# PRIMESCIENTIST：让研究智能体按预算分配实验

- 来源：Rohan Paul (@rohanpaul_ai)
- 发布时间：2026-09-27 08:11
- AIHOT 分数：42
- AIHOT 链接：https://aihot.news/items/cmuj3dz8c0j9rrohyqcvs354w
- 原文链接：https://x.com/rohanpaul_ai/status/2104000875597635926

## AI 摘要

PRIMESCIENTIST 提出研究智能体应自主决定实验资源投向，而非沿单一思路耗尽预算。它用树结构维护多个可执行方案，实验结果更新分支价值，预算充足时多探索、预算收紧时聚焦强分支。在 12 项 FIRE-Bench 任务上，其平均奖励比 AutoResearch 高 10.3%，相同 token 预算下实验尝试次数少 50.6%，24 项任务中有 23 项尝试更少。

## 正文

PRIMESCIENTIST shows that research agents should choose where to spend their experiments, rather than keep pushing the same idea until the budget runs out.

Instead of following a single trajectory, it keeps competing executable plans in a tree. Experiment results update branch values, while the allocation policy explores more when resources are plentiful and concentrates on stronger branches as the budget shrinks.

On 12 FIRE-Bench tasks, it delivered 10.3% higher average reward than AutoResearch while using 50.6% fewer research attempts under the same token budget. Across the full evaluation, it used fewer attempts on 23 of 24 tasks.