Skill-policy co-evolution, in which an agent's policy model and its skill bank improve each other during training, is a promising paradigm for self-improving agents. Current evaluations score the co-evolved policy on the final bank it trained with (the delivered bank). After deployment, however, skills may be rewritten...
Yu-Jie Feng, Xiao-Bin Wang, Jin-Luan Yang et al.· 0 citations
EvoRubric is proposed, a co-evolutionary RL framework that combines criterion-validity feedback, response discrimination, and peer agreement to learn rubrics for open-ended generation and improves over matched static and external evolving-rubric baselines across five benchmarks in Medical, Writing, and Science.
Analysis of rubric-grounded credit suggests more efficient evidence acquisition and higher-quality reports under limited research-turn budgets, motivating the extension of rubric-grounded process supervision to a broader range of rubric-based tasks.
Ying-Jian Zhu, Zhen-Yi Wang, Jia-Xing Guo et al.· 0 citations
This work introduces two exact, gradient-equivalent corrections: LogitTree, a segmented K-forward traversal, and a packed 4D attention mask, and proposes SDCC (Self-Distillation for Conditioning Consistency), a single-backward-pass variational relaxation.
J. Zinco, Xun-Jie Zhu, Shen Huang et al.· 0 citations
Experimental results show that although current agents can reliably uncover the problems exposed by alerts, they struggle to proactively investigate the disk for silent intrusions and to produce comprehensive, verified remediation plans, with no model achieving complete detection and remediation on any single range.
Le-Han Wang, Boli Chen, Ruixue Ding et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
