Shunyu Yao (@ShunyuYao12) / X

Shunyu Yao

835 posts

Shunyu Yao

@ShunyuYao12

Language agents

Joined June 2020

Pinned
Shunyu Yao
@ShunyuYao12
Apr 14, 2025
I finally wrote another blogpost: ysymyth.github.io/The-Second-Hal… AI just keeps getting better over time, but NOW is a special moment that i call “the halftime”. Before it, training > eval. After it, eval > training. The reason: RL finally works. Lmk ur feedback so I’ll polish it.
355K
Shunyu Yao
@ShunyuYao12
Aug 1, 2024
almost forget to post: i've joined @OpenAI! time to convert the research vision to reality, and expect something exciting to drop out :)
154K
Shunyu Yao
@ShunyuYao12
May 19, 2023
Still use ⛓️Chain-of-Thought (CoT) for all your prompting? May be underutilizing LLM capabilities🤠 Introducing 🌲Tree-of-Thought (ToT), a framework to unleash complex & general problem solving with LLMs, through a deliberate ‘System 2’ tree search. arxiv.org/abs/2305.10601
706K
Shunyu Yao
@ShunyuYao12
May 10, 2024
I've defended my PhD! "Language Agents: From Next-Token Prediction to Digital Automation" - Talk (WebShop, SWE-bench, ReAct, ToT, CoALA, and on the future of agents): youtube.com/watch?v=zwfE6J… - Thesis (covers even more): ysymyth.github.io/papers/Dissert…
65K
Shunyu Yao
@ShunyuYao12
May 1, 2024
I will present my thesis defense tomorrow! Language Agents: From Next-Token Prediction to Digital Automation - 10am EST on Thursday, May 2 - princeton.zoom.us/my/shunyuy - WebShop, ReAct, ToT, CoALA - Briefly: SWE-bench/agent - Thoughts on the future of language agents
70K
Shunyu Yao
@ShunyuYao12
Oct 10, 2023
🧠🦾ReAct -> 🔥FireAct Most language agents prompt LMs - ReAct, AutoGPT, ToT, Generative Agents, ... - Which is expensive, slow, and non-robust😢 Most fine-tuned LMs not for agents... FireAct asks: WHY NOT? Paper, code, data, ckpts: fireact-agent.github.io (1/5)
81K
Shunyu Yao
@ShunyuYao12
Sep 6, 2023
Language Agents are cool & fast-moving, but no systematic way to understand & design them.. So we use classical CogSci & AI insights to propose Cognitive Architectures for Language Agents (🐨CoALA)! arxiv.org/abs/2309.02427 w/ great @tedsumers @karthik_r_n @cocosci_lab (1/6)
76K
Shunyu Yao
@ShunyuYao12
Mar 12, 2024
Solving >10% of our SWE-Bench (swebench.com) is THE most impressive result in 2024 so far, and a milestone for the research and application of AI agents. Congrats @cognition_labs !
Cognition
@cognition
Mar 12, 2024
Today we're excited to introduce Devin, the first AI software engineer. Devin is the new state-of-the-art on the SWE-Bench coding benchmark, has successfully passed practical engineering interviews from leading AI companies, and has even completed real jobs on Upwork. Devin is
00:00
133K
Shunyu Yao
@ShunyuYao12
Oct 10, 2022
Large Language Models (LLM) are 🔥in 2 ways: 1.🧠Reason via internal thoughts (explain jokes, math reasoning..) 2.💪Act in external worlds (SayCan, ADEPT ACT-1, WebGPT..) But so far 🧠and💪 remain distinct methods/tasks... Why not 🧠+💪? In our new work ReAct, we show 1+1>>2!
This post is unavailable.
Shunyu Yao
@ShunyuYao12
Jul 3, 2023
The art of programming is interactive. Why should coding benchmarks be "seq2seq"? Thrilled to present 🔄InterCode, next-gen framework of coding tasks as standard RL tasks (action=code, observation=execution feedback) paper, code, data, pip: intercode-benchmark.github.io (1/7)
107K
Shunyu Yao
@ShunyuYao12
Jan 23, 2025
We’re releasing - CUA, the first agent model from OpenAI - Operator, the first agent product from OpenAI - openai.com/careers/resear… , the first agent job post from OpenAI — apply and work with us!!
OpenAI
@OpenAI
Jan 23, 2025
Introduction to Operator & Agents openai.com/index/introduc…
40K
Shunyu Yao
@ShunyuYao12
May 23, 2023
Code released at github.com/ysymyth/tree-o…, thanks for waiting! It's intentionally kept minimalistic (core ~ 100 lines), though some features (e.g. variable breadth across steps) can be easily added to improve perf & reduce cost. (1/2)
Shunyu Yao
@ShunyuYao12
May 19, 2023
Still use ⛓️Chain-of-Thought (CoT) for all your prompting? May be underutilizing LLM capabilities🤠 Introducing 🌲Tree-of-Thought (ToT), a framework to unleash complex & general problem solving with LLMs, through a deliberate ‘System 2’ tree search. arxiv.org/abs/2305.10601
75K
Shunyu Yao
@ShunyuYao12
Apr 18, 2024
Coding is the frontier of AI. Excited to push the two frontiers of AI coding: 1. SWE(-bench/agent) 2. Olympiad programming (this tweet) Introduce USACO benchmark: * inference methods (RAG/reflect) help a bit: 9->20% * human feedback helps a lot: 0->86%! princeton-nlp.github.io/USACOBench/
62K