Rubric4Setwise is proposed, a training-free method that converts rubric-based evaluation criteria into document set selection signals, achieving the best downstream generation performance with fewer documents and search rounds, validating the effectiveness of closing the loop from evaluation to optimization.
Kai-Lin Jiang, Lei Liu, Jian-Fei Xi et al.· arXiv.org· 3 citations
Experimental results demonstrate that DRG-MAPPO achieves a state-of-the-art win rate of 87%, suggesting that the framework effectively balances relational modeling, interpretability, and optimization stability for cooperative air combat.
Junlin Liu, Cheng-Wei Li, Yang Gao et al.· 0 citations
DecoEvo (Decoupled Co-Evolution), which co-evolves a solver skill and a rubric-generator skill under decoupled objectives without using gold rubrics during optimization, is introduced.
Jiangwang Chen, Zixin Song, Junlin Liu et al.· arXiv.org· 3 citations
Multi-Agent Protocol Distillation (MAPD), a joint distillation and RL framework uses a structured, style-normalized protocol as an intermediate representation that generalizes robustly across diverse proprietary teachers while effectively mitigating the student policy from style drift and verbosity degeneration.
Junlin Liu, Jiangwang Chen, Zixin Song et al.· arXiv.org· 6 citations
PReM (Preserve and Refresh Memory), a context-compression framework that maintains the long context as the model's internal layer-wise KV memory and learns what to preserve and when to refresh it, is introduced.
Bohan Yu, Lei Shen, Chenxi Zhou et al.· arXiv.org· 0 citations
ClawTrack is presented, a dual-assessment benchmark that simultaneously measures what an agent achieves (Task Score) and how it achieves it (Process Score) and finds that process scores effectively attribute success and failure to specific reasoning dimensions, filtering lucky passes invisible to outcome-only evaluatio...
Xingjian Wu, Xuhan Zhu, Xing-Chen Liu et al.· arXiv.org· 0 citations
Persistent Consistency Self-Distillation (PCSD) is proposed, which derives token-level distillation weights from the local persistence of teacher-favoring signals, and combines adaptive windows with exponentially decayed aggregation to capture persistent relative teacher support.
Chun-Ji Lv, Yang-Guang Wei, Junlin Liu et al.· 2 citations
Contrastive Reinforced Policy Optimization (CRPO) is introduced, which reformulates agentic OPSD from a contrastive learning perspective, and conducts group-wise contrast to preserve reliable, fine-grained optimization signals.
Xingjian Wu, Junlin Liu, Xing-Chen Liu et al.· arXiv.org· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
