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

> Полный текст доступен на английском

**Published:** 5 октября 2026 г.
**Author:** Yu Li, Zheng Zhang, Xin Liu, Shengtian Yang, Guangfeng Cai, Lei Feng
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/ru/articles/choosing-before-acting-comparative-value-estimation-for-long-horizon-too

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 assignment over long interaction…

> Материал агрегирован из первоисточника: **arXiv — cs.AI**
> [Читать полностью в arXiv — cs.AI](https://arxiv.org/abs/2610.02330)

**Теги:** #arXiv

---

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