Enhanced Mycelium of Thought (EMoT): A Bio-Inspired Hierarchical Reasoning Architecture with Strategic Dormancy and Mnemonic Encoding

Computer Science > Artificial Intelligence [Submitted on 25 Mar 2026] Enhanced Mycelium of Thought (EMoT): A Bio-Inspired Hierarchical Reasoning Architecture with Strategic Dormancy and Mnemonic Encoding Florian Odi Stummer 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. Comments: 32 pages, 6 figures, 15 tables; includes ablation studies and reasoning trace visualisation Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2603.24065 [cs.AI]   (or arXiv:2603.24065v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2603.24065 Focus to learn more Submission history From: Odi F. Stummer [view email] [v1] Wed, 25 Mar 2026 08:18:56 UTC (956 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-03 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)