Saved in:
Bibliographic Details
Main Authors: Rafique, Mofasshara, Bindschaedler, Laurent
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.10352
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908957106241536
author Rafique, Mofasshara
Bindschaedler, Laurent
author_facet Rafique, Mofasshara
Bindschaedler, Laurent
contents Stateful tool-using LLM agents treat the context window as working memory, yet today's agent harnesses manage residency and durability as best-effort, causing recurring failures: lost state after compaction, bypassed flushes on reset, and destructive writeback. We present \textsc{ClawVM}, a virtual memory layer that manages state as typed pages with minimum-fidelity invariants, multi-resolution representations under a token budget, and validated writeback at every lifecycle boundary. Because the harness already assembles prompts, mediates tools, and observes lifecycle events, it is the natural enforcement point; placing the contract there makes residency and durability deterministic and auditable. Across synthetic workloads, 12 real-session traces, and adversarial stress tests, \textsc{ClawVM} eliminates all policy-controllable faults whenever the minimum-fidelity set fits within the token budget, confirmed by an offline oracle, and adds median <50 microseconds of policy-engine overhead per turn.
format Preprint
id arxiv_https___arxiv_org_abs_2604_10352
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ClawVM: Harness-Managed Virtual Memory for Stateful Tool-Using LLM Agents
Rafique, Mofasshara
Bindschaedler, Laurent
Artificial Intelligence
Operating Systems
Software Engineering
D.4.2; I.2.11
Stateful tool-using LLM agents treat the context window as working memory, yet today's agent harnesses manage residency and durability as best-effort, causing recurring failures: lost state after compaction, bypassed flushes on reset, and destructive writeback. We present \textsc{ClawVM}, a virtual memory layer that manages state as typed pages with minimum-fidelity invariants, multi-resolution representations under a token budget, and validated writeback at every lifecycle boundary. Because the harness already assembles prompts, mediates tools, and observes lifecycle events, it is the natural enforcement point; placing the contract there makes residency and durability deterministic and auditable. Across synthetic workloads, 12 real-session traces, and adversarial stress tests, \textsc{ClawVM} eliminates all policy-controllable faults whenever the minimum-fidelity set fits within the token budget, confirmed by an offline oracle, and adds median <50 microseconds of policy-engine overhead per turn.
title ClawVM: Harness-Managed Virtual Memory for Stateful Tool-Using LLM Agents
topic Artificial Intelligence
Operating Systems
Software Engineering
D.4.2; I.2.11
url https://arxiv.org/abs/2604.10352