StatePlane: A Cognitive State Plane for Long-Horizon AI Systems Under Bounded Context

TL;DR

StatePlane introduces a cognitive state management framework for AI systems that enables long-horizon reasoning without expanding context windows, by formalizing episodic, semantic, and procedural memory with novel algorithms and mechanisms.

Contribution

It presents a model-agnostic cognitive state plane that formalizes state management, retrieval, and decay, addressing limitations of static memory approaches in long-term AI reasoning.

Findings

Enables long-horizon reasoning without larger context windows

Demonstrates effective state management across six domain-specific benchmarks

Provides security and governance mechanisms for state integrity

Abstract

Large language models (LLMs) and small language models (SLMs) operate under strict context window and key-value (KV) cache constraints, fundamentally limiting their ability to reason coherently over long interaction horizons. Existing approaches -- extended context windows, retrieval-augmented generation, summarization, or static documentation -- treat memory as static storage and fail to preserve decision-relevant state under long-running, multi-session tasks. We introduce StatePlane, a model-agnostic cognitive state plane that governs the formation, evolution, retrieval, and decay of episodic, semantic, and procedural state for AI systems operating under bounded context. Grounded in cognitive psychology and systems design, StatePlane formalizes episodic segmentation, selective encoding via information-theoretic constraints, goal-conditioned retrieval with intent routing, reconstructive state synthesis, and adaptive forgetting. We present a formal state model, KV-aware algorithms, security and governance mechanisms including write-path anti-poisoning, enterprise integration pathways, and an evaluation framework with six domain-specific benchmarks. StatePlane demonstrates that long-horizon intelligence can be achieved without expanding context windows or retraining models.