collaborators

10 papers

cs.CL2026

: A Generalist Value Model for Any Policy at State Zero

Yi-Kai Zhang, Zhiyuan Yao, Hongyan Hao +6

Policy gradient methods rely on a baseline to measure the relative advantage of an action, ensuring the model reinforces behaviors that outperform its current average capability. I…

cs.AI2026

LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning

Jianing Wang, Jianfei Zhang, Qi Guo +24

We introduce LongCat-Flash-Prover, a flagship 560-billion-parameter open-source Mixture-of- Experts (MoE) model that advances Native Formal Reasoning in Lean4 through agentic tool-…

cs.AI2026

Can RL Improve Generalization of LLM Agents? An Empirical Study

Zhiheng Xi, Xin Guo, Jiaqi Liu +11

Reinforcement fine-tuning (RFT) has shown promise for training LLM agents to perform multi-turn decision-making based on environment feedback. However, most existing evaluations re…

cs.LG2026

: Generalist Value Model as a Prior for Sparse RL Rollouts

Yi-Kai Zhang, Yueqing Sun, Hongyan Hao +4

In Reinforcement Learning with Verifiable Rewards (RLVR), constructing a robust advantage baseline is critical for policy gradients, effectively guiding the policy model to reinfor…

cs.CL2026

AMemGym: Interactive Memory Benchmarking for Assistants in Long-Horizon Conversations

Cheng Jiayang, Dongyu Ru, Lin Qiu +4

Long-horizon interactions between users and LLM-based assistants necessitate effective memory management, yet current approaches face challenges in training and evaluation of memor…

cs.LG2026

TopoCurate:Modeling Interaction Topology for Tool-Use Agent Training

Jinluan Yang, Yuxin Liu, Zhengyu Chen +7

Training tool-use agents typically relies on outcome-based filtering: Supervised Fine-Tuning (SFT) on successful trajectories and Reinforcement Learning (RL) on pass-rate-selected…