Harness evolution improves LLM agents by learning from execution trajectories, but existing experience- and skill-based methods are less effective on long-horizon tasks. As interactions grow, useful evidence can be buried by redundant or outdated context, making context management itself a key bottleneck. We introduce...
Wei-Yuan Li, Jing-Heng Xu, Ai-Li Chen et al.· 0 citations
Maintaining persona consistency across multi-turn dialogues remains a core challenge for role-playing language models. Off-policy distillation from external teachers incurs distribution mismatch that compounds across dialogue turns, while reinforcement learning struggles with reward ambiguity inherent in subjective per...
Rui Xu, Yikai Zhang, Ai-Li Chen et al.· 0 citations
Open-ended reinforcement learning often relies on rubric-based rewards for tasks without directly verifiable answers. Yet the policy and reward system form a dynamic feedback loop: as the policy optimizes the current reward, an initially useful reward system may become unreliable due to reward hacking or reduced respon...
Weiyuan Li, Aili Chen, Xin-Tao Wang et al.· 0 citations
This work proposes SocialRL, a multi-turn reinforcement learning framework using PPO that propagates delayed outcome rewards back to each turn, enabling long-horizon planning and demonstrates the effectiveness of SocialRL across synthetic and real social scenes, as well as standard and challenging social scenarios.
Jia-Ning Wang, Xin-Tao Wang, Ai-Li Chen et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
