Han Luo

Han Luo portrait

I am a third-year undergraduate student in Computer Science at the University of Leeds, UK, and Southwest Jiaotong University, China. My research focuses on reliable agents and recursive self-improvement (RSI).

I am fortunate to work with Prof. Lucy Lu Wang in the LARCH Lab at the University of Washington. Previously, I worked with Prof. Guy Laban in LabaLab at Ben-Gurion University of the Negev and at the University of Cambridge.

NeurIPS 2026 · Sydney 🇦🇺

I'll be there! Open to research internships, collaborations, and coffee chats on reliable agents and RSI. Let's connect

My research explores two closely connected directions:

Reliable Agents
  1. Knowing when to act and when to abstain. Agentic Abstention (NeurIPS 2026) · HERA
  2. Maintaining behavioral consistency and evaluating safety in agent interactions. SPASM (ACL 2026) · DialogGuard (ACL 2026)
  3. Transferring learned experience to open-world embodied navigation. SAGE (ICML 2026)
Recursive Self-Improvement (RSI)
  1. Evolving agent context through lessons learned from interaction trajectories. CONVOLVE (NeurIPS 2026)
  2. Co-evolving agent harnesses and environments through execution feedback. HERA

Selected publications

View all >

HERA

arXiv 2026

Han Luo*, Bingbing Wen*, Guang Yang, Zora Zhiruo Wang, Pan Lu, Lucy Lu Wang

* Equal contribution

Co-evolving agent harnesses and environments for reliable agentic abstention.

Agentic Abstention

NeurIPS 2026

Han Luo*, Bingbing Wen*, Lucy Lu Wang

* Equal contribution

A benchmark and context-engineering study of when LLM agents should stop acting and abstain.

Plan in Sandbox

ICML 2026

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

A physics-grounded sandbox framework for learning abstracted embodied navigation experience.

SPASM

Findings of ACL 2026

Han Luo, Guy Laban

A stability-first framework for persona-driven LLM-LLM dialogue simulation with egocentric context projection.

DialogGuard

ACL 2026 Demo

Han Luo, Guy Laban

A practitioner-facing interface for multi-agent psychosocial safety evaluation of sensitive LLM responses.

News

  • Our HERA preprint on harness–environment co-evolution is now available on arXiv.

  • Agentic Abstention has been accepted to NeurIPS 2026. See ya in Sydney 🇦🇺!

  • I spent two months at LARCH Lab, University of Washington, in Seattle 🇺🇸, working with Prof. Lucy Lu Wang.

  • Plan in Sandbox, Navigate in Open Worlds has been accepted to ICML 2026. See ya in Seoul 🇰🇷!

  • SPASM has been accepted to Findings of ACL 2026. See ya in San Diego 🇺🇸!

  • DialogGuard has been accepted to ACL 2026 System Demonstrations. See ya in San Diego 🇺🇸!

  • I spent two months at LabaLab, Ben-Gurion University of the Negev, in Israel 🇮🇱, working with Prof. Guy Laban.

  • My Cambridge OSRP project received a Best Research Project nomination.

Where to find me

Now Chengdu

Dec 2026 Sydney

Academic Service

ICLR 2027
Reviewer
NeurIPS 2026
Reviewer
CUI 2026
Reviewer
WWW 2026
Reviewer