---
id: 20261006-T0-17
title: "Choosing Before Acting: Comparative Value Estimation for Long-Horizon Tool-Use Agents"
url: https://ai.daily.yangsir.net/daily/20261006-T0-17
issue_date: 2026-10-06
publish_date: 2026-10-05T04:00:00.000Z
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2610.02330
---

# Choosing Before Acting: Comparative Value Estimation for Long-Horizon Tool-Use Agents

arXiv:2610.02330v1 Announce Type: new Abstract: Large language models (LLMs) rely on long-horizon tool invocation sequences for complex tasks, where each invocation can alter the task state and condition subsequent decisions. In long-horizon tool use, final-outcome rewards provide weak credit assign

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2610.02330)

**详情页**：https://ai.daily.yangsir.net/daily/20261006-T0-17

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*