Papers for

government intelligence teams

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Minimal agent harness improves self-hosted large language models accuracy

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

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 the tools, guardrails, memory policies, and loop components that improve accuracy while remaining general and auditable. On our held-out dataset, the CLEO harness reaches an 83.8% pass rate, within 1.2 points of the strongest out-of-the-box Claude Code SDK baseline, while being two orders of magnitude smaller.

Mon 2 NovArtificial IntelligenceComputation and LanguageMultiagent Systems

The gist

Handling large, messy collections of evidence is tough for government intelligence because secure, cost-effective language models don’t offer lots of tools or ways to check their work. The authors created CLEO, a way to carefully add just the right tools and rules around a self-hosted language model so it works better without becoming complex or hard to audit. With CLEO, the system performed almost as well as a much bigger, more complex model but stayed simpler and easier to control.

Open → 2611.03434v1