Asynchronous reinforcement-learning post-training of large language models is computationally efficient but inherently off-policy: the learner updates on rollouts generated by a stale policy, while correcting this mismatch requires importance weights that can be extremely heavy-tailed. A small number of trajectories ma...
This work introduces budgeted KV-cache repair: recovering task performance by recomputing a user-chosen fraction of the retained suffix, and finds that refreshing coherent regions can substantially outperform refreshing isolated tokens.
Han Yu, Wen-Hui Zhu, Jincheng Cao et al.· 0 citations
Multi-teacher on-policy distillation (MOPD) is used in two settings. In common-domain composition, several teachers score each student rollout from one prompt domain and their signals form a single target; in routed-domain distillation, prompts from different domains are assigned to the corresponding specialist. Both s...
Yuanda Xu, He-Jian Sang, Zheng-Ze Zhou et al.· 0 citations
Hierarchical reinforcement learning improves long-horizon control by organizing primitive actions around persistent subgoals and assigning credit at multiple temporal scales. Recent hierarchical language agents bring these benefits to interactive tasks by explicitly separating subgoal planning from action execution. We...
AvoKV-E is introduced, a training-free eviction policy that first delays eligibility for recent states and then ranks eligible entries using candidate-normalized read pressure, key redundancy, and value-payload potential, which shows that long-reasoning KV eviction should preserve not only keys that are likely to be re...
Han Yu, Wen-Hui Zhu, Xi-Wen Chen et al.· 0 citations
Segment-level Hindsight Advantage Reweighting for Policy Optimization (SHARPO), a credit-assignment mechanism that refines Group Relative Policy Optimization at the level of environment-facing segments that outperforms existing baselines on the ALFWorld and WebShop benchmarks.
Xin-Chen Du, Zheng-Ze Zhou, Wen-Hui Zhu et al.· 0 citations
TREK (Teacher-Routed Exploration via Forward KL), a simple staged procedure that uses distillation not for imitation but for exploration support expansion, achieves high success rates early in training while unaided GRPO requires substantially more optimization steps to reach comparable levels.