AI.info

Haitao Mi

Explore Haitao Mi on AI.info.

• Verified Critical Step Optimization for LLM Agents
• Inference-Time Scaling of Verification: Self-Evolving Deep Research Agents via Test-Time Rubric-Guided Verification
• Stable and Efficient Single-Rollout RL for Multimodal Reasoning
• DeepCompress: A Dual Reward Strategy for Dynamically Exploring and Compressing Reasoning Chains