Prime Agent 是一款非常有趣的自我改进工具，它能够显著提升模型的性能，值得一试。
Prime Agent 是一款开源的自我改进工具，适用于长期目标智能体工作。它通过持续的记忆和技能传递，使模型在每次运行中不断进步。ARC-AGI-3 RHAE 在最佳移动方面从30%提升到95.5%，并在长上下文编码、GPU内核生成和自主nanoGPT速度竞赛中与原生工具相匹配或超越。
Recommended read. There are a few interesting harness ideas emerging for recursive self-improvement.
Recommended read. There are a few interesting harness ideas emerging for recursive self-improvement. DAIR.AI @dair_ai Very interesting new work from Prime Intellect. Prime Agent is an impressive open-source self-improving harnesses. It's a harness for long-horizon agent work. A persistent IPython REPL lets the model process its own context programmatically, and a Continual Harness carries histories, memories, skills, prompts, and subagent specifications across trajectories, so improvements compound instead of resetting on every run. Same model class, ARC-AGI-3 RHAE Best @1 moves from 30% to 95.5%. It also matches or beats native harnesses on long-context coding, GPU kernel generation, and autonomous nanoGPT speedruns. Paper: arxiv.org/abs/2608.23552 Track more trending AI papers in our academy: academy.dair.ai 🔗 View Quoted Tweet 💬 1 🔄 2 ❤️ 12 👀 2681 📊 3 ⚡
- arXiv cs.AI08-24 17:54原文