header-langage
简体中文
繁體中文
English
Tiếng Việt
한국어
日本語
ภาษาไทย
Türkçe
Scan to Download the APP
Partnered With:

Prime Intellect Open Sources Self-Improving Agent Framework, Opus 5 Surpasses Human Experts in ARC-AGI-3

According to Dynalysis Beating monitoring, the AI training platform Prime Intellect has open-sourced Prime Agent. It is a runtime framework deployed outside the model, responsible for maintaining history, invoking tools, scheduling sub-agents, and able to adjust its prompts, memories, and skills based on failure records. The model parameters remain unchanged. The project is released under the MIT license.

Prime Intellect ran the ARC-AGI-3 public tasks three times using Opus 5, achieving scores of 95.0%, 95.2%, and 95.5% respectively. The highest score slightly surpasses its referenced 95.4% human expert baseline.

However, it is not a community first. The ARC Prize community leaderboard already includes Tycho with 100%, Retrodict with 99.9%, and baseline1 with 99.0%. These solutions also fall under the category of "model plus custom runtime framework," leveraging memory, code execution, or a world model to assist AI in problem-solving.

RelatedRecommended
By developing a viable distributed AI training framework, Prime Intellect unlocks the potential of a decentralized GPU computing market.
The total number of financings last week was 20, which was less than before, with a total amount of approximately US$191 million and an average financing amount of US$9.55 million.
Correction/Report
Submit
Add Library
Visible to myself only
Public
Save
Choose Library
Add Library
Cancel
Finish