PLAY2PROMPT: Zero-shot Tool Instruction Optimization for LLM Agents via Tool Play
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Layout and Task Aware Instruction Prompt for Zero-shot Document Image Question Answering
Layout-aware pre-trained models has achieved significant progress on document image question answering. They introduce extra learnable modules into existing language models to capture layout information within document i…
Optical Character Recognition (OCR)Question AnsweringVisual Question Answering (VQA)Zero-Shot LearningRole-Play Zero-Shot Prompting with Large Language Models for Open-Domain Human-Machine Conversation
Recently, various methods have been proposed to create open-domain conversational agents with Large Language Models (LLMs). These models are able to answer user queries, but in a one-way Q&A format rather than a true con…
Instruction FollowingCan Prompting LLMs Unlock Hate Speech Detection across Languages? A Zero-shot and Few-shot Study
Despite growing interest in automated hate speech detection, most existing approaches overlook the linguistic diversity of online content. Multilingual instruction-tuned large language models such as LLaMA, Aya, Qwen, an…
DiversityHate Speech DetectionGPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction
This paper aims to efficiently enable Large Language Models (LLMs) to use multimodal tools. Advanced proprietary LLMs, such as ChatGPT and GPT-4, have shown great potential for tool usage through sophisticated prompt eng…
Image GenerationInstruction FollowingLanguage ModelingLanguage Modelling+2Conversational Prompt Engineering
Prompts are how humans communicate with LLMs. Informative prompts are essential for guiding LLMs to produce the desired output. However, prompt engineering is often tedious and time-consuming, requiring significant exper…
Prompt Engineering