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

> 全文为英语

**Published:** 2026年10月5日
**Author:** Ankur Samanta, Yonathan Efroni, Paul Sajda, Kaveh Hassani, Anirudh Goyal
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/zh/articles/learning-what-to-investigate-next-meta-reasoning-for-long-horizon-resear

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…

> 内容来自原始来源： **arXiv — cs.AI**
> [在 arXiv — cs.AI 阅读全文](https://arxiv.org/abs/2610.02525)

**标签：** #arXiv

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*