activity
20242026
collaborators

24 papers

cs.CL2026

SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning

Jinyang Wu, Shuo Yang, Zhengxi Lu +8

The paper introduces SEED, a framework that extracts reusable natural-language skills from on-policy trajectories and distills them back into the policy to provide dense token-leve…

cs.CV2026

Representation Distribution Matching for One-Step Visual Generation

Lan Feng, Wuyang Li, Eloi Zablocki +2

We elucidate the design space of Representation Distribution Matching (RDM), our name for the paradigm that trains a one-step image generator by matching generated and reference fe…

cs.CL2026

REAR: Test-time Preference Realignment through Reward Decomposition

Fuxiang Zhang, Pengcheng Wang, Chenran Li +6

Aligning large language models (LLMs) with diverse user preferences is a critical yet challenging task. While post-training methods can adapt models to specific needs, they often r…

cs.AI2026

CaveAgent: Transforming LLMs into Stateful Runtime Operators

Maohao Ran, Zhenglin Wan, Cooper Lin +21

LLM-based agents are increasingly capable of complex task execution, yet current agentic systems remain constrained by text-centric paradigms that struggle with long-horizon tasks…

cs.CL2026

OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning

Shuo Yang, Jinyang Wu, Zhengxi Lu +8

Outcome-based reinforcement learning provides a stable optimization backbone for language agents, but its sparse trajectory-level rewards provide little guidance on which intermedi…

cs.LG2026

Training Diffusion Policies via Prior-Mapping Co-Evolution

Chubin Zhang, Zhenglin Wan, Feng Chen +7

Reinforcement learning (RL) faces a persistent tension: policies that are stable to optimize (e.g., Gaussians) are often too simple to represent the multimodal action distributions…