Ben He

LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?

Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models

RefCritic: Training Long Chain-of-Thought Critic Models with Refinement Feedback

SAISA: Towards Multimodal Large Language Models with Both Training and Inference Efficiency

Rethinking Reward Model Evaluation: Are We Barking up the Wrong Tree?

DiffLM: Controllable Synthetic Data Generation via Diffusion Language Models

On-Policy Fine-grained Knowledge Feedback for Hallucination Mitigation