Large reasoning models achieve strong performance on challenging tasks, but their long chain-of-thought often incurs substantial inference costs by continuing to deliberate after sufficient informatio
LoCo uses local preference learning to teach reasoning models when to stop deliberating, reducing output length substantially while preserving or improving accuracy across math and code tasks.
Large reasoning models achieve strong performance on challenging tasks, but their long chain-of-thought often incurs substantial inference costs by continuing to deliberate after sufficient information has been obtained. Existing reasoning compression methods primarily operate on reasoning trajectories, paying less attention to the local decision of whether further reasoning is necessary given the current state. We propose LoCo, a local preference learning method for reasoning compression. LoCo detects candidate overthinking states from the model's own traces, freezes the corresponding reasoning prefixes, regenerates shorter verified continuations from the same states, and trains on the…
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Think Less, Locally: Local Preference Learning for Reasoning Compression was first seen on Hugging Face · Daily papers on Nov 4, 2026. Since then it has appeared in 15 checks on 2 different days. Its best position was #1 of 30, reached on Nov 5, 07:28 UTC. It dropped off the list after Nov 5, 17:28 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 Nov 5, 17:28 UTC, after 2 days of trending.
#1 on Hugging Face · Daily papers, on Nov 5, 07:28 UTC. Trendoday checks this list every 120 minutes.
It was first seen on Nov 4, 2026 and has been on the list on 2 days (15 checks) since.