让游戏角色能自然对话并执行任务，响应快资源少。
Efficient Tool-Calling Multi-Expert NPC Agent for Commonsense Persona-Grounded Dialogue
- 用三个专家模块分工：工具调用、回应解析和直接对话。
- 在2025常识角色对话挑战中排名第二，响应速度快。
- 基于Qwen3和LoRA适配，适合游戏开发与交互系统应用。
我们提出一个多专家系统，用于构建能在交互环境中实现自然对话和上下文动作执行的非玩家角色（NPC）。以Qwen3为基础模型，结合低秩适配（LoRA）生成三个专业模块：工具调用、工具响应解析和直接对话。系统在L40S GPU上运行时计算效率高，响应迅速且资源占用小。在2025年常识角色接地对话挑战赛中，该方法取得总体第二名。代码已开源：https://github.com/MahammadNuriyev62/CPDC-challenge-2025-solution/
原文摘要 · Abstract (English)
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/
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。