增强思维菌丝(EMoT):一种受生物启发的分层推理架构,具有战略休眠和记忆编码
Enhanced Mycelium of Thought (EMoT): A Bio-Inspired Hierarchical Reasoning Architecture with Strategic Dormancy and Mnemonic Encoding
AI总结:
EMoT是一种受生物启发的分层推理架构,通过四层结构(微、中、宏、元)实现战略休眠与激活,结合记忆宫殿和五种记忆编码方式,提升多领域复杂问题解决能力,但存在样本量小、计算成本高等限制。
摘要:
当前大语言模型(LLM)的提示范式,包括链式思维(CoT)和树状思维(ToT),遵循线性或树状推理路径,缺乏持久记忆、战略休眠和跨领域合成能力。我们提出增强思维菌丝(EMoT)框架,一种受生物启发的推理架构,将认知处理组织为四层结构(微、中、宏、元),实现推理节点的战略休眠与再激活,并整合包含五种记忆编码方式的记忆宫殿。EMoT是为复杂多领域问题设计的研究原型,而非通用提示增强工具。两项互补评估揭示了特征性的权衡。在跨三个领域的盲LLM-as-Judge评估中,EMoT在4.20(vs. 4.33/5.0)接近CoT,稳定性更高,并在跨领域合成任务中优于CoT(4.8 vs. 4.4)。消融研究显示,战略休眠在架构上至关重要(禁用时质量从4.2降至1.0)。在15项简答基准测试中,EMoT(27%)显著低于简单基线,证实了在简单问题上的系统性过度思考。这些结果受重要限制:样本量小(n=3复杂案例,n=15简答项目)、LLM-as-Judge评估可能存在自我偏好偏差,以及约33倍的计算成本开销。据我们所知,EMoT是首个将分层拓扑、战略思维休眠与再激活、以及记忆编码整合于单一架构的推理框架。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。