My research focuses on continual learning agents with advanced social intelligence. I work on:
- Reasoning about Human Interaction: MindZero (ICML 2026); AutoToM (NeurIPS 2025 Spotlight); MuMA-ToM (AAAI 2025 Oral); MMToM-QA (ACL 2024 Outstanding Paper Award)
- Learning from Human Interaction: ThoughtTrace (ICML 2026 RLxF Best Paper Award), RLHI (2025)
- Self-Improvement and Co-Improvement with Humans: SPICE (2025), OS-Genesis (ACL 2025)