news
| Oct 2026 | New survey: Proactive AI for Superintelligent Agents, with collaborators from UIUC, Google, Stanford, Berkeley, and CMU. We organize the mechanisms behind proactive agents into six capacities and examine how much initiative agents take relative to the authority they are granted across 13 application domains.  |
|---|---|
| Sep 2026 | PlugMem was selected for an oral presentation at the PALM Workshop @ NeurIPS 2026.  |
| Sep 2026 | New preprint: StudentSim: Training LLM-based Student Simulators — personalized LLM-based student simulators trained from sparse learner records, evaluated by whether they match student responses and change reliably after AI tutor guidance. Project site.  |
| Jun 2026 | Joined Google as a Student Researcher this summer.  |
| Feb 2026 | New preprint: PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents — a plug-and-play memory module that turns raw agent experience into reusable knowledge and consistently improves long-horizon decision-making. Code on GitHub.  |
| May 2025 | New preprint: Ten Principles of AI Agent Economics — my first perspective paper, reflecting on AI agent incentives and what they imply for the broader economy.  |
| May 2025 | New preprint on benchmarking Just-in-time Information Recommendation — AI assistants that proactively recommend the right information at the right time.  |