MADS：用于构建鲁棒对话智能体的多智能体对话模拟
MADS: Multi-Agent Dialog Simulation for Robust Conversational Agents
AI总结：
针对现有函数调用基准对抗性对话轨迹代表性不足的问题，提出MADS多智能体对话模拟流水线，构建含66%易出错场景的MADS-Bench基准，结合SFT与RLVR训练方法提升对话智能体鲁棒性。
摘要：
面向任务的对话智能体在实际场景中仍较为脆弱，尤其是当用户表现出非合作行为时。现有的函数调用基准对对抗性对话轨迹的代表性不足，从而限制了开发鲁棒智能体可用的训练资源。我们提出MADS（Multi-Agent Dialog Simulation，多智能体对话模拟），这是一种生成结构化、多样化对话轨迹的合成数据生成流水线。我们注入对抗性对话，生成能捕捉现实中不理想路径的经验证的对话轨迹。利用MADS，我们构建了MADS-Bench：一个涵盖6个领域、55个角色设定、1095次对话的基准，其中约66%的对话包含易出错的对话场景。我们采用结合监督微调（SFT）与带可验证奖励的强化学习（RLVR）的两阶段训练方法，评估训练后模型的鲁棒性。
英文摘要：
Task-oriented conversational agents remain fragile under realistic conditions, especially when users exhibit non-cooperative behavior. Existing function-calling benchmarks underrepresent adversarial conversation trajectories, thereby limiting the training resources available for developing robust agents. We present MADS (Multi-Agent Dialog Simulation), a synthetic data generation pipeline that produces structured, diverse dialogue trajectories. We inject adversarial conversation, producing validated conversation trajectories that capture realistic, unhappy paths. Using MADS, we construct MADS-Bench: a benchmark spanning six domains, 55 personas, and 1095 conversations, with approximately 66% of conversations containing failure-prone conversation scenarios. We evaluate the robustness of the trained models using a two-stage training approach that combines supervised fine-tuning (SFT) and reinforcement learning with verifiable rewards (RLVR).
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
