- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper investigates how flow models can leverage additional integration steps for reasoning. Then, it proves that a flow parameterized by a two-layer Transformer can solve graph reachability. Furthermore, it proposes UFM, which trains through the model’s own latent rollout using a single endpoint loss, and shows that it outperforms standard flow language models on several reasoning tasks.
Critical strengths
- The paper identifies a clear limitation of standard flow language models, that extra sampling steps barely help on reasoning tasks.
- Against the flow baselines it compares with, UFM performs clearly better on the two tasks (using a smaller model).
Critical weaknesses
-
UFM is a flow model in name only. Its only training signal is a cross-entropy loss at the endpoint, and it does not uses the FM theoretical framework. Essentially, it is a recurrent network trained by backpropagating through its own iterations, which is already explored by the existing recursive reasoners and truncated sampler backpropagation. So, what's new?
-
During training, UFM initializes its trajectory from a mixture of Gaussian noise and the ground-truth answer embedding, whereas inference starts from pure noise. This introduces privileged answer information into training, potentially allowing the model to learn denoising shortcuts rather than reasoning from the prompt.
-
The experiments do not isolate UFM's gains. Baselines are limited to FLM and S-FLM, which are not built for reasoning, with no recursive or plain recurrent baseline under the same protocol. No component is properly ablated.
Questions for authors
.
4 comments
Response to Reviewer aQQs — Part 2/2
Q2. Answer-informed initialization
“This introduces privileged answer information into training”
To investigate answer-informed initialization, we trained a pure-Gaussian, configuration using the original scheduled update. It reaches 99.50% on Sudoku-Hard and 59.94% on the 2,000-puzzle Sudoku-Extreme subset. This demonstrates successful learning without an answer-derived starting state in that configuration. Fixing also changes the training rollout interval, so the comparison measures these choices together.
We also checked validation during training and final inference. Both start from pure noise, with answer labels excluded from the model inputs. Our split checks found no overlap for identical puzzles or solutions, Sudoku digit relabelling, or the eight Maze rotations and reflections. Sudoku row, column, and band permutations were outside these checks.
Q3. Component ablations
“No component is properly ablated.”
Following the reviewers' suggestions, we added controls for the gradient horizon, retraction, initialization, and state representation. The Sudoku-Hard controls use the separate 150-epoch budget. The gradient-horizon comparison keeps the backbone, decoder, training data, and all 24 forward updates fixed.
The table below reports single-training-run comparisons. Values are means and standard deviations over five inference-noise draws, using 128 uniform updates and one rollout.
| Condition | Sudoku-Hard (%) | Maze-Hard (%) |
|---|---|---|
| Scheduled reference | 96.09 ± 0.25 | 89.34 ± 0.21 |
| One-update backpropagation | 3.66 ± 0.55 | 70.38 ± 0.71 |
To examine the remaining components, we also trained separate Sudoku-Hard controls without retraction, with pure-noise initialization at , and with a vocabulary-sized carried state. Using the same evaluation protocol, these configurations reach 97.53 ± 0.17%, 99.50 ± 0.07%, and 85.47 ± 0.51%, respectively. Values are means and standard deviations over five inference-noise draws, with one training run per condition.
The gradient-horizon comparison was also repeated across three independent Sudoku-Hard training runs. The scheduled reference reaches 94.14 ± 2.02% with six-update backpropagation and 2.09 ± 1.89% with one-update backpropagation. These values are means and sample standard deviations across training runs, with each run's score averaging five inference-noise draws.
The initialization and representation controls require additional qualification. Fixing removes the answer-derived initial component and changes the training rollout interval. The vocabulary-state variant also changes the input mapping, decoder, and noise distribution. We therefore report these as combined interventions, without attributing their effects to a single underlying factor.
For Maze-Hard, the reported checkpoints are selected on a separate generated validation set at 64 updates with one noise draw. Reporting uses the official released test set.
These ablations show a substantial benefit from longer gradients in the scheduled puzzle recipe. They also show that high Sudoku-Hard accuracy remains possible without retraction or answer-derived initialization. Detailed configurations and results are reported in the appendix under Additional controlled experiments.
We sincerely hope that we have addressed the concerns of the reviewer satisfactorily in the revised version and would kindly ask the reviewer to update their score accordingly.
Thank the authors for the response and additional experiments. My concerns are addressed, and I have updated the score to 3.
Thanking the Reviewer
We sincerely thank the reviewer for your positive assessment of our paper and for appreciating our additional results. We are glad we could address all of your concerns.
Response to Reviewer aQQs — Part 1/2
We thank the reviewer for appreciating the merits of our paper and their suggestions for improvement.
We have uploaded a revised version of the paper, with all changes highlighted in blue. All references to pages, sections, figures, tables, and equations use the revised version's numbering.
Q1. Flow formulation and novelty
“UFM is a flow model in name only.” “So, what's new?”
We respectfully disagree with the reviewer on this point. UFM retains a flow-parameterized latent update and uses unrolling of the latent states during training. We view this training strategy as an important contribution, as it enables stronger reasoning capabilities that scale with the number of integration steps, while using a flow-based architecture. Given the growing interest in flow models for language, we believe UFM offers a promising path toward extending their reasoning capabilities.
Building on the prompt-caching construction of Zhu et al., our theoretical contribution gives an explicit linear-attention reachability flow with a closed-form solution and an analysis of its finite Euler updates.
To clarify the role of latent-state unrolling during training, we have added an ablation to the revised manuscript comparing backpropagation through one versus six updates under the reference puzzle training recipe. We hold the architecture and all 24 forward updates fixed, varying only the gradient horizon. The six-update condition backpropagates through the final six calls.
The Sudoku-Hard test results across three training runs, each trained for 150 epochs, are:
The table shows the mean and sample standard deviation across training runs. Each run's score averages five inference-noise seeds at 128 updates and one rollout. These results further underline the importance of backpropagating through several unrolled latent states under the reference update and training budget.