PLACEMEM: Toward a Compute-Aware Memory Plane for Lifelong Agents

📅 2026-07-04
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This work addresses the challenges of memory persistence, evolution, and correction faced by lifelong intelligent agents through a novel compute-aware memory plane architecture. The proposed framework models memory as versioned capsules endowed with revision-aware capabilities, enabling unified management of semantic content, provenance metadata, validity status, and reusable runtime states, while supporting replay-aware service integration. A prototype implementation built upon vLLM incorporates persistent capsule states, concurrency-safe invalidation mechanisms, OpenAI-compatible routing bypasses, typed metadata contracts, and a real-time benchmarking framework. Experimental results demonstrate that the approach achieves low latency, high reuse rates, and behavior correctability under prompt-level text retrieval, key-value-aware routing, and cascading failure control scenarios.
📝 Abstract
Lifelong agents need more than larger context windows and better retrieval. They need memories that can persist, evolve, and be corrected without forcing the serving stack to recompute the same history on every turn or silently reuse stale runtime state. We present PLACEMEM as a systems position on lifelong-agent memory, instantiated by an executable control-plane prototype. The central claim is that agent memory should be represented as versioned capsules that unify semantics, provenance, validity, and reusable runtime state under one correction-aware identity. In the current prototype, capsules drive prompt-level text retrieval, KV-aware routing, and cascading invalidation over live streamed backends; prospective layer-frontier replay is intentionally framed as a deeper integration agenda rather than a claimed engine feature. We describe a vLLM-first prototype with persistent capsule state, concurrency-safe invalidation, an OpenAI-compatible routing sidecar, a typed metadata contract, and a benchmark harness that measures live first-token latency, reuse, and post-correction behavior. The result is both an executable artifact that demonstrates correction-aware control-plane behavior today and a concrete roadmap for replay-aware serving integration in future lifelong-agent systems.
Problem

Research questions and friction points this paper is trying to address.

lifelong agents
memory persistence
state correction
runtime state reuse
memory evolution
Innovation

Methods, ideas, or system contributions that make the work stand out.

versioned capsules
lifelong agents
correction-aware memory
KV-aware routing
replay-aware serving