用动态工具裁剪和强化学习提升对话智能体表现
Interactive AI NPCs Powered by LLMs: Technical Report for the CPDC Challenge 2025
- 通过动态工具裁剪与角色信息压缩，优化输入并提升指令执行稳定性
- 采用GRPO强化学习，在小样本下显著改善任务导向对话性能
- 适合关注角色扮演对话系统与高效推理框架的研究者
本报告介绍我队MSRA_SC在常识性角色基础对话挑战（CPDC 2025）中的解决方案与成果。我们提出一种简洁而有效的统一框架，覆盖GPU赛道与API赛道。方法核心包含两个部分：首先，上下文工程通过动态工具裁剪与角色信息截断实现输入压缩，并结合参数归一化、函数合并等后处理技术，辅以人工优化提示，显著提升工具调用稳定性、执行可靠性及角色扮演引导性；其次，在GPU赛道中，我们采用GRPO训练，以奖励信号直接优化，替代监督微调，有效缓解小样本过拟合问题，大幅增强任务导向对话能力。最终评测中，我队在任务2 API赛道排名第一，任务1 API赛道排名第二，任务3 API与GPU赛道均位列第三，验证了方法的有效性。代码已公开于https://gitlab.aicrowd.com/nikoo_yu/cpdc-2025-winning-solution。
原文摘要 · Abstract (English)
This report presents the solution and results of our team MSRA\_SC in the Commonsense Persona-Grounded Dialogue Challenge (CPDC 2025). We propose a simple yet effective framework that unifies improvements across both GPU Track and API Track. Our method centers on two key components. First, Context Engineering applies dynamic tool pruning and persona clipping for input compression, combined with post-processing techniques such as parameter normalization and function merging. Together with manually refined prompts, this design improves tool call stability, execution reliability, and role-playing guidance. Second, in the GPU Track, we further adopt GRPO training, replacing supervised fine-tuning with reinforcement learning directly optimized by reward signals. This mitigates small-sample overfitting and significantly enhances task-oriented dialogue performance. In the final evaluation, our team ranks 1st in Task 2 API, 2nd in Task 1 API, and 3rd in both Task 3 API and GPU track, demonstrating the effectiveness of our approach. Our code is publicly available at https://gitlab.aicrowd.com/nikoo_yu/cpdc-2025-winning-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。