English(EN) Stop Training Against Soft Users: Mentalized Adversarial Self-Play for Proactive Dialogue

新的MASP框架训练AI对话代理对抗理性抵抗

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-16 04:00

研究人员开发了一个名为MASP（心智化对抗性自我博弈）的新框架，以改进主动对话代理。与以往训练对抗过于顺从的模拟器的旧方法不同，MASP将对话视为系统与理性抵抗用户之间的博弈。这种方法模拟了用户不断变化的心智状态，并使用自我博弈更新来训练系统和用户策略，使代理能够更有效地对抗难缠的用户。与标准的监督微调和仅规划器方法相比，MASP在各种基准测试中都显著提高了成功率并减少了对话轮数。 AI

影响通过训练对抗性用户来增强AI对话代理的鲁棒性，有可能在复杂交互中提高任务完成率。

排序理由详细介绍AI对话代理新框架的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 17 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍AI对话代理新框架的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Zanwu Liu, Dan Zhang, Xiaodi Wang, Yongbo Mao, Xiaoyang Guo, Yonglin Wu, Peiyue Jiang, Yangyang Wei, Zecheng Lin · 2026-10-16 04:00

停止针对“软用户”进行训练：心智化对抗性自博弈以实现主动对话

arXiv:2610.21156v1 Announce Type: new Abstract: Proactive dialogue agents must guide multi-turn interactions toward task goals while adapting to users whose intentions and attitudes evolve. Existing planners improve system side action selection through search, learned policies, o…

本文如何被排名

报道来源 [1]

停止针对“软用户”进行训练：心智化对抗性自博弈以实现主动对话

相关实体

相关话题