Harness Evolution Hits a Ceiling: When Weight Training Should Begin

The paper investigates when to evolve a harness versus training model weights for long‑horizon LLM agents. By labeling failed trajectories with the first signal that fires, the authors separate process failures from content failures, showing that harness evolution fixes the former while weight training addresses the latter. Experiments on DeepPlanning and WebArena‑Lite demonstrate significant performance gains, with LoRA adapters trained on evolved harness trajectories further improving held‑out scores and reducing content failures.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• agents
• fine-tuning
• benchmarks