Flow Reasoning Models: turning flow models into recurrent reasoners without BPTT
alec_helbling · x · 2026-09-17
The author presents a new paper, "Flow Reasoning Models": they convert a flow model into a recurrent model to solve reasoning problems like Sudoku.
Key ideas:
- Predictions are fed back as inputs and iteratively refined across passes
- Each pass gets its own local loss, so no backpropagation through time is needed
This offers a path to iterative reasoning with flow models while sidestepping the usual difficulty of training through many recurrent steps.
Related event: Flow Reasoning Models Turn Flow Models into Recurrent Reasoners(3 posts)→
More from Research
- Dream-RSI: Google DeepMind paper makes the research process itself self-improving — McDonaghMatthew · 2026-09-17
- Dream-RSI from Google DeepMind turns AI experiment logs into reusable self-improvement testbeds — McDonaghMatthew · 2026-09-17
- MIT's FloatForm robot boats self-assemble into bridges on water, published in Nature — lukas_m_ziegler · 2026-09-17
- DeepMind open-sources a fruit fly that learned to fly, 59-dim action space on a laptop — anthara_ai · 2026-09-17
- XPeng unveils XPACE, a unified embodied world model powering its IRON humanoid — CyberRobooo · 2026-09-17
- Max-pooling attribution maps model outputs back to input words in new sparse-model release — antoine_chaffin · 2026-09-17