用多LoRA融合提升游戏对话智能体的工具调用与角色扮演能力
Model Fusion with Multi-LoRA Inference for Tool-Enhanced Game Dialogue Agents
- 通过多个LoRA适配器分别处理工具调用、带结果回复和无调用回复
- 在三项任务中分别取得第一、第二、第一的排名，性能领先
- 基于vLLM实现高效多LoRA推理，适合资源受限场景下的对话系统部署
本文介绍的是opdainlp团队在CPDC 2025挑战赛GPU赛道中的解决方案。比赛包含三个任务，旨在构建一个符合角色设定、契合游戏世界观并支持函数调用的游戏中对话AI。考虑到推理阶段的效果、资源与时间限制，我们基于赛事方提供的数据集对部分任务进行了合成数据增强。采用Qwen3-14B模型结合LoRA微调与模型融合策略，在推理时使用集成多个LoRA适配器的基础模型。具体地，比赛中使用三个独立的LoRA适配器分别处理工具调用、含工具调用结果的回复生成以及不含工具调用的回复生成。多LoRA推理通过vLLM实现。最终方案在任务1和任务3中获得第一名，在任务2中获得第二名。
原文摘要 · Abstract (English)
This paper presents the opdainlp team's solution for the GPU track of the CPDC 2025 challenge. The challenge consists of three tasks, aiming to build an in-game conversational AI that adheres to character personas, aligns with the game's worldview, and supports function calling. Considering both effectiveness and resource/time constraints during inference, we synthesized data for some of the tasks based on the datasets provided by the competition organizers. We employed Qwen3-14B with LoRA fine-tuning and model fusion, and utilized a base model integrated with multiple LoRA adapters during inference. Specifically, in the competition, we used three distinct LoRA adapters to handle tool calling, response generation with tool call results, and response generation without tool call results, respectively. MultiLoRA inference was implemented using vLLM. Our solution achieved the first place in Task 1 and Task 3, and the second place in Task 2 of the GPU track.
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。