Lune

ACL Findings2025

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

Wei Fang, Yang Zhang, Kaizhi Qian, James R. Glass, Yada Zhu

Abstract

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 zeroshot tool performance across both open and closed models, offering a scalable and effective solution for domain-specific tool integration 1 .

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Gorilla: Large Language Model Connected with Massive APIs cites Toolformer: Language Models Can Teach Themselves to Use Tools
  • Gorilla: Large Language Model Connected with Massive APIs cites HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face
  • Reflexion: language agents with verbal reinforcement learning cites Self-Refine: Iterative Refinement with Self-Feedback
  • Reflexion: language agents with verbal reinforcement learning cites Toolformer: Language Models Can Teach Themselves to Use Tools
  • Reflexion: language agents with verbal reinforcement learning cites HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face
  • HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face cites Toolformer: Language Models Can Teach Themselves to Use Tools
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. Don't Adapt Small Language Models for Tools; Adapt Tool Schemas to the ModelsJonggeun Lee, Woojung Song, Jongwook Han, Haesung Pyun et al.ACL 2026 · 2 citations

Builds on19

  1. Toolformer: Language Models Can Teach Themselves to Use ToolsTimo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu et al.NeurIPS 2023 · 5,989 citations
  2. Reflexion: language agents with verbal reinforcement learningNoah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan et al.NeurIPS 2023 · 5,828 citations
  3. Self-Refine: Iterative Refinement with Self-FeedbackAman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan et al.NeurIPS 2023 · 4,972 citations
  4. HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging FaceYongliang Shen, Kaitao Song, Xu Tan, Dongsheng Li et al.NeurIPS 2023 · 1,778 citations
  5. Gorilla: Large Language Model Connected with Massive APIsShishir G. Patil, Tianjun Zhang, Xin Wang, Joseph E. GonzalezNeurIPS 2024 · 1,715 citations

Related papers

  1. From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven InteractionsChangle Qu, Sunhao Dai, Xiaochi Wei, Hengyi Cai et al.ICLR 2025
  2. Tool Learning in the Wild: Empowering Language Models as Automatic Tool AgentsZhengliang Shi, Shen Gao, Lingyong Yan, Yue Feng et al.WWW 2025 · 59 citations
  3. ORPP: Self-Optimizing Role-playing Prompts to Enhance Language Model CapabilitiesYifan Duan, Yihong Tang, Kehai Chen, Liqiang Nie et al.EMNLP 2025
  4. PromptWizard: Optimizing Prompts via Task-Aware, Feedback-Driven Self-EvolutionEshaan Agarwal, Raghav Magazine, Joykirat Singh, Vivek Dani et al.ACL Findings 2025 · 2 citations
  5. GOAT: A Training Framework for Goal-Oriented Agent with ToolsHyunji Min, Sangwon Jung, Junyoung Sung, Dosung Lee et al.ACL Findings 2026
Dusk over the sea between two cliffs drawn in fine vertical lines