AI & ML New Capability

Introduces StatePlane, a model-agnostic memory architecture that enables long-horizon AI reasoning without expanding the context window or KV cache.

arXiv · March 17, 2026 · 2603.13644

Sasank Annapureddy, John Mulcahy, Anjaneya Prasad Thamatani

The Takeaway

It treats memory as an evolving 'state plane' governed by cognitive principles (segmentation, selective encoding, and adaptive forgetting) rather than static storage. This allows LLMs/SLMs to maintain coherence over multi-session, long-running tasks that typically exceed hardware context constraints.

From the 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-a