AI.info

Huan Sun

Explore Huan Sun on AI.info.

• REMem: Reasoning with Episodic Memory in Language Agent
• When Actions Go Off-Task: Detecting and Correcting Misaligned Actions in Computer-Use Agents
• When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents
• Accelerating Scientific Discovery with Autonomous Goal-evolving Agents
• Evaluating Large Language Models in Scientific Discovery
• Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agents
• ScholarEval: Research Idea Evaluation Grounded in Literature
• Agent Learning via Early Experience