UC Berkeley 论文提出用周期性遗忘扩展研究型智能体
UC Berkeley 一篇论文提出通过让智能体遗忘来扩展自动化研究：周期性丢弃每个智能体的会话与候选历史，从目前找到的最佳候选重新开始，以避免智能体锚定自身过往尝试、只做小改动的问题。在启发式编程、kernel 优化和模型训练任务上，该方法在同等预算下相比并行智能体最高提升 15%，相比单个智能体最高提升 39%。论文地址 arxiv.org/abs/2610.20563。
Brilliant paper on scaling research agents from UC Berkeley.
(bookmark it)
They propose an unexpected and interesting way to scale automated research with agents.
It's common to see research agents keep their full history and iterate on it to solve a task. After a while, each agent anchors on its own past attempts, makes smaller edits, and extra budget stops improving things.
So this work induces forgetting in the agents.
Periodically, they discard each agent's session and the candidate history, and then restart from the best candidate found so far.
Across heuristic programming, kernel optimization, and model training tasks, this gives up to 15% over parallel agents and up to 39% over a single agent with the same budget.
arxiv.org/abs/2610.20563
Chat with Paper: academy.dair.ai/papers/scali…
来源：omarsar0 · x.com