---
id: 20261013-T0-10
title: "SpireBench: Evaluating Long-Horizon Strategic Play of Agentic Models with Slay the Spire"
url: https://ai.daily.yangsir.net/daily/20261013-T0-10
issue_date: 2026-10-13
publish_date: 2026-10-12T04:00:00.000Z
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2610.12596
---

# SpireBench: Evaluating Long-Horizon Strategic Play of Agentic Models with Slay the Spire

arXiv:2610.12596v1 Announce Type: new Abstract: Agentic large language models now tackle complex tasks, yet strategic reasoning over long horizons is under-studied: most agentic benchmarks are short and episodic, and performance on long tasks is hard to dissect into stored knowledge, reasoning and l

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2610.12596)

**详情页**：https://ai.daily.yangsir.net/daily/20261013-T0-10

---

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