Harness-Zero: Harness Distillation via Agent-as-Harness
Ranking
Overall
87
Content
95
Popularity
68
Observed public metrics from 1 member.
Merged summary
TL;DR - Harness-Zero distills behaviors induced by specialized agent harnesses into model weights, allowing agents to retain performance gains while deploying with one fixed harness. It nearly doubles macro-average task success from 23.3% to 44.3%, surpassing the 41.7% achieved with the specialized harness attached.
- A harnessing agent translates optimized-harness guidance into corrected demonstrations compatible with the target harness’s action space.
- Fine-tuning on these trajectories internalizes specialized tool-use and reasoning behaviors, removing the need for deployment-time harness routing.
- Across knowledge work, tool use, and science tasks, agent-as-harness outperformed code-as-harness for frontier LLMs using the same evolved harness.
- The method recovered 82.3% on average of 28 harness-induced behavioral patterns absent from the base model.
Sources (1)
Harness-Zero: Harness Distillation via Agent-as-Harness
Public signals
Hugging Face upvotes 35
TL;DR - Harness-Zero distills behaviors induced by specialized agent harnesses into model weights, allowing agents to retain performance gains while deploying with one fixed harness. It nearly doubles macro-average task success from 23.3% to 44.3%, surpassing the 41.7% achieved with the specialized harness attached.
- A harnessing agent translates optimized-harness guidance into corrected demonstrations compatible with the target harness’s action space.
- Fine-tuning on these trajectories internalizes specialized tool-use and reasoning behaviors, removing the need for deployment-time harness routing.
- Across knowledge work, tool use, and science tasks, agent-as-harness outperformed code-as-harness for frontier LLMs using the same evolved harness.
- The method recovered 82.3% on average of 28 harness-induced behavioral patterns absent from the base model.