracy

    Oct 19, 2026Ke Zhang, Sahchit Chundur, Jerry Peprah Owusu +2LLM Tool UseLLM Agent Reliability

  22. Learning Which Device to Call: Online Tool Grounding for LLM Agents in IoT

    Oct 18, 2026Yichen Liu, Xiaochong Jiang, Haoran Yu +1LLM Tool UseTool Selection for Language Model Agents

  23. Muse Glimmer 30B: An On-Device Agentic Model

    Oct 17, 2026Arash Ebrahim Abtahizadeh, Muna Aghamelu, Adil Ahmed +326LLM AgentsLLM Tool Use

  24. Rethinking the Role of Tool Graph Memory in Multi-Turn Tool Use

    Oct 15, 2026Uiji Hwang, Richeng Xuan, Taeuk KimLLM Tool UseAgent Memory

  25. Tool-Augmented Large Language Models for Reliable Medical Calculation from Patient Notes

    Oct 15, 2026Yang Zhong, Ling Luo, Xuanlyu Zhu +4LLM Tool UseClinical Decision Support

  26. Incentivizing Tool-Use Reinforcement Learning for Post-Arrival Emergency Care Prediction

    Oct 15, 2026Pengfei Hu, Chenwei Wu, Qiao Jin +4Clinical Outcome PredictionClinical Risk Prediction