Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

LoCo learns when to stop reasoning

AI summary

A new paper proposes LoCo, a DPO-based method that detects candidate overthinking states in a reasoning model’s traces, freezes the corresponding reasoning prefixes, regenerates shorter verified continuations and trains on state-conditioned preference pairs. The authors report completion-length reductions of 41.7%–45.4% on five mathematical benchmarks and 23.4%–36.3% on three code-generation benchmarks, while maintaining or improving accuracy.

In-depth insight

The paper addresses the inference costs caused by continued deliberation after sufficient information has been obtained. LoCo makes state-dependent decisions about whether to continue reasoning or conclude, rather than simply shortening every reasoning trajectory.

Computer Science > Artificial Intelligence

arXiv:2611.04814 (cs)

[Submitted on 3 Nov 2026]

Title:Think Less, Locally: Local Preference Learning for Reasoning Compression

Authors:Muyao Yuan, Liyan Xu, Weizhan Zhang, Muyan Jiao, Jiangnan Li, Jinchao Zhang, Jie Zhou

View a PDF of the paper titled Think Less, Locally: Local Preference Learning for Reasoning Compression, by Muyao Yuan and 6 other authors

#LoCo#DPO#LoCo-7B

Original · 3 min readRead the original
Group chat

No comments yet. Start the conversation.