![[2601.15311] Aeon: High-Performance Neuro-Symbolic Memory Management for Long-Horizon LLM Agents](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2601.15311] Aeon: High-Performance Neuro-Symbolic Memory Management for Long-Horizon LLM Agents
Summary
The paper presents Aeon, a Neuro-Symbolic Cognitive Operating System designed to enhance memory management in Long-Horizon LLM agents, addressing limitations in existing architectures.
Why It Matters
As AI systems increasingly rely on large language models (LLMs), optimizing memory management is crucial for improving reasoning and interaction capabilities. Aeon proposes a novel approach that structures memory more effectively, potentially advancing the performance of autonomous agents in various applications.
Key Takeaways
- Aeon redefines memory management for LLMs, improving efficiency.
- Utilizes a Memory Palace structure for better contextual retrieval.
- Achieves sub-millisecond retrieval latencies, enhancing conversational AI.
- Addresses the 'Lost in the Middle' phenomenon in LLMs.
- Implements a predictive caching mechanism for improved performance.
Computer Science > Artificial Intelligence arXiv:2601.15311 (cs) [Submitted on 14 Jan 2026 (v1), last revised 14 Feb 2026 (this version, v2)] Title:Aeon: High-Performance Neuro-Symbolic Memory Management for Long-Horizon LLM Agents Authors:Mustafa Arslan View a PDF of the paper titled Aeon: High-Performance Neuro-Symbolic Memory Management for Long-Horizon LLM Agents, by Mustafa Arslan View PDF HTML (experimental) Abstract:Large Language Models (LLMs) are fundamentally constrained by the quadratic computational cost of self-attention and the "Lost in the Middle" phenomenon, where reasoning capabilities degrade as context windows expand. Existing solutions, primarily "Flat RAG" architectures relying on vector databases, treat memory as an unstructured bag of embeddings. This approach fails to capture the hierarchical and temporal structure of long-horizon interactions, leading to "Vector Haze": the retrieval of disjointed facts lacking episodic continuity. This paper proposes Aeon, a Neuro-Symbolic Cognitive Operating System that redefines memory not as a static store, but as a managed OS resource. Aeon structures memory into a Memory Palace (a spatial index implemented via Atlas, a SIMD-accelerated Page-Clustered Vector Index that combines small-world graph navigation with B+ Tree-style disk locality to minimize read amplification) and a Trace (a neuro-symbolic episodic graph). The Semantic Lookaside Buffer (SLB), a predictive caching mechanism, exploits conversational loc...
