activity
20242026
most citedContextual Rollout Bandits for Reinforcement Learning with Verifiable Rewards

1 citations · 1 across the 14 of their papers we have counts for

collaborators

38 papers

cs.CL2026

HiDiffTIR: Hierarchical Difficulty-Aware Policy Optimization for Multi-Turn Tool-Integrated Reasoning

Yucan Guo, Xiaohan Wang, Miao Su +8

Tool-Integrated Reasoning (TIR) is a fundamental capability for LLM agents to solve complex tasks by interacting with external tools iteratively. Reinforcement Learning (RL) has be…

cs.LG2026

Toward Plasticity-Preserving KL Regularization for Capability Retention in LLM Reinforcement Learning

Li Wang, Xiaodong Lu, Xiaohan Wang +4

Reinforcement learning (RL) has become a central paradigm for large language model (LLM) post-training, but optimization toward new objectives can degrade capabilities already pres…

cs.CL2026

UniMem: Complementary Episodic-to-Parametric Memory for Boundary-Agnostic Task Streams

Siyu Xia, Chenheng Zhang, Yanting Wu +8

Memory is essential for LLM agents to accumulate task experience and reuse task-specific execution strategies. However, real-world deployment over boundary-agnostic and evolving ta…

cs.LG2026

Learning from Own Solutions: Self-Conditioned Credit Assignment for Reinforcement Learning with Verifiable Rewards

Yingyu Shan, Yuhang Guo, Zihao Cheng +7

Reinforcement learning with verifiable rewards (RLVR) has driven substantial progress in training LLMs for reasoning tasks, but representative methods such as GRPO assign uniform c…

cs.LG2026

PolarQuant: Leveraging Polar Transformation for Efficient Key Cache Quantization and Decoding Acceleration

Songhao Wu, Ang Lv, Xiao Feng +5

The KV cache in large language models is a dominant factor in memory usage, limiting their broader applicability. Quantizing the cache to lower bit widths is an effective way to re…

cs.CL2026

Are Full Rollouts Necessary for On-Policy Distillation?

Yaocheng Zhang, Jiajun Chai, Yuqian Fu +7

On-policy distillation (OPD) provides dense teacher feedback along student-generated rollouts rather than fixed teacher traces and has emerged as a promising post-training paradigm…