Zhengru Fang
2 papers · Latest:
Machine Learning
Self-Induced Outcome Potential: Turn-Level Credit Assignment for Agents without Verifiers
SIOP provides turn-level credit assignment for LLM agents without verifiers by clustering final answers into latent outcome states.
2605.04984
RoboticsAgent-Centric Visual Reinforcement Learning under Dynamic Perturbations
ACO-MoE robustifies visual RL against dynamic perturbations by using agent-centric restoration experts, achieving near clean performance on a new benchmark.
2604.24661
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.