# MemMux preprint reports memory controls for parallel coding agents

_Published Wednesday, October 7, 2026 at 12:10 AM EDT · AI, Science · Latest · Tier 2 — Notable_

Researchers report in an arXiv preprint that MemMux, a local runtime for parallel coding agents, kept a Linux test fleet within a 7.5 GiB memory budget with zero swap. It admitted only a subset of agents and reclaimed resources under pressure; ungoverned tools ran every agent and spilled about 2 GiB into swap.

MemMux reclaimed 100% of a terminated agent's process subtree and detected 10 of 10 escaped child processes. The researchers released the engine, benchmark and a one-command reproducer. Its memory-attribution scan ran at 1 Hz and consumed 2.7% CPU with ten agents, exceeding their 2% target.

## Sources

- [cs.AI updates on arXiv.org](https://arxiv.org/abs/2610.07257)

---
Canonical: https://techandbusiness.org/newswire/EwWLkFqiBR1vtLCxp32Cdh
Published: 2026-10-07T04:10:11.744Z
Story chronology: 2026-10-07T04:00:00.000Z
Retrieved: 2026-10-07T05:59:37.547Z
Publisher: Tech & Business (techandbusiness.org)