
Research Engineer @Google, working on LLMs.
Pittsburgh
Joined August 2013
- Tweets10
- Following26
- Followers28
- Likes0
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.
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
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
Let's go Pens! teapawt.org/penguins/status/736027…
I earn @AmericanAir #AAdvantage miles to celebrate milestones like __________. #MilesForMilestones #Promotion https://teapawt.org/t.co/0L3HK7kLwv





