FACTOR is introduced, which uses checkpoint-calibrated TD residuals to assign per-action credits that telescope to the trajectory advantage, and feedback-conditioned teacher-student likelihood gaps to allocate each credit across the realized action tokens.
Li-Chao Ma, Yang Sun, Shuai Zhao et al.· 3 citations
SelSkill is proposed, a dual-granularity preference-learning framework for selective skill invocation that formulates skill use as a skill-or-skip decision, uses predictive uncertainty to prioritize candidate decision points, and constructs controlled invoke-skip preference pairs from shared trajectory prefixes.
Chishui Chen, Jiaye Lin, Te Sun et al.· arXiv.org· 1 citation· ⚡1
Comparative experiments conducted on four checkpoints from a single model family validate a concise and effective scaling trend: end-to-end detection correctness exhibits a complexity-differentiated scaling pattern, and the complexity metric derived from the constraint dependency graph can effectively quantify instance...
Shuai Zhao, Fengmei Ni, Lichao Ma et al.· 0 citations
Observation-Calibrated Self-Distillation (OCSD), which contrasts two structurally matched replay views, Full and Observation-Ablated, to derive an observation residual that discounts score changes shared by the replay scaffold, and applies this residual to modulate token-level GRPO updates at high-uncertainty steps, wh...
Yi Yang, Congming Qin, Xiaodan Liu et al.· 4 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
