{"ID":2876481,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.00482","arxiv_id":"2509.00482","title":"Talk Less, Call Right: Enhancing Role-Play LLM Agents with Automatic Prompt Optimization and Role Prompting","abstract":"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","short_abstract":"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) whi...","url_abs":"https://arxiv.org/abs/2509.00482","url_pdf":"https://arxiv.org/pdf/2509.00482v2","authors":"[\"Saksorn Ruangtanusak\",\"Pittawat Taveekitworachai\",\"Kunat Pipatanakul\"]","published":"2025-08-30T12:45:36Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.HC\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":610300,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2876481,"paper_url":"https://arxiv.org/abs/2509.00482","paper_title":"Talk Less, Call Right: Enhancing Role-Play LLM Agents with Automatic Prompt Optimization and Role Prompting","repo_url":"https://github.com/scb-10x/apo","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}