受真菌菌丝启发，构建分层思考框架，实现记忆与休眠策略的智能推理。
Enhanced Mycelium of Thought (EMoT): A Bio-Inspired Hierarchical Reasoning Architecture with Strategic Dormancy and Mnemonic Encoding
- 分四级层次结构组织思考，支持节点休眠与唤醒，模拟生物认知机制。
- 跨领域综合任务表现优于传统方法（4.8 vs 4.4），但简单问题易过度思考。
- 首次融合分层拓扑、休眠机制与记忆编码，适合复杂多领域问题求解。
当前大语言模型的提示范式（如 CoT、ToT）采用线性或树状推理路径，缺乏持久记忆、策略性休眠及跨领域整合能力。本文提出受生物启发的增强菌丝思维框架（EMoT），将认知过程组织为四层结构（微、中、宏、元），实现推理节点的策略性休眠与重激活，并集成包含五种记忆编码方式的「记忆宫殿」。该框架专为复杂多领域问题设计，非通用提示优化。双评估显示：在三领域盲评中，EMoT 与 CoT 接近（4.20 vs 4.33/5.0），稳定性更高；跨领域合成任务表现更优（4.8 vs 4.4）。消融实验表明，休眠机制不可或缺（禁用后质量从 4.2 降至 1.0）。但在 15 道简答题上，其准确率仅 27%，显著低于基线，反映对简单问题存在系统性过度思考。结果受限于小样本（n=3 复杂案例，n=15 简答项）、基于 LLM 的评判可能存在的自偏好偏差，以及约 33 倍计算开销。据我们所知，EMoT 是首个将分层拓扑、策略性休眠与记忆编码统一于单一架构的推理框架。
原文摘要 · Abstract (English)
Current prompting paradigms for large language models (LLMs), including Chain-of-Thought (CoT) and Tree-of-Thoughts (ToT), follow linear or tree-structured reasoning paths that lack persistent memory, strategic dormancy, and cross-domain synthesis. We present the Enhanced Mycelium of Thought (EMoT) framework, a bio-inspired reasoning architecture that organises cognitive processing into a four-level hierarchy (Micro, Meso, Macro, Meta), implements strategic dormancy and reactivation of reasoning nodes, and integrates a Memory Palace with five mnemonic encoding styles. EMoT is a research prototype for complex, multi-domain problems, not a general-purpose prompting enhancement. Two complementary evaluations reveal a characteristic trade-off. In a blind LLM-as-Judge evaluation across three domains, EMoT achieved near-parity with CoT (4.20 vs. 4.33/5.0) with higher stability, and outperformed CoT on Cross-Domain Synthesis (4.8 vs. 4.4). Ablation studies show that strategic dormancy is architecturally essential (quality collapsed from 4.2 to 1.0 when disabled). On a 15-item short-answer benchmark, EMoT (27%) substantially underperformed simpler baselines, confirming systematic overthinking on simple problems. These results are subject to important limitations: small sample sizes (n=3 complex cases, n=15 short-answer items), LLM-as-Judge evaluation with potential self-preference bias, and approximately 33-fold computational cost overhead. To our knowledge, EMoT is the first reasoning framework to combine hierarchical topology, strategic thought dormancy with reactivation, and mnemonic memory encoding in a single architecture.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。