Signals 4 · free daily AI digest

Optimize the Harness, Not the Model: Fitting a Minimal Agent to a Self-Hostable LLM for Investigative Analysis

Paper recorded by Signals 4 on 2026-11-02 in cs.CL. Abstract reproduced from arXiv; link to the original below.

Published 2026-11-02 on arXiv · recorded by Signals 4 on 2026-11-03

Category: cs.CL · 自然语言处理 · first seen 2026-11-03

Abstract

Government intelligence teams need LLM agents that can analyze large, messy evidence collections, but security and cost constraints often rule out hosted frontier models and broad, hard-to-audit tool surfaces. We report CLEO: Constrained Loop for Environment Optimization, a method for fitting a minimal agent harness to a fixed, self-hostable LLM. Given an expert-validated dataset, CLEO admits only

Read on arXiv →

#16 most recent of 628 cs.CL papers we have recorded · ↑ newer: Online Label-Free Gradient Matching for Continual Language Model Train · ↓ older: IdeaTaste: Do LLMs Share the Research Taste of Human Researchers?
Cite this page: Optimize the Harness, Not the Model: Fitting a Minimal Agent to a Self-Hostable LLM for Investigative Analysis: the #16 most recent of 628 cs.CL papers we have recorded (as of 2026-11-02). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/optimize-the-harness-not-the-model-fitting-a-minimal-agent-to-a-self-hostable-ll.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CL 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