Flow Reasoning Models: Scaling Reasoning Through Iterative Self-Refinement

• URL: http://arxiv.org/abs/2606.29150v1
• Date: Sun, 28 Jun 2026 02:10:36 GMT
• Title: Flow Reasoning Models: Scaling Reasoning Through Iterative Self-Refinement
• Abstract summary: We introduce Reasoning Flow Models, a training and test-time-scaling framework for structured reasoning with flow models.<n>A correct answer is a stable fixed point of the denoising dynamics, returning to itself when re-noised and re-solved.<n>We train flow models with a self-conditioning channel and close it at inference, letting them refine their own past predictions.
• Score: 13.205772367296353
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Discrete flow models have recently shown promising performance on few-step text generation; however, when naively applied to structured reasoning tasks such as Sudoku and Zebra puzzles, they converge confidently to incorrect answers (solving only $\sim$36% of Sudoku puzzles). We introduce Flow Reasoning Models (FRMs), a training and test-time-scaling framework for structured reasoning with flow models. We make the observation that, despite their poor solve rate, flow models can act as their own verifiers. A correct answer is a stable fixed point of the denoising dynamics, returning to itself when re-noised and re-solved. This enables a test-time-scaling paradigm: propose many candidate solutions and keep those that are dynamically stable, which alone reaches high solve rates on Sudoku-Shah (~$100\%$) and Zebra ($95.9\%$). This even generalizes to harder out-of-distribution puzzles like Sudoku-Extreme ($96.1\%$), without ever training on that distribution. This pure search, however, wastes a great deal of computation generating incorrect candidate solutions. We therefore design a training recipe to improve the base model's efficiency. First, we train flow models with a self-conditioning channel and close it at inference, letting them refine their own past predictions. Second, we train models to avoid their own failed generations using direct preference optimization. These changes substantially improve the base model's efficiency, letting it reach $99.2\%$ on Sudoku in just $7$ forward passes, over $8\times$ fewer than the strongest matched masked-diffusion baseline we compare needs for the same accuracy. When combined with test-time scaling, this lets flow models solve hard out-of-distribution puzzles (e.g. Sudoku-Extreme) far more efficiently.

Related papers

• Let It Go or Learn to Self-Correct: Continuous Diffusion for Constrained Discrete Tasks [16.76819088768813]
  Denoising Diffusion Probabilistic Models generate samples by repeatedly denoising while keeping each update close to the current noisy state.<n>We show that standard diffusion sampling may preserve early mistakes, even when the model's clean predictions are informative.<n>We introduce self-correction training, which exposes the model to its own predictions, improving robustness to errors that arise during inference.
  arXiv  Detail & Related papers  (2026-09-08T16:45:52Z)
• Recurrent Reasoning on Symbolic Puzzles with Sequence Models [3.900695166480356]
  We introduce RecurrReason, a difficulty-controlled benchmark of four recurrent logic puzzles.<n>We benchmark two Transformer families, an encoder-decoder model (T5-style) and a decoder-only model (GPT-2-style)<n>Fine-tuned pre-trained T5 achieves 97.27% validation and 81.00% OOD accuracy on Block World; all models score 0.00% on River Crossing under all conditions.
  arXiv  Detail & Related papers  (2026-04-19T15:48:32Z)
• Self-Aware Markov Models for Discrete Reasoning [8.161697757509701]
  We introduce a method based on learning a Markov transition kernel that is trained on its own outputs.<n>This design enables tokens to be remasked, allowing the model to correct its previous mistakes.<n>On the Sudoku-Extreme dataset we clearly outperform other flow based methods with a validity of 95%.
  arXiv  Detail & Related papers  (2026-03-17T15:30:06Z)
• Test-Time Scaling with Diffusion Language Models via Reward-Guided Stitching [66.39914384073145]
  We propose a self-consistency framework that turns cheap diffusion-sampled reasoning into a reusable pool of step-level candidates.<n>We find that step-level recombination is most beneficial on harder problems.<n>Our training-free framework improves average accuracy by up to 2 across six math and coding tasks.
  arXiv  Detail & Related papers  (2026-02-26T11:08:39Z)
• INC: An Indirect Neural Corrector for Auto-Regressive Hybrid PDE Solvers [61.84396402100827]
  We propose the Indirect Neural Corrector ($mathrmINC$), which integrates learned corrections into the governing equations.<n>$mathrmINC$ reduces the error amplification on the order of $t-1 + L$, where $t$ is the timestep and $L$ the Lipschitz constant.<n>We test $mathrmINC$ in extensive benchmarks, covering numerous differentiable solvers, neural backbones, and test cases ranging from a 1D chaotic system to 3D turbulence.
  arXiv  Detail & Related papers  (2025-11-16T20:14:28Z)
• Catch Your Breath: Adaptive Computation for Self-Paced Sequence Production [55.76222360698305]
  We explore a class of supervised training objectives that allow a language model to dynamically and autonomously scale the number of compute steps used for each input token.<n>For any token, the model can request additional compute steps by emitting a don't know> output.<n>We find that the CYB model requests additional steps when doing so improves accuracy, and the model adapts its processing time to token-level complexity and context.
  arXiv  Detail & Related papers  (2025-10-13T21:07:05Z)
• Entropy After $\langle \texttt{/Think} \rangle$ for reasoning model early exiting [38.93424884988798]
  We show that large reasoning models overthink, continuing to revise answers even after reaching the correct solution.<n>We propose Entropy After /Think> (EAT) for monitoring and deciding whether to exit reasoning early.<n>EAT reduces token usage by 13 - 21% without harming accuracy.
  arXiv  Detail & Related papers  (2025-09-30T16:59:37Z)
• DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models [30.184895117009457]
  This paper introduces Difficulty-Adaptive Slow Thinking (DAST), a novel framework that enables models to autonomously adjust the length of Chain-of-Thought (CoT) based on problem difficulty.<n>Experiments on diverse datasets and model scales demonstrate that DAST effectively mitigates overthinking while preserving reasoning accuracy on complex problems.
  arXiv  Detail & Related papers  (2025-03-06T14:23:06Z)
• Truncated Consistency Models [57.50243901368328]
  Training consistency models requires learning to map all intermediate points along PF ODE trajectories to their corresponding endpoints.<n>We empirically find that this training paradigm limits the one-step generation performance of consistency models.<n>We propose a new parameterization of the consistency function and a two-stage training procedure that prevents the truncated-time training from collapsing to a trivial solution.
  arXiv  Detail & Related papers  (2024-10-18T22:38:08Z)
• Language models scale reliably with over-training and on downstream tasks [121.69867718185125]
  Scaling laws are useful guides for derisking expensive training runs. However, there remain gaps between current studies and how language models are trained. In contrast, scaling laws mostly predict loss on inference, but models are usually compared on downstream task performance.
  arXiv  Detail & Related papers  (2024-03-13T13:54:00Z)
• Learning to Optimize Permutation Flow Shop Scheduling via Graph-based Imitation Learning [70.65666982566655]
  Permutation flow shop scheduling (PFSS) is widely used in manufacturing systems. We propose to train the model via expert-driven imitation learning, which accelerates convergence more stably and accurately. Our model's network parameters are reduced to only 37% of theirs, and the solution gap of our model towards the expert solutions decreases from 6.8% to 1.3% on average.
  arXiv  Detail & Related papers  (2022-10-31T09:46:26Z)
• Thought Flow Nets: From Single Predictions to Trains of Model Thought [39.619001911390804]
  When humans solve complex problems, they rarely come up with a decision right-away. Instead, they start with an intuitive decision reflecting upon it, spot mistakes, resolve contradictions and jump between different hypotheses.
  arXiv  Detail & Related papers  (2021-07-26T13:56:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.