Self-Improvement as Coherence Optimization: A Theoretical Account

Excerpt

arXiv:2601.13566v2 Announce Type: replace-cross Abstract: Can language models improve their accuracy without external supervision? Methods such as debate, bootstrap, and internal coherence maximization achieve this surprising feat, even matching golden finetuning performance. Yet why they work remains theoretically unclear. We show that they can all be understood as coherence optimization, the search for a context-to-behavior mapping that is most compressible and jointly predictable, with debate