阿斯塔纳时间
AI QAZAQSTANKZ · AI测试版

哈萨克斯坦人工智能与高科技领域的智能门户

Research1 分钟阅读

内容来自原始来源：

arXiv — cs.AI

在 arXiv — cs.AI 阅读全文

本内容来自公开来源。若发布内容影响您的权利 → 申请删除信息

标题为英语Learning What to Investigate Next: Meta-Reasoning for Long-Horizon Research Agents

Long-horizon research agents must decide both how to investigate and what to investigate next as evidence accumulates. This is hard to learn because such decisions are sparse in long execution traces, and their consequences may emerge several investigations later. We introduce…

arXiv — cs.AI作者: Ankur Samanta, Yonathan Efroni, Paul Sajda, Kaveh Hassani, Anirudh Goyal2026年10月5日 (10月5日)
提供 1 种语言版本

AI 摘要：要点

  • Long-horizon research agents must decide both how to investigate and what to investigate next as evidence accumulates
  • This is hard to learn because such decisions are sparse in long execution traces, and their consequences may emerge several investigations later
  • We introduce…
Research
KZ·AI C7F7
Инсайт дня

Learning What to Investigate Next: Meta-Reasoning for Long-Horizon Research Agents

标签：#arXiv
Поделиться:

相关文章

返回列表