Jiayi Zhang
@didiforx
Followers
2K
Following
1K
Media
22
Statuses
237
Ph.D. student @HKUSTGuangZhou, Researcher @MetaGPT_, Cofounder of OpenManus, previously at RUC, Lenovo Research AI Lab, Zhipu AI.
ShenZhen
Joined July 2023
It's actually a pity that we got no enough time to maintain OpenManus during the past 3 months. But the better news is that we will build a formal open-source community for OpenManus at the end of this month.
8
23
89
RT @yupenghou97: Did you know tokenization for generative recommendation today looks a lot like LLM tokenization did *10 years* ago?. Meet….
0
26
0
Real God🥵.
Did you know tokenization for generative recommendation today looks a lot like LLM tokenization did *10 years* ago?. Meet ActionPiece, our #ICML2025 Spotlight paper, the first context-aware action tokenizer. 1/5 🧵
1
0
1
RT @allhands_ai: It finally happened 😭. After 8 months of hard work, the OpenHands agent surpassed the last human developer on our reposito….
0
24
0
And I will absolutely build one during my PhD, maybe at the end of this year.
0
0
4
I want to build a startup everytime i have a great research idea . The fucking agent research is too charming.
AI agent research is very practical and utility-driven. If your agent project does not lead to a startup idea, you should probably rethink about it.
1
0
14
Nice work from zhongzhi!.
Our team from the Microsoft Research Asia, UCLA, Chinese Academy of Sciences, Tsinghua University, and released a paper, “TL;DR: Too Long, Do Re-weighting for Efficient LLM Reasoning Compression”proposing an innovative training method that effectively compresses the reasoning.
0
1
6
RT @ZhongzhiLi4: Hi everyone!.The field of LLM-based reasoning has seen tremendous progress and rapid development over the past few months.….
0
17
0
RT @JunhongShen1: 🔥Unlocking New Paradigm for Test-Time Scaling of Agents!. We introduce Test-Time Interaction (TTI), which scales the numb….
0
36
0
Looks good to me. Try to build a horror research game with MGX. Publish something or go die 😭.
The MGX · AI Tools Challenge is live!. Build a powerful AI app and aim for the top!.Just publish your app to join. 🗓️ Deadline: June 17th, 6:00 PM PT.🎁 Top reward: $500 MGX Pro + usage credits. Vote daily to earn too — no app needed!.[Join now] ➡️
0
1
4
RT @YifeiZhou02: 📢 New Preprint: Self-Challenging Agent (SCA) 📢. It’s costly to scale agent tasks with reliable verifiers. In SCA, the key….
0
36
0
RT @hanlinwang1024: 🚀 Excited to share our new work on Agent RL Training!. 📑 SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attributi….
0
11
0
RT @_jasonwei: There are traditionally two types of research: problem-driven research and method-driven research. As we’ve seen with large….
0
93
0
RT @hanzhou032: Automating Multi-Agent Design:. 🧩Multi-agent systems aren’t just about throwing more LLM agents together. 🛠️They require m….
0
165
0
Format is one of the most important factors that affects performance, but it's also a point that most work in experimental settings fails to mention. When conducting Agent Research with @isaac_jinyu, we discovered that this same issue exists in Agents, and we incorporated Format.
Confused about recent LLM RL results where models improve without any ground-truth signal? We were too. Until we looked at the reported numbers of the Pre-RL models and realized they were serverely underreported across papers. We compiled discrepancies in a blog below🧵👇
0
1
8
RT @AnthropicAI: Our interpretability team recently released research that traced the thoughts of a large language model. Now we’re open-s….
0
584
0
Nice Work! Seems AFlow and ADAS @shengranhu have been a default baseline for automating mas design.
Multi-Agent Systems (MAS) can outperform single-agent approaches, however designing MAS manually is difficult, especially when LLM preferences differ from human intuition, and manually designed MAS are hard to adapt to new tasks. 🏆 We are introducing MAS-ZERO: Designing
0
3
8