{"ID":2846761,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.01720","arxiv_id":"2511.01720","title":"Efficient Tool-Calling Multi-Expert NPC Agent for Commonsense Persona-Grounded Dialogue","abstract":"We present a multi-expert system for creating Non-Player Characters (NPCs) capable of both natural dialogue and contextual action execution in interactive environments. Using Qwen3 as the base model and Low-Rank Adaptation (LoRA) adapters, we instantiate three specialists: tool calling, tool-response interpretation, and direct dialogue. Our system comfortably meets the computational efficiency requirements, delivering fast responses and maintaining modest resource usage on L40S GPUs. In the Commonsense Persona-Grounded Dialogue Challenge 2025, our method ranked second overall. Code available at: https://github.com/MahammadNuriyev62/CPDC-challenge-2025-solution/","short_abstract":"We present a multi-expert system for creating Non-Player Characters (NPCs) capable of both natural dialogue and contextual action execution in interactive environments. Using Qwen3 as the base model and Low-Rank Adaptation (LoRA) adapters, we instantiate three specialists: tool calling, tool-response interpretation, an...","url_abs":"https://arxiv.org/abs/2511.01720","url_pdf":"https://arxiv.org/pdf/2511.01720v1","authors":"[\"Mahammad Nuriyev\"]","published":"2025-11-03T16:28:47Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"LoRA\"]","has_code":false,"code_links":[{"ID":607461,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2846761,"paper_url":"https://arxiv.org/abs/2511.01720","paper_title":"Efficient Tool-Calling Multi-Expert NPC Agent for Commonsense Persona-Grounded Dialogue","repo_url":"https://github.com/MahammadNuriyev62/CPDC-challenge-2025-solution","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}