Yanfei Chen (@anmourchen) header
Yanfei Chen (@anmourchen) profile picture

Research Engineer @Google, working on LLMs.

Pittsburgh
Joined August 2013
Yanfei Chen retweeted
Can RSI improve an agent's harness, and also how that harness gets improved? Earlier RSI methods evolve harnesses for a seen task distribution. But in an open world, the improvement process itself must evolve too. Introducing Harness²: Recursive Agent Harnessing for an Open World.
8
3
2
13
897
Traveling ✈️ to Rio de Janeiro 🇧🇷 next week to attend #ICLR2026, looking forward to catching up with everyone to discuss the latest breakthroughs in #LLM #agents and their enterprise applications. Can't wait to meet everyone in Rio 🙌🏻!
1
2
57
Memory is crucial for building personalized agents. I'll be at ACL 2025 next week to present our paper in reflective memory management, see you in Vienna! Paper link: arxiv.org/pdf/2503.08026 #LLM #memory #agent #ACL2025
1
1
557
Yanfei Chen retweeted
Thrilled to introduce "𝗗𝗲𝗲𝗽 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵𝗲𝗿 𝘄𝗶𝘁𝗵 𝗧𝗲𝘀𝘁-𝗧𝗶𝗺𝗲 𝗗𝗶𝗳𝗳𝘂𝘀𝗶𝗼𝗻," a new deep research agent designed to mimic the iterative nature of human research, complete with cycles of planning, drafting, and revision. 🚀🚀 arxiv.org/pdf/2507.16075
12
84
8
448
37,120
Join me on HelloFax. It's the easiest way to sign and send documents online -
EMBRACE THE MOMENT! The Pittsburgh Penguins are going to the Stanley Cup Final! 🏆
I earn @AmericanAir #AAdvantage miles to celebrate milestones like __________. #MilesForMilestones #Promotion https://teapawt.org/t.co/0L3HK7kLwv
降り出した雨を見上げて、君の声聞きなくなった。
Need to do something this weekend!
下了雨以后,匹村又凉快了不少。 – at Pittsburgh, PA