news

Jul 14, 2026 New! Our workshop Managing Agents that Manage Agents: Workshop on Responsible Use of Meta-Agents is accepted to NeurIPS 2026, see you in Sydney!
Jul 11, 2026 New! Coding with “Enemy”: Can Human Developers Detect AI Agent Sabotage? received the Best Paper Award at the DL4C Workshop @ ICML 2026!
Jul 11, 2026 New! Overconfident and Blind to Details: Fixing Prompt Insensitivity with Abductive Preference Learning is accepted to COLM 2026!
May 11, 2026 New! New preprint out on Shepherd: Enabling Programmable Meta-Agents via Reversible Agentic Execution Traces, a collaboration with Stanford NLP. Code at shepherd-agents/shepherd (1.5K+ stars), featured on X with 400K+ views.
May 09, 2026 New! 2 papers accepted to ICML 2026: Verbalized Sampling and Unsafer in Many Turns. See you in Seoul!
Feb 13, 2026 New! New preprint out on Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents — project page at unsafer-in-many-turns.github.io, code at CHATS-lab/ToolShield.
Jan 26, 2026 New! 3 papers accepted to ICLR 2026: PolySkill, GEM, and SPIRAL. See you in Rio, Brazil!
Dec 06, 2025 New! Hosting the Multi-Turn Interaction workshop @ NeurIPS 2025, see you in San Diego!
Oct 06, 2025 New! Our GEM paper received Oral at the SEA workshop @ NeurIPS 2025 and Spotlight at the MTI-LLM workshop @ NeurIPS 2025!
Oct 01, 2025 New! New preprint out on GEM: A Gym for Generalist LLMs.
Oct 01, 2025 New! New preprint out on Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity.
Jun 24, 2025 New! New preprint out on SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning.
Apr 15, 2025 New! New preprint out on TextArena.
Nov 16, 2024 New! I will be presenting our paper related to Is Multilingualism solved? at EMNLP 2024.
Oct 07, 2024 New! I will be presenting at the COLM-2024, see you in UPenn!
Sep 01, 2024 New! Started as a PhD student at Northeastern University, advised by Prof. Weiyan Shi.
Jul 10, 2024 New! Our paper on Retrieval Safety is accepted by COLM-2024!
Nov 10, 2023 New! Started Colloboration with Liangyu Chen@NTU, Marzieh Fadaee@Cohere and Sara Ahmadian@Google in Efficient Data Selection.