arXiv cs.AI· Sadig Gojayev, Carolina Fortuna·· 9 天前AI 评分22
面向智能序贯决策的 3D 表征框架
A 3D Characterization Framework for Intelligent Sequential Decision Making
AI 导读
研究者提出一个三维表征框架，将 AI 方法投影到 MDP 序贯决策形式化，并从自主程度、技能与计算成本三个维度进行分析。该框架以汉诺塔为基准，对比了 Neurosolver、FBRL 与 AutoToS（含双智能体扩展 DA-ToS）三类方法。结果显示，基于 LLM 的方法因动作空间约束较弱，将复杂度从架构转移到推理时验证，内存与运行成本显著高于 Neurosolver 和 FBRL。
正文 · 原文
Abstract:Puzzles are widely used to evaluate the reasoning capabilities of artificial intelligence (AI) systems for sequential decision making, yet approaches originating from different paradigms are rarely compared under unified conditions. To address this gap, we introduce a three-dimensional characterization framework that enables the analysts of AI methods by 1) projecting them to the Markov decision process (MDP) sequential decision making formalism, 2) degree of autonomy through human prior ranking of their designs and, 3) skill and computational cost. Using this framework, we analyze how representative graph-based, reinforcement learning, and large language model (LLM)-based approaches differ in their design choices and performance characteristics, instantiated respectively by Neurosolver, forward-backward reinforcement learning (FBRL), and automated thought-of-search (AutoToS), including a double-agent extension of thought-of-search (DA-ToS). The analysis relies on the Tower of Hanoi puzzle that provides a controlled benchmark with well-defined rules and scalable complexity, enabling consistent comparison across increasing problem sizes. The 3D characterization reveals that LLM-based methods, due to their weakly constrained action-space design, shift complexity from architecture to inference-time verification, leading to substantially higher memory and runtime costs than Neurosolver and FBRL.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.11696 [cs.AI] |
| (or arXiv:2610.11696v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.11696 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Sadig Gojayev [view email]
[v1]
Thu, 8 Oct 2026 11:06:51 UTC (1,002 KB)
来源：arXiv cs.AI · arxiv.org