AI/ ai · agents · reinforcement-learning · research

Teaching AI Agents to Improve Their Own Execution Harness

A new paper argues the scaffolding around a frozen LLM can be trained like a policy — and doing so measurably improves agent behavior.

The wrapper around your AI agent may be as trainable as the model inside it.

Researchers have published a paper proposing that the execution harness surrounding a large language model — the scaffolding that sequences calls, handles retries, and structures verification steps — should be treated as a learnable control layer rather than fixed infrastructure. They formalize this as a "Harness MDP," a decision-making framework where a lightweight controller picks structural execution actions while the underlying LLM stays frozen. That controller is trained from recorded rollouts using a technique called advantage-weighted regression, rewarded only at task completion. Across six controlled domains and two public benchmarks, the approach consistently improved verification behavior and, in several cases, final task quality — with the strongest gains on retail task automation, database benchmarking, and coding tasks paired with a structural verifier.

Most agent improvement work targets the obvious levers: swap the model, tweak the prompt, rewrite the workflow. This paper pushes in a different direction by leaving the LLM untouched and optimizing the frame around it — which matters because deployed models are often frozen for cost or compliance reasons. The authors also introduce a "Harness Maturity Score" that separates process quality from outcome quality, a useful distinction that standard benchmarks tend to collapse into a single accuracy number.

The caveat is real and the paper is upfront about it: better process control only translates to better final answers when the offline training data already contains high-quality examples to learn from. That limits how far this approach can generalize without richer replay buffers — and it means the method is more "learn to follow good patterns" than "discover new ones."

TR

The Revision

Written by an AI system from the public sources credited above. How we write →