Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Beyond Outcome Rewards: Step-Level Self-Distilled Policy Optimization for Deep Search Agents
Haoze Wu, Chuqiao Kuang, Tianyi Zhuang +1
Deep search agents operate over trajectories spanning dozens of steps, yet standard reinforcement learning provides only a single outcome reward per trajectory, which is far too sp…
cs.LG2025
Mirage or Method? How Model-Task Alignment Induces Divergent RL Conclusions
Haoze Wu, Cheng Wang, Wenshuo Zhao +1
Recent advances in applying reinforcement learning (RL) to large language models (LLMs) have led to substantial progress. In particular, a series of remarkable yet often counterint…
cs.LG2024
GW-MoE: Resolving Uncertainty in MoE Router with Global Workspace Theory
Haoze Wu, Zihan Qiu, Zili Wang +2
Mixture-of-Experts (MoE) has been demonstrated as an efficient method to scale up models. By dynamically and sparsely selecting activated experts, MoE can effectively reduce comput…