AI/ ai agents · llm training · arxiv research · agent harnesses

New Method Trains AI Agent Harnesses on Repeated Failures

A new method called Ecdysis aggregates failures across tasks before rewriting an AI agent's harness, avoiding fixes tailored to one model's quirks.

Researchers have a new way to train the scaffolding that AI agents run inside, and it starts by not trusting any single failure.

A new paper describes Ecdysis, a method for evolving the runtime harnesses that wrap large language model agents - the code that manages prompts, tools, and retries around the model itself. Existing failure-driven approaches assume any observed agent failure is evidence the harness needs a fix, but the researchers point out that a failure might instead be a quirk of that specific model rather than a flaw in the harness. Ecdysis waits, collecting failure evidence across many different tasks, and only promotes a harness change once the same failure pattern shows up repeatedly. It also runs a collaborative failure-analysis step to refine each proposed fix, spending more reasoning time during training to make modifications more precise.

That patience pays off. Across multiple LLMs and benchmarks, Ecdysis-trained harnesses were 18.56% more accurate than those built with prior harness-evolution methods, trained up to 1.84x faster, and needed less data to get there. The bigger deal is generalization - harnesses built this way transferred better across different models and used fewer tokens at inference time, rather than being tuned to whichever model happened to be running during training.

It's a reminder that in agent engineering, chasing every bug report is often worse than waiting to see which ones keep coming back.

TR

The Revision

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