Signals 4 · free daily AI digest

HarnessMM: Recursive Self-Improvement for Harness Token Efficiency

Paper recorded by Signals 4 on 2026-10-23 in cs.AI. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-23 on arXiv · recorded by Signals 4 on 2026-10-26

Category: cs.AI · 人工智能 · first seen 2026-10-26

Abstract

Agent harnesses repeatedly invoke reasoning after tool feedback, even when an earlier call has already fixed the next action. We introduce HarnessMM (Harness Minus Minus), a method for improving harness token efficiency through guarded decision reuse and recursive self-improvement (RSI). RSI iteratively refines companion harness configurations from training feedback, with validation selecting the

Read on arXiv →

#178 most recent of 960 cs.AI papers we have recorded · ↑ newer: Reimagining Enterprise RAG for Multi-Agent Systems: A Knowledge Layer · ↓ older: Multiplicative vs. Additive State Coupling in Learned Optimizer Schedu

Cite this page: HarnessMM: Recursive Self-Improvement for Harness Token Efficiency: the #178 most recent of 960 cs.AI papers we have recorded (as of 2026-10-23). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/harnessmm-recursive-self-improvement-for-harness-token-efficiency.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json

Related: More cs.AI papers · arXiv signals · All papers · Today in AI

Get 4 AI signals a day by email — free.

Subscribe free → See all plans →

Get 4 AI signals a day by email — free

All models · All repos · By company · Daily editions