通过规则化提示优化，让对话智能体更精准扮演角色并合理使用工具。
Talk Less, Call Right: Enhancing Role-Play LLM Agents with Automatic Prompt Optimization and Role Prompting
- 设计角色卡与场景合约，强制规范函数调用
- 在CPDC挑战中得分0.571，优于零样本基线0.519
- 适合需要可靠角色扮演的对话系统开发者
本报告研究了如何通过提示工程，使具备工具调用能力的大语言模型在2025年常识人格对话挑战（CPDC）的API赛道中担任角色扮演对话代理。当前代理常出现过度发言（长回复）且未能根据人格有效使用工具（如调用不存在的函数或冗余调用），影响表现。本文探索四种提示方法：基础角色提示、改进角色提示、自动提示优化（APO）及基于规则的角色提示（RRP）。RRP通过角色卡/场景合约设计与严格函数调用约束，取得最佳成绩——总分0.571，较零样本基线0.519显著提升。结果表明，规则化设计比复杂优化方法更有效。为支持后续研究，作者开源所有最优提示及APO工具代码，项目地址见https://github.com/scb-10x/apo。
原文摘要 · Abstract (English)
This report investigates approaches for prompting a tool-augmented large language model (LLM) to act as a role-playing dialogue agent in the API track of the Commonsense Persona-grounded Dialogue Challenge (CPDC) 2025. In this setting, dialogue agents often produce overly long in-character responses (over-speaking) while failing to use tools effectively according to the persona (under-acting), such as generating function calls that do not exist or making unnecessary tool calls before answering. We explore four prompting approaches to address these issues: 1) basic role prompting, 2) improved role prompting, 3) automatic prompt optimization (APO), and 4) rule-based role prompting. The rule-based role prompting (RRP) approach achieved the best performance through two novel techniques-character-card/scene-contract design and strict enforcement of function calling-which led to an overall score of 0.571, improving on the zero-shot baseline score of 0.519. These findings demonstrate that RRP design can substantially improve the effectiveness and reliability of role-playing dialogue agents compared with more elaborate methods such as APO. To support future efforts in developing persona prompts, we are open-sourcing all of our best-performing prompts and the APO tool Source code is available at https://github.com/scb-10x/apo
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。