OptEP is developed, a scalable continuous relaxation that directly optimizes differentiable expert-selection variables, followed by a lightweight reconstruction-based update of the retained expert weights, demonstrating that reconstruction-driven expert selection and weight adaptation can preserve substantially more of...
Jelena Markovic-Voronov, P. Prastakos, Kayhan Behdin et al.· 0 citations
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...
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
LatentPress is introduced, which writes conversational histories and long documents into a third representation: continuous memory tokens that a frozen decoder reads directly through its input-embedding interface, with no text reconstruction at inference.
Yuanda Xu, Zheng-Ze Zhou, He-Jian Sang et al.· 1 citation
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.