MADS：面向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 导读

研究团队提出 MADS（Multi-Agent Dialog Simulation）合成数据生成管线，可注入对抗性对话，生成结构化、多样化的对话轨迹，用于训练更鲁棒的对话智能体。基于该管线构建的 MADS-Bench 覆盖 6 个领域、55 种人物设定和 1095 段对话，其中约 66% 包含易失败场景。团队采用 SFT 与 RLVR 两阶段训练评估模型鲁棒性。

正文 · 原文

View PDF HTML (experimental)

Abstract: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).

Comments:	Submitted to Interspeech in February 2026
Subjects:	Computation and Language (cs.CL)
Cite as:	arXiv:2610.12757 [cs.CL]
	(or arXiv:2610.12757v1 [cs.CL] for this version)
	https://doi.org/10.48550/arXiv.2610.12757 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Arkajyoti Chakraborty [view email]
[v1] Thu, 8 Oct 2026 22:08:10 UTC (420 KB)

来源：arXiv cs.CL · arxiv.org