arXiv cs.AI· Yezhou Cheng, Charles Ling·· 11 小时前AI 评分31
滑动拼图中 LLM 原生规划的可验证效率上限
Verifiable Efficiency Limits of Innate LLM Planning in Sliding Puzzles
AI 导读
研究提出可验证框架 SPE=R×Q×E，将成功加权规划效率分解为执行可靠性、合法规划间协调性和完成规划的动作经济性，并用轨迹回放与认证最优解验证。基于 7 种模型条件在 4×4 滑动拼图上生成的 8,400 份完整规划输出，模型即使完成全部试验，在更长视野下仍变得不够经济，完成规划的高效率可与较差的目标达成率并存。该框架使无工具辅助规划的长视野局限可被定量验证。
正文 · 原文
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 execution feedback. We propose a verifiable framework that decomposes success-weighted plan efficiency as $\mathrm{SPE}=R\times Q\times E$: execution reliability, planning coordination among legal plans, and action economy among completed plans. Trajectory replay and certified optima verify these factors; the joint score includes unsuccessful attempts. We evaluate 8,400 full-plan outputs from seven model conditions on $4\times4$ sliding puzzles, controlling exact horizon and obstacle count in the primary cohort. Models that complete every trial still become less economical at longer horizons, while higher efficiency among completed plans can coexist with poor goal attainment. SPE separates the overall capability hierarchy, while its factors distinguish coordination failure from inefficient completion. The framework makes long-horizon limitations in unaided planning quantitatively verifiable.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.36415 [cs.AI] |
| (or arXiv:2610.36415v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.36415 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yezhou Cheng [view email]
[v1]
Mon, 26 Oct 2026 23:53:23 UTC (112 KB)
来源：arXiv cs.AI · arxiv.org