{"ID":3083626,"CreatedAt":"2026-06-05T06:46:15.197025399Z","UpdatedAt":"2026-06-07T03:54:17.966829144Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.06337","arxiv_id":"2606.06337","title":"TokenMizer: Graph-Structured Session Memory for Long-Horizon LLM Context Management","abstract":"Large language model (LLM) deployments for long-horizon tasks face a fundamental constraint: context windows are finite while productive work sessions are not. When history exceeds the Maximum Effective Context Window (MECW), critical structured information - architectural decisions, task transitions, file histories - is silently discarded. Existing mitigations treat history as flat text, destroying the relational structure that makes sessions resumable. We present TokenMizer, an open-source proxy system that models LLM session history as a typed knowledge graph. The schema defines 14 node types and 7 edge types. A hybrid extraction pipeline populates the graph incrementally, while a three-tier checkpoint system serializes it into compact resume blocks. An 8-layer compression pipeline reduces context overhead, and a semantic cache reduces repeated-query latency. Evaluated on a controlled benchmark of 21 sessions spanning 5 domains, TokenMizer demonstrates significant token economy. It produces resume blocks averaging 78 tokens (range: 42-124) - 2x smaller than evaluated baselines (159-170 tokens) - while achieving higher decision recall (+9-17 percentage points). Crucially, baselines only preserve that a technology was mentioned; TokenMizer preserves the rationale. Across all sessions, TokenMizer achieves mean task recall 51.0%, decision recall 46.6%, and file recall 58.7%. Variance reflects domain heterogeneity: explicit imperative phrasing (software engineering) scores higher than implicit reasoning (research). Ablation studies show fuzzy label matching is the dominant improvement factor (+33 pp task recall). The heuristic compression achieves 47.3% token reduction with zero external dependencies. TokenMizer provides a queryable alternative to text-retention baselines at half the token cost.","short_abstract":"Large language model (LLM) deployments for long-horizon tasks face a fundamental constraint: context windows are finite while productive work sessions are not. When history exceeds the Maximum Effective Context Window (MECW), critical structured information - architectural decisions, task transitions, file histories -...","url_abs":"https://arxiv.org/abs/2606.06337","url_pdf":"https://arxiv.org/pdf/2606.06337v1","authors":"[\"Shweta Mishra\"]","published":"2026-06-04T16:12:28Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}