🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

I will be attending #AAAI2025 from today to next Wed. in Philadelphia 🦅 with Daniel Shao & Jiapeng Chen! If you are around, let's chat about agents, reasoning, & llm for science. My good friend Yilun Zhao and I will attend the amazing AI4Research workshop as well!

Just attended Multi-Agent Workshop at AAAI 2025 and it's hands down the best workshop I've been to at AAAI! It was buzzing and truly inspiring. Huge shoutout to the organizers (Weiyan Shi@ICLR and CHI Raphael Shu) for putting together such an unforgettable experience! #AAAI2025

MultiAgentBench‼️‼️

A comprehensive survey on AI agents, with some interesting discussion on the connection to biological intelligence. It's not perfect yet because this is such a complex subject, but it's a start.

// Advances and Challenges in Foundation Agents // 260+ pages on this one! It provides a comprehensive overview, framing intelligent agents within a modular, brain-inspired architecture that integrates principles from cognitive science, neuroscience, and computational research.

Excited to attend #ICLR2025! 🇸🇬 😀find me at ① 3 - 5:30 p.m., Fri 25 Apr (Hall 3 + Hall 2B #8). I will present ChemAgent as a poster. ② 4:30 - 4:45 p.m., Sun 27 Apr. Agentic AI for Scientific Discovery Workshop. I will be on the job market. Feel free to contact me and chat!

Just at Stanford for the first time — feels surreal to be walking through a place that’s shaped so much of ai and nlp. Excited and a little starstruck.

Ethan Dyer and I have started a new team at Anthropic — and we’re hiring! Our team is organized around the north star goal of building an AI scientist: a system capable of solving the long-term reasoning challenges and core capabilities needed to push the scientific

🔥 ACL 2025 Accepted! Our LocAgent tackles one of software engineering's most critical challenges - code localization (finding exactly where bugs hide in massive codebases). 92.7% accuracy + 86% cost reduction. Graph-guided reasoning >> dense embed. This changes how we debug! 🚀