Beyond Similarity Search: Tenure and the Case for Structured Belief State in LLM Memory

TL;DR

The paper introduces Tenure, a structured belief state system for LLM memory that improves cross-session knowledge management through typed, scoped, and versioned belief stores, outperforming traditional similarity search methods.

Contribution

Tenure provides a novel local-first belief store with epistemic status, scope isolation, and actionable schema, addressing limitations of similarity search in LLM memory management.

Findings

BM25 achieves perfect precision (1.0) in retrieval cases, outperforming cosine similarity.

Tenure's alias-weighted BM25 maintains high accuracy across all test cases.

Hybrid retrieval reduces vocabulary mismatch issues in multi-author contexts.

Abstract

Why do we need another AI to help the AI? We argue you don't. Stateless LLM sessions impose re-orientation costs on iterative, session-heavy workflows. Prior work addresses cross-session memory through retrieval-augmented approaches: store history, embed it, retrieve by semantic similarity. Cross-session memory is a state management problem, not a search problem. Similarity search fails for named entity resolution within bounded vocabulary contexts because beliefs about a shared technical domain are semantically proximate by construction. A single user is the simplest bounded vocabulary context; engineering teams converge on the same property through shared codebases and terminology. We present Tenure, a local-first proxy that maintains a typed belief store with epistemic status, versioned supersession, and scope isolation, injecting curated context into every LLM session through precision-first retrieval. Hard scope isolation provides a structural guarantee: the right beliefs surface, and only within the boundaries the user has authorized. Tenure's typed schema converts extracted facts into imperative instructions via a why it matters field, making injected beliefs directly actionable rather than raw material for the model to re-derive. A controlled evaluation on 72 retrieval cases demonstrates the gap. Cosine similarity over dense embeddings achieves mean precision of 0.12. Alias-weighted BM25 maintains mean precision of 1.0, passing 72/72 cases versus 8/72 for cosine similarity on the same corpus. Hybrid retrieval typically solves vocabulary mismatch between disparate authors; Tenure eliminates this structurally: query and belief authors are the same person, and an alias enrichment flywheel continuously indexes their specific vocabulary. Under multi-turn topic drift this worsens: the vector backend produces drift scores of 0.43--0.50 on noise-critical turns where BM25 maintains 0.