English

Contextual Memory Virtualisation: DAG-Based State Management and Structurally Lossless Trimming for LLM Agents

Software Engineering 2026-02-27 v1 Artificial Intelligence Human-Computer Interaction Operating Systems

Abstract

As large language models engage in extended reasoning tasks, they accumulate significant state -- architectural mappings, trade-off decisions, codebase conventions -- within the context window. This understanding is lost when sessions reach context limits and undergo lossy compaction. We propose Contextual Memory Virtualisation (CMV), a system that treats accumulated LLM understanding as version-controlled state. Borrowing from operating system virtual memory, CMV models session history as a Directed Acyclic Graph (DAG) with formally defined snapshot, branch, and trim primitives that enable context reuse across independent parallel sessions. We introduce a three-pass structurally lossless trimming algorithm that preserves every user message and assistant response verbatim while reducing token counts by a mean of 20% and up to 86% for sessions with significant overhead by stripping mechanical bloat such as raw tool outputs, base64 images, and metadata. A single-user case-study evaluation across 76 real-world coding sessions demonstrates that trimming remains economically viable under prompt caching, with the strongest gains in mixed tool-use sessions, which average 39% reduction and reach break-even within 10 turns. A reference implementation is available at https://github.com/CosmoNaught/claude-code-cmv.

Keywords

Cite

@article{arxiv.2602.22402,
  title  = {Contextual Memory Virtualisation: DAG-Based State Management and Structurally Lossless Trimming for LLM Agents},
  author = {Cosmo Santoni},
  journal= {arXiv preprint arXiv:2602.22402},
  year   = {2026}
}

Comments

11 pages. 6 figures. Introduces a DAG-based state management system for LLM agents. Evaluation on 76 coding sessions shows up to 86% token reduction (mean 20%) while remaining economically viable under prompt caching. Includes reference implementation for Claude Code

R2 v1 2026-07-01T10:52:57.703Z