arXiv:2611.03434v1 Announce Type: new
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.
arxiv
CLEO: Fitting a Minimal Agent Harness to a Self-Hostable LLM for Investigative Analysis
CLEO is a method for optimizing the agent harness—tools, guardrails, memory policies, and loop components—rather than the model itself, to fit a fixed, self-hostable LLM. On a held-out dataset, the CLEO harness achieves an 83.8% pass rate, within 1.2 points of a strong Claude Code SDK baseline, while being two orders of magnitude smaller. This approach addresses security and cost constraints in government intelligence settings by keeping the tool surface minimal and auditable.
Provides a concrete, recent method for building efficient AI agents on self-hosted models, with measurable performance and size trade-offs, valuable for constrained deployments.
Comments & Questions (0)
No comments yet
Be the first to comment!