Signals 4 · free daily AI digest

Harness Learning Enables Generalizable Test-Time Adaptation

Paper recorded by Signals 4 on 2026-09-28 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-28 on arXiv · recorded by Signals 4 on 2026-09-29

Category: cs.LG · 机器学习 · first seen 2026-09-29

Abstract

A language-model agent is jointly defined by its model and its harness, the executable program that organizes model calls, tool use, and information flow. Because different tasks call for different ways of organizing these operations, the harness needs to be adapted using feedback from the task at hand. We introduce harness learning, which trains a proposer model to revise a solver's harness using

Read on arXiv →

#6 most recent of 322 cs.LG papers we have recorded · ↑ newer: Improving Test-Time Scaling with Adaptive Looped Transformers · ↓ older: ScAn-Bench: Evaluating Scaling Analysis Methodology
Cite this page: Harness Learning Enables Generalizable Test-Time Adaptation: the #6 most recent of 322 cs.LG papers we have recorded (as of 2026-09-28). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/harness-learning-enables-generalizable-test-time-adaptation.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.LG 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