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

• URL: http://arxiv.org/abs/2607.04089v1
• Date: Sun, 05 Jul 2026 02:55:10 GMT
• Title: PLACEMEM: Toward a Compute-Aware Memory Plane for Lifelong Agents
• Abstract summary: We present PLACEMEM as a systems position on lifelong-agent memory, instantiated by an executable control-plane prototype.<n>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.<n>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.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• ChronoMem: Version Control and Semantic Rollback for Large Language Model Agent Memory [13.447555042917884]
  ChronoMem is a semantic version-control layer for agentic memory integrated into the production-ready, open-source Agent Development Kit by Google.<n>To our knowledge, ChronoMem is the first open-source system and benchmark for systematic semantic global memory rollback in LLM agents.
  arXiv  Detail & Related papers  (2026-07-30T07:07:39Z)
• PhyAgentOS: A Self-Evolving Operating System for Embodied Agents with Decoupled Cognitive Planning and Physical Execution [49.776611937968]
  We present PhyAgentOS, a foundation delivering scheduling, verification, memory, benchmarking, and safety as system-level services.<n>Its Session-Centered treats a session, not an action, as the minimum unit of scheduling, compatibility, supervised execution, evidence collection, and acceptance.<n>SessionVerifier distinguishes execution termination from semantic task completion via evidence-grounded verdicts of success, failure, or replan.<n> Benchmarking reuses the deployment session and verification path, so results trace to real execution.
  arXiv  Detail & Related papers  (2026-07-18T04:46:53Z)
• WorldMemArena: Evaluating Multimodal Agent Memory Through Action-World Interaction [72.1620416874118]
  Multimodal large language models are increasingly deployed as long-horizon agents.<n>Existing benchmarks measure recall over static dialogue, collapse memory into a single end-of-task accuracy, and reduce visual observations to captions.<n>We formulate multimodal agent memory as an Action-World Interaction Loop with an observable four-stage lifecycle.
  arXiv  Detail & Related papers  (2026-05-28T04:27:20Z)
• STAMP: Training Explicit Memory for Mobile GUI Agents in Controllable and Scalable Virtual Environments [63.39393178045112]
  Mobile agents excel at immediate reactive control but frequently fail in realistic, longhorizon tasks that require memory.<n>We present STAMP, a framework that trains explicit memory in mobile agents through controllable virtual environments.<n>The resulting StampGUI agent sets a new high watermark on our Memory-World benchmark, demonstrating exceptional memory accuracy and task resilience.
  arXiv  Detail & Related papers  (2026-05-28T04:00:13Z)
• Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems [60.79651380135334]
  Long-lived AI agents are increasingly deployed as persistent operational systems.<n>How long does an agent remain reliable after deployment?<n>We introduce AgingBench, a longitudinal reliability benchmark for agent lifespan engineering.
  arXiv  Detail & Related papers  (2026-05-25T19:55:12Z)
• Portable Agent Memory: A Protocol for Cryptographically-Verified Memory Transfer Across Heterogeneous AI Agents [0.0]
  We present Portable Agent Memory, an open protocol and reference implementation for transferring persistent memory state across AI agents.<n>We provide a Python SDK with 54 passing tests, and demonstrate cross-model memory transfer between GPT-4, Claude, Gemini, Llama architectures.<n>The protocol is open-source under Apache 2.0.
  arXiv  Detail & Related papers  (2026-05-10T23:24:06Z)
• Mem-W: Latent Memory-Native GUI Agents [50.87647372904382]
  We introduce Mem-W, a series of latent-memory-native GUI agents that treat memory as part of the agent's continuous context.<n>Across four web and mobile navigation benchmarks, Mem-W consistently improves diverse backbones and memory-enhanced baselines.
  arXiv  Detail & Related papers  (2026-05-10T04:31:23Z)
• Feedback-Normalized Developer Memory for Reinforcement-Learning Coding Agents: A Safety-Gated MCP Architecture [0.0]
  This paper presents RL Developer Memory, a local-first, Model Context Protocol (MCP)-native developer-memory architecture for RL coding agents.<n>It treats memory selection as a logged contextual decision process.<n>System is evaluated on a deterministic 200-case benchmark with RL algorithm bugs, hard negatives, review-gated RL/control cases, and low-risk failures.
  arXiv  Detail & Related papers  (2026-05-02T18:37:36Z)
• MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-Evolution [52.29303869050117]
  Memory-augmented LLM agents maintain external memory banks to support long-horizon interaction.<n>MemMA is a plug-and-play multi-agent framework that coordinates the memory cycle along both the forward and backward paths.
  arXiv  Detail & Related papers  (2026-03-19T10:15:59Z)
• HiMAP: History-aware Map-occupancy Prediction with Fallback [17.3826007449443]
  We present textbfHiMAP, a prediction framework that remains reliable under MOT failures.<n>HiMAP converts past detections into historical occupancy maps and retrieves agent-specific history from unlabeled occupancy representations.<n>On Argoverse2, HiMAP performance comparable to tracking-based methods while operating without IDs.
  arXiv  Detail & Related papers  (2026-02-19T10:24:02Z)
• MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval [5.734678752740074]
  MemoryGraft is a novel indirect injection attack that compromises agent behavior not through immediate jailbreaks, but by implanting malicious successful experiences into the agent's long-term memory.<n>We demonstrate that an attacker who can supply benign ingestion-level artifacts that the agent reads during execution can induce it to construct a poisoned RAG store.<n>When the agent later encounters semantically similar tasks, union retrieval over lexical templates and embedding similarity reliably surfaces these grafted memories, and the agent adopts the embedded unsafe patterns, leading to persistent behavioral drift across sessions.
  arXiv  Detail & Related papers  (2025-12-18T08:34:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.