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

306 papers26 papers in the last four weeks, down 57% on the four weeks before. 0.2% of all new papers.

  1. AgenTRIM: Tool Risk Mitigation for Agentic AI

    Jan 18, 2026Roy Betser, Amit Giloni, Shamik Bose +4LLM Agent SecurityIndirect Prompt Injection

  2. Multi-Agent Coordinated Rename Refactoring

    Jan 1, 2026Abhiram Bellur, Mohammed Raihan Ullah, Dima Golubenko +10Automated Code RefactoringTool-Using Agents

  3. AGAPI-Agents: An Open-Access Agentic AI Platform for Accelerated Materials Design on AtomGPT.org

    Dec 12, 2025Jaehyung Lee, Justin Ely, Kent Zhang +3AI Agents for Scientific DiscoveryLLM Agent Evaluation

  4. PPTArena: A Benchmark for PowerPoint Editing

    Dec 2, 2025Michael Ofengenden, Yunze Man, Ziqi Pang +2LLM Agent EvaluationAI Agent Benchmarks

  5. Check Yourself Before You Wreck Yourself: Selectively Quitting Improves LLM Agent Safety

    Oct 18, 2025Vamshi Krishna Bonagiri, Ponnurangam Kumaragurum, Khanh Nguyen +1LLM Agent EvaluationTool-Using Agents