collaborators
Showing cs.LGShow all

11 papers · 1 filter

cs.LG2026

CoMem: Context Management with A Decoupled Long-Context Model

Yuwei Zhang, Chengyu Dong, Shuowei Jin +11

Context management enables agentic models to solve long-horizon tasks through iterative summarization of previous interaction histories. However, this process typically incurs subs…

cs.LG2026

Learning with Rare Success but Rich Feedback via Reflection-Enhanced Self-Distillation

Yuwei Zhang, Sha Li, Changlong Yu +9

Enabling Large Language Models (LLMs) to continuously improve from environmental interactions is a central challenge in post-training. While on-policy self-distillation offers a pr…

cs.LG2026

Rethinking Importance Sampling in LLM Policy Optimization: A Cumulative Token Perspective

Yuheng Zhang, Chenlu Ye, Shuowei Jin +4

Reinforcement learning, including reinforcement learning with verifiable rewards (RLVR), has emerged as a powerful approach for LLM post-training. Central to these approaches is th…

cs.LG2026

Beyond Test-Time Memory: State-Space Optimal Control for LLM Reasoning

Peihao Wang, Shan Yang, Xijun Wang +8

Associative memory has long underpinned the design of sequential models. Beyond recall, humans reason by projecting future states and selecting goal-directed actions, a capability…

cs.LG2026

Approximation of Log-Partition Function in Policy Mirror Descent Induces Implicit Regularization for LLM Post-Training

Zhenghao Xu, Qin Lu, Changlong Yu +1

Policy mirror descent (PMD) provides a principled framework for reinforcement learning (RL) by iteratively solving KL-regularized policy improvement subproblems. While this approac…

cs.LG2026

HeaPA: Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learning

Weiqi Wang, Xin Liu, Binxuan Huang +13

RLVR has become a standard recipe for training LLMs on reasoning tasks with verifiable outcomes, but when rollout generation dominates the cost, efficiency hinges on which prompts…