Publication

2026

arXiv:2610.06563 (Preprint)

HERA: Harness-Environment Co-Evolution for Reliable Agentic Abstention

Han Luo* , Bingbing Wen* , Guang Yang , Zora Zhiruo Wang , Pan Lu , Lucy Lu Wang (* co-first authorship)

Project Preprint arXiv Code

NeurIPS 2026 (Accepted)

Agentic Abstention: Do Agents Know When to Stop Instead of Act?

Han Luo* , Bingbing Wen* , Lucy Lu Wang (* co-first authorship)

Project PDF arXiv Code Demo

ICML 2026 (arXiv:2605.10118)

Plan in Sandbox, Navigate in Open Worlds: Learning Physics-Grounded Abstracted Experience for Embodied Navigation

Zhixuan Shen , Jiawei Du , Ziyu Guo , Han Luo , Lilan Peng , Joey Tianyi Zhou , Haonan Luo , Tianrui Li

Project PDF arXiv

Findings of ACL 2026

SPASM: Stable Persona-driven Agent Simulation for Multi-turn Dialogue Generation

Han Luo , Guy Laban

Project PDF Code

ACL 2026 System Demonstrations

DialogGuard: Multi-Agent Psychosocial Safety Evaluation Interface of Sensitive LLM Responses

Han Luo , Guy Laban

Project PDF Demo