Dongge Han

Senior Researcher in LLM Agents @ Microsoft Cambridge

2025 Dec | Senior Researcher@Microsoft Cambridge

I got promoted to Senior Researcher (L64).

2024 Jul | Senior Researcher@Microsoft Cambridge

I joined Microsoft as a Senior Researcher (L63) working on exciting applied research projects on LLM Agents.

2023 Aug | Postdoc@University of Edinburgh

I worked as a postdoc on LLM and RL for personalized household robotics at the University of Edinburgh, where I work with Prof. Amos Storkey, Prof. Peter Bell and Dr. Stefano Albrecht.

2022-23 Jul | Applied Scientist II@Amazon

Prior to joining UoE, I worked as an Applied Scientist II on personalized recommendation at Amazon.

2016-22 May | PhD in Computer Science@University of Oxford

I obtained my PhD in Computer Science at the University of Oxford, supervised by Prof. Michael Wooldridge and Prof. Alex Rogers. My research interests include Multiagent Reinforcement Learning, Hierarchical Reinforcement Learning and Game Theory. In particular, my thesis studies Game-theoretic Payoff Allocation in Multiagent Machine Learning Systems.

2019 Jul-Oct | Intern@Microsoft Research Cambridge

I was an Intern at Microsoft Research Cambridge where I worked on ML data valuation with Dr. Sebastian Tschiatschek, Dr. Olya Ohrimenko and Dr. Shruti Tople.

2017 Jul-Oct | Intern@Apple Siri Cambridge

I was an Intern at Apple Siri Cambridge where I worked on ML user simulation in dialogue systems with Dr. Thomas Voice.

2015-16 Sep | MSc in Computer Science@University of Oxford

I obtained MSc in Computer Science (Graduated with Distinction) from the University of Oxford.

2011-15 Jul | BSc in Physics@Hong Kong University of Science and Technology

I obtained a BSc in Physics with a Minor Degree in IT (First class honours) from the Hong Kong University of Science and Technology.

2014 Feb-Jul | Undergraduate Exchange@EPFL

I was an exchange student at EPFL and took courses in Physics and Computer Science.

news

Aug 1, 2023 New Affiliation: I am joining University of Edinburgh as a postdoc research associate, working on NLP and Reinforcement learning for robotics.
Jul 11, 2022 Paper accepted at IEEE Transactions on Artificial Intelligence: Replication Robust Payoff Allocation in Submodular Cooperative Games
Jul 1, 2022 New Affiliation: I am joining Amazon as an Applied Scientist in the Personalization team.
May 14, 2022 Paper accepted at IJCAI’22 (Long Oral): Option Transfer and SMDP Abstraction with Successor Features
Feb 11, 2022 PhD ThesisThesis Defended! :sparkles: :smile:

selected publications

  1. ICML’26
    A Tale of Two Graphs: Separating Knowledge Exploration from Outline Structure for Open-Ended Deep Research
    Shi, Zhuofan, Ma, Ming, Yao, Zekun, Yang, Fangkai, Zhang, Jue, Han, Dongge, Rühle, Victor, Lin, Qingwei, Rajmohan, Saravan, and Zhang, Dongmei
    Forty-Third International Conference on Machine Learning 2026
  2. ICML’26
    Acon: Optimizing context compression for long-horizon llm agents
    Kang, Minki, Chen, Wei-Ning, Han, Dongge, Inan, Huseyin A, Wutschitz, Lukas, Chen, Yanzhi, Sim, Robert, and Rajmohan, Saravan
    Forty-Third International Conference on Machine Learning 2026
  3. AAMAS’26
    Legomem: Modular procedural memory for multi-agent llm systems for workflow automation
    Han, Dongge, Couturier, Camille, Diaz, Daniel Madrigal, Zhang, Xuchao, Rühle, Victor, and Rajmohan, Saravan
    25th International Conference on Autonomous Agents and Multiagent Systems 2026
  4. Arxiv
    Odysseybench: Evaluating llm agents on long-horizon complex office application workflows
    Wang, Weixuan, Han, Dongge, Diaz, Daniel Madrigal, Xu, Jin, Rühle, Victor, and Rajmohan, Saravan
    arXiv preprint arXiv:2508.09124 2025
  5. COLING’25
    Llm-personalize: Aligning llm planners with human preferences via reinforced self-training for housekeeping robots
    Han, Dongge, McInroe, Trevor, Jelley, Adam, Albrecht, Stefano V, Bell, Peter, and Storkey, Amos
    In 2025
  6. AAMAS’22
    Multiagent Model-based Credit Assignment for Continuous Control
    Han, Dongge, Lu, Chris Xiaoxuan, Michalak, Tomasz P., and Wooldridge, Michael
    In The 21st International Conference on Autonomous Agents and Multiagent Systems (AAMAS) 2022
    arXiv
  7. IJCAI’22
    Option Transfer and SMDP Abstraction with Successor Features
    Han, Dongge, and Tschiatschek, Sebastian
    The 31st International Joint Conference on Artificial Intelligence 2022
    arXiv
  8. Oxford
    Game-theoretic payoff allocation in multiagent machine learning systems
    Han, Dongge
    2021
  9. IEEE TAI
    Replication Robust Payoff Allocation in Submodular Cooperative Games
    Han, Dongge, Wooldridge, Michael, Rogers, Alex, Tople, Shruti, Ohrimenko, Olga, and Tschiatschek, Sebastian
    IEEE Transactions on Artificial Intelligence 2022
    arXiv
  10. Inf. Comput.
    Behavioural strategies in weighted Boolean games
    Han, Dongge, Harrenstein, Paul, Nugent, Steven, Philpott, Jonathan, and Wooldridge, Michael
    Information and Computation 2021
    HTML
  11. AAMAS’19
    Multi-Agent Hierarchical Reinforcement Learning with Dynamic Termination
    Han, Dongge, Boehmer, Wendelin, Wooldridge, Michael, and Rogers, Alex
    In Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems 2019
    arXiv