Our paper has been accepted to EMNLP 2026 🎉 LLM-simulated conversations are increasingly used to model human social behavior, from social media prototyping to replacing human studies in social science. But can LLMs truly simulate human group behavior? arxiv.org/abs/2603.17094

Arrived at #ICML2026 and will be here till 7/9! Catch me if you also get excited/talkative on agent-as-team-player, simulation env/game for multi-party post training, group common grounding, and food/cycling in Korea ;)

Excited to share our new work on Reinforcing Human Behavior Simulation via Verbal Feedback. Can human simulators learn from feedback, not just rewards? Most RL for LLMs turns feedback into a single score. But human behavior is rarely just right or wrong. It is social, contextual, subjective, and multi-dimensional. A score can tell the model what is better. Verbal feedback can tell it why. Meet DITTO + SOUL. Paper: arxiv.org/abs/2605.20506 Code: github.com/sunnweiwei/OdysSi… Model: huggingface.co/sunweiwei/Dit…

Thrilled to announce that our paper “WildFeedback: Aligning LLMs with In-situ User Interactions and Feedback” has been accepted to ACL 2026! We turn real-world user interactions into powerful alignment signals, pushing LLMs beyond static datasets toward learning from the wild.

[1/6] Can AI fix office feuds humans can’t? 🤝 Check out our recent paper accepted at ACL Findings — ProMediate, the first testbed for evaluating proactive AI mediators in complex, multi-party negotiations. Our evaluations include socio-cognitive assessment and dynamic group outcome tracking.

A lot of useful training data can't be shared due to privacy. How do we create synthetic training data without data owners ever sharing their content? 🚀 Introducing 𝐃𝐏-𝐑𝐅𝐓: using RL to train LLMs to generate high-fidelity domain data without seeing a single private sample.

For decades, we’ve trained AI to chase rewards. But humans don’t just optimize outcomes. We experience, reflect, then learn. Can AI do the same? Introducing 𝐄𝐱𝐩𝐞𝐫𝐢𝐞𝐧𝐭𝐢𝐚𝐥 𝐑𝐞𝐢𝐧𝐟𝐨𝐫𝐜𝐞𝐦𝐞𝐧𝐭 𝐋𝐞𝐚𝐫𝐧𝐢𝐧𝐠, a step toward AI that truly learn from experience.

Send your most proud open source projects our way, MLEs! Pretty sure this is an extremely exciting opportunity where you’ll be diving into solving impactful challenges with cutting edge science and research at the core.

I couldn’t make it to #ACL2025, but excited to share our paper GenTool from @MSFTResearch and @EdinburghUni! aclanthology.org/2025.findin… We introduce GenTool: a training framework that simulates zero-to-one and weak-to-strong tool transitions to boost tool generalization in LLMs.

Having thoughts on how to build the future of human-agent group collaboration and can’t wait to enhance current frontier model’s social/communciation intelligence? Join us🔻! There’re lots of fun chats to be had 💬😎

Heading to #NAACL2025 w/ @peizNLP @soshsihao We are hiring full-time scientists on LLM post training, long-context reasoning, agents, and reinforcement finetuning. Please reach out if you are interested in chatting at the conference!

Internship alert! We have an immediate part-time research intern opening at Microsoft’s Office of Applied Research to improve LLM reasoning. Please reach out if you or your students are interested!

Many @Microsoft Office of Applied Research #OAR members will attend @NeurIPSConf this week: @ylongqi @BahaarehS @peizNLP @sharma_ashish_2 @soshsihao @bhecht & myself. We are hiring (both spring & summer) research interns, FTEs and postdocs. Please reach out if you're interested!

Friends and colleagues! I'm on the academic job market in Fall 24/Spring 25. My research intersects NLP, IR, and HCI and I develop interactive and personalized models to aid workflows where knowledge workers find, consume, and produce information. Please help spread the word! 🧵

Join @_jennhu 's lab doing awesome cool research at CogSci x AI✨ I'd apply if time rewinds :)

Life update: I defended my Ph.D. thesis and have joined @Microsoft's Office of Applied Research (OAR)! One big takeaway from my Ph.D study is that -- research is all about translating ideas into impacts. I feel blessed to work with talented researchers who share the same values!

FTE Job post out! jobs.careers.microsoft.com/g…