mlsanityData to 7 Oct 2026

PLAY2PROMPT: Zero-shot Tool Instruction Optimization for LLM Agents via Tool Play

arXiv 2503.14432 ↗First posted 18 Mar 2025cs.CL cs.AI cs.LGcited by 14

On the map: LLM agents and tool use → Tool learning and function calling

Abstract (arXiv)

Large language models (LLMs) are increasingly integrated with specialized external tools, yet many tasks demand zero-shot tool usage with minimal or noisy documentation. Existing solutions rely on manual rewriting or labeled data for validation, making them inapplicable in true zero-shot settings. To address these challenges, we propose PLAY2PROMPT, an automated framework that systematically "plays" with each tool to explore its input-output behaviors. Through this iterative trial-and-error process, PLAY2PROMPT refines tool documentation and generates usage examples without any labeled data. These examples not only guide LLM inference but also serve as validation to further enhance tool utilization. Extensive experiments on real-world tasks demonstrate that PLAY2PROMPT significantly improves zero-shot tool performance across both open and closed models, offering a scalable and effective solution for domain-specific tool integration.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use. Builds on 23 of its 48 references that are in the map. First posted on arXiv 18 Mar 2025.

Builds on

23 of 48 references.

Closest ancestors · 9

Same direction, newest first

  1. 2024From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions10 Oct
  2. 2024ToolACE: Winning the Points of LLM Function Calling2 Sep
  3. 2024EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instruction11 Jan
  4. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs31 Jul
  5. 2023GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction30 May
  6. 2023Large Language Models as Tool Makers26 May
  7. 2023Gorilla: Large Language Model Connected with Massive APIs24 May
  8. 2023ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings19 May
  9. 2023Toolformer: Language Models Can Teach Themselves to Use Tools9 Feb

Other references · 14

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  5. 2022LaMDA: Language Models for Dialog Applicationscited by 1,218
  6. 2023Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Modelscited by 659
  7. 2023Automatic Prompt Optimization with "Gradient Descent" and Beam Searchcited by 628
  8. 2023ViperGPT: Visual Inference via Python Execution for Reasoningcited by 591
  9. 2022Visual Programming: Compositional visual reasoning without trainingcited by 507
  10. 2019Learning Loss for Active Learningcited by 335
  11. 2023PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimizationcited by 226
  12. 2023TaskBench: Benchmarking Large Language Models for Task Automationcited by 138
2 more
  1. 2023ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Searchcited by 103
  2. 2023Natural Language Embedded Programs for Hybrid Language Symbolic Reasoningcited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 12.

14 papers.

Sort:

By area:

  1. 2025A Survey of Context Engineering for Large Language Modelscited by 120
  2. 2026TimeART: Towards Agentic Time Series Reasoning via Tool-Augmentationcited by 25
  3. 2026The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestrationcited by 11
  4. 2025Don't Adapt Small Language Models for Tools; Adapt Tool Schemas to the Modelscited by 6
  5. 2026Self-Improvement of Large Language Models: A Technical Overview and Future Outlookcited by 5
  6. 2026SkillsInjector: Dynamic Skill Context Construction for LLM Agentscited by 5
  7. 2026Learning to Rewrite Tool Descriptions for Reliable LLM-Agent Tool Usecited by 4
  8. 2026OpaqueToolsBench: Learning Nuances of Tool Behavior Through Interactioncited by 3
  9. 2026Beyond Single-Shot: Multi-step Tool Retrieval via Query Planningcited by 2
  10. 2026AgentSearchBench: A Benchmark for AI Agent Search in the Wildcited by 1
  11. 2026A Single Rewrite Suffices: Empirical Lessons from Production Skill Description Optimizationcited by 0
  12. 2026ToolAtlas: Learning Once, Reusing Everywhere with Tool-Side Memorycited by 0
2 more
  1. 2026AISE-Bench: A Full-Cycle Curated Benchmark for Information Seeking on Academic Knowledge Graphscited by 0
  2. 2026DOCSCHISEL: Adaptive Tool Documentation Optimization Framework for LLM Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026ToolMenuBench: Benchmarking Tool-Menu Filtering Strategies for Reliable and Efficient LLM Agents
  2. 2025Dynamic System Instructions and Tool Exposure for Efficient Agentic LLMs
  3. 2026JTPRO: A Joint Tool-Prompt Reflective Optimization Framework for Language Agents
  4. 2026Action-Space Shaping for LLM Agents: Measuring and Mitigating Tool-Schema Bias
  5. 2026Gecko: A Simulation Environment with Stateful Feedback for Refining Agent Tool Calls
  6. 2024LLM With Tools: A Survey
  7. 2026Are Tools All We Need? Unveiling the Tool-Use Tax in LLM Agents
  8. 2026Skill Weaving: Efficient LLM Improvement via Modular Skillpacks