# Local Preference Learning

Large reasoning models often keep deliberating after enough information is available, raising decoding latency and memory cost. LoCo moves the compression decision to individual reasoning states: it finds candidate overthinking states in the model's own traces, freezes that prefix, regenerates shorter continuations whose answers verify as correct, and learns a continue-or-conclude preference with DPO. Across five math benchmarks, completion length drops 41.7%–45.4% while accuracy holds or improves; trained on math only, the same model cuts length by 23.4%–36.3% on three code benchmarks.

Large reasoning models often keep deliberating after enough information is available, raising decoding latency and memory cost. LoCo moves the compression decision to individual reasoning states: it finds candidate overthinking states in the model's own traces, freezes that prefix, regenerates shorter continuations whose answers verify as correct, and learns a continue-or-conclude preference with DPO. Across five math benchmarks, completion length drops 41.7%–45.4% while accuracy holds or improves; trained on math only, the same model cuts length by 23.4%–36.3% on three code benchmarks.