Language model agents are post-trained and deployed through a harness, the prompts, tools, and control logic that present a task to the model and execute its outputs. Harnesses are often revised and j
Under KL-regularized control, a policy encodes its harness preferences, so deployed performance equals harness potential minus policy mismatch, and harness comparisons must separate these terms to predict training gains.
Language model agents are post-trained and deployed through a harness, the prompts, tools, and control logic that present a task to the model and execute its outputs. Harnesses are often revised and judged by how an already trained model performs under them, which assumes that what the model learned under one harness carries over to the next. We ask what a policy learns from its harness and what survives when the harness changes. Under KL-regularized control, we show that the log odds of an optimal policy recover how strongly its harness favors each action over the others, so a trained policy carries the preferences of its harness. Deployed return then equals the ceiling of the harness,…
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Your Policy Is Secretly a Harness: The Decision Geometry of Agent Interfaces was first seen on Hugging Face · Daily papers on Oct 28, 2026. Since then it has appeared in 18 checks on 3 different days. Its best position was #24 of 30, reached on Oct 30, 01:28 UTC. It dropped off the list after Oct 30, 03:28 UTC.
Position on Hugging Face · Daily papers at every check (lower is better).
Best rank per day (UTC).
Platform metric as reported by Hugging Face.
Archived daily, weekly and monthly lists that include this entry.
Not at the moment. It was last on the list on Oct 30, 03:28 UTC, after 3 days of trending.
#24 on Hugging Face · Daily papers, on Oct 30, 01:28 UTC. Trendoday checks this list every 120 minutes.
It was first seen on Oct 28, 2026 and has been on the list on 3 days (18 checks) since.