# Study Finds Reasoning Fine-Tuning Collapses Behavioral Diversity in Game Play

Supervised fine-tuning narrows the range of moves models make in sequential decisions, a hidden cost of adapting models to downstream tasks.

- Published: 2026-07-23T05:46:05.758Z
- Canonical: https://polylog.news/ai/2026-07-23/study-finds-reasoning-fine-tuning-collapses-behavioral-diver
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [arXiv cs.CL](https://arxiv.org/abs/2607.19523)

A controlled study examines how supervised fine-tuning (SFT) affects behavioral diversity in sequential decision-making, documenting what the authors call diversity collapse in game play. Adapting a model to a downstream task with SFT tends…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-07-23/study-finds-reasoning-fine-tuning-collapses-behavioral-diver (subscription information: https://polylog.news/pricing).