Adversarial Closed-Loop Curriculum for Evolving Role-Playing Agents
Source
Zheng Zhang, Liu Liu, Qi Chai, Deheng Ye, Peilin Zhao, Mao Zheng, Hao Wang
Author
Zheng Zhang, Liu Liu, Qi Chai, Deheng Ye, Peilin Zhao, Mao Zheng, Hao Wang
Date
Key takeaways · AI-distilled
AdvRole alternates two components: an Actor that learns to role-play and a Rewriter that edits character profiles and dialogue contexts into scenarios that are hard for the current Actor.
The Rewriter is rewarded by the performance gap, favoring rewrites that lower the Actor's score relative to the original scenario, so the scenario pool keeps shifting toward under-mastered regions of the character-context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → space.
The authors report consistent gains over baselines on three role-playing benchmarks in English and Chinese plus a new multilingual benchmarkA standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.Full definition → they release; the abstract does not give margins.
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.
Why it matters
Addresses a real limitation in RL training for persona/role-play agents, that static scenario pools stop challenging the AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → as it improves, with a curriculum that adapts alongside it.
articleDeepInstructor: An Agentic AI Instructor for Experience-Driven Idea EvaluationRongcan Pei, Fang Guo, Qinglin Qi, Qi Zhu, Yun Luo, Jianhao Yan, Minjun Zhu, Qiujie Xie, Dehong Zheng, Yue Zhang
articleCoaching Qwen3 Coder 30B to Think Like a CodeClash Arena AgentIvy Ning Zhang
articleSelf-Evolving Embodied Agents via Skill-Harness EvolutionPeidong Wang, Zhiming Ma, Ying Chang, Xufang Luo, Xiaocui Yang, Shi Feng, Yuqing Yang, Dongsheng Li