# Verifiable Efficiency Limits of Innate LLM Planning in Sliding Puzzles

> Полный текст доступен на английском

**Published:** 28 октября 2026 г.
**Author:** Yezhou Cheng, Charles Ling
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/ru/articles/verifiable-efficiency-limits-of-innate-llm-planning-in-sliding-puzzles

arXiv:2610.36415v1 Announce Type: new Abstract: Tool-assisted planning success can reflect external search and verification, leaving a model's unaided planning ability unresolved. We isolate innate planning through complete plans generated in one response without tools or…

> Материал агрегирован из первоисточника: **arXiv — cs.AI**
> [Читать полностью в arXiv — cs.AI](https://arxiv.org/abs/2610.36415)

**Теги:** #arXiv

---

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