- Rating
- 2
- Confidence
- 2(+1)
- Informativeness
- 2
- Presentation
- 2(+1)
- Soundness
- 2
Read review
Paper summary
This paper proposes Invariant-Measure Reasoners (ImR) to address prediction instability across recurrent depths. It replaces prediction from the final latent state with an average of prediction-head logits along a trajectory, interpreted as an approximation to an expectation under an invariant measure. The authors study prediction-head fine-tuning and training from scratch using EqR and deep thinking networks on maze and Sudoku tasks. The results show improved stability and accuracy in several settings, including accurate predictions from trajectories whose latent states continue to change.
Critical strengths
The paper presents a useful way to obtain stable predictions without requiring individual latent states to converge to a fixed point. The implementation is simple, preserves the architecture, and introduces no additional trainable parameters. Its application to both a linear EqR head and a nonlinear DT head provides evidence beyond a single implementation.
Critical weaknesses
-
The comparisons do not adequately isolate ImR’s contribution. Missing controls include averaging with the original pretrained head and alternative temporal aggregation methods. The Sudoku comparison without the puzzle prefix also uses different training horizons and gradient budgets. These gaps weaken the attribution of improvements to the proposed method.
-
The practical significance remains insufficiently established. Evaluation is restricted to structured puzzle tasks, with some gains emerging only after thousands of recurrent updates. Although accuracy-versus-depth curves are provided, the paper does not establish whether these gains translate into a favorable accuracy–runtime tradeoff in a practical use setting.
Questions for authors
-
How does ImR compare with averaging using the original pretrained head and other temporal aggregation methods under matched inference budgets?
-
What are the results of the Sudoku EqR baseline with the same training horizon and gradient budget as ImR?
-
Could the authors clarify what broader reasoning challenges the chosen maze and Sudoku settings are intended to capture, and which conclusions about latent reasoning are expected to generalize beyond these controlled tasks?
5 comments
Reply to Reviewer duQ8 Part 2/2
CW1 and Q2 Comparisons with matched training horizon L and backpropagation length K
CW1: The Sudoku comparison without the puzzle prefix also uses different training horizons and gradient budgets. These gaps weaken the attribution of improvements to the proposed method.
Q2: What are the results of the Sudoku EqR baseline with the same training horizon and gradient budget as ImR?
The original EqR hyperparameter search for Sudoku-Extreme without the prefix already included the setting (L, K) = (36, 4), while the (3, 1) setting was selected by validation accuracy. The (36, 4) setting was also selected for EqR on Maze-Unique without the prefix (Table 6). To make the comparison more informative, we additionally evaluated the existing checkpoint trained with the (36, 4) setting on the test set.
The table below reports test accuracy on Sudoku-Extreme without the prefix at depth 1,024 (Appendix B.3 and Table 9). It compares EqR and ImR with the same training horizon L = 36 and backpropagation length K = 4, alongside the selected EqR setting (3, 1). Entries with three seeds are means.
| Model | Training setting (L, K) | Accuracy (%) | Training seeds |
|---|---|---|---|
| EqR | (3, 1) | 96.2 | 3 |
| EqR | (36, 4) | 69.0 | 1 |
| ImR | (36, 4) | 99.0 | 3 |
In this evaluation, EqR with the (36, 4) setting achieved lower accuracy than the selected (3, 1) baseline. ImR remained more accurate than EqR when both models used the (36, 4) setting.
CW2 Accuracy versus inference time
Although accuracy-versus-depth curves are provided, the paper does not establish whether these gains translate into a favorable accuracy–runtime tradeoff in a practical use setting.
We added measurements of accuracy versus inference time in Appendix C.3 (Figures 11–12), including the cost of the prediction head and logit averaging. The linear prediction head in the EqR architecture adds little cost relative to the recurrent block. For DT, ImR (FT) takes slightly longer at matched recurrent depths because it evaluates the nonlinear prediction head at every step. Despite this additional cost, the accuracy gains observed at large recurrent depths can also be obtained at comparable inference times. These results support test-time scaling with ImR within the evaluated range.
CW2 and Q3 Choice of tasks and limitations
CW2: The practical significance remains insufficiently established. Evaluation is restricted to structured puzzle tasks, with some gains emerging only after thousands of recurrent updates.
Q3: Could the authors clarify what broader reasoning challenges the chosen maze and Sudoku settings are intended to capture, and which conclusions about latent reasoning are expected to generalize beyond these controlled tasks?
We chose maze and Sudoku to examine prediction instability in existing latent reasoning models and evaluate how averaging and training with ImR affect stability and accuracy. The tasks involve pathfinding and constraint satisfaction, respectively, and allow us to track how predictions change as recurrent computation is extended. The maze experiments also test controlled changes in problem size and the degree of the start cell. The improvements observed across multiple settings of these different reasoning tasks suggest that ImR may also be useful for other reasoning problems.
We expanded the paragraph on limitations in Section 6 to clarify which conclusions extend beyond these tasks. Non-fixed-point behavior has also been reported in research on large language models [1], suggesting that prediction instability may also arise in other domains. Under the assumptions in Sections 3.1–3.2, we expect averaged logits to stabilize predictions in other domains. Our analyses further suggest that learning stable representations through f and training g can provide benefits beyond averaging at inference alone. Further evaluation is needed to determine whether ImR improves performance in natural language and other domains.
References
[1] Geiping, J., et al. "Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach." NeurIPS, 2025.
Thank you for the response and the additional ablations and timing experiments. Comparisons with other temporal aggregation methods would still be helpful, as would further validation of practical utility beyond the current puzzle settings. I have raised some individual assessment scores and my confidence to reflect these improvements, while keeping my overall rating unchanged for now.
Reply to Reviewer duQ8 Part 1/2
Thank you for your careful review and constructive feedback. We quote and respond to your comments below. Section, appendix, table, and figure numbers in our responses refer to the revised manuscript.
CW1 and Q1 Comparing averaging with and without ImR training
We added comparisons to separate the effects of averaging and training in Appendix C.2. Keeping each model's parameters fixed, we evaluated prediction from the final state (Final) and from averaged logits (Average) with the same number of recurrent updates. These comparisons include the unchanged pretrained model and the conventionally fine-tuned model under Average, and ImR (FT) under Final. We also evaluated ImR trained from scratch under both rules.
Figures 8–10 show accuracy across recurrent depth, and Tables 7–10 report prediction stability and accuracy at the final depth.
Prediction stability. EqR stability is evaluated over the final 64 depths, ending at depth 512 on Maze-Unique and 1,024 on Sudoku-Extreme (Table 7). For models evaluated with three training seeds, we report the means.
For brevity, the table below presents selected prediction stability results on Maze-Unique under Final and Average.
The table below presents the corresponding prediction stability results on Sudoku-Extreme under Final and Average.
The tables show that averaging alone reduces instability but can stabilize incorrect predictions. Under Average, head fine-tuning increases the stable correct proportion on Maze-Unique, while the three heads give similar results on Sudoku-Extreme. ImR (FT) also has the highest stable correct proportion under Average on DT (Table 8). ImR trained from scratch without the prefix produces predominantly stable correct predictions even under Final, and averaging further reduces instability. Its higher accuracy than EqR under both prediction rules (Figures 8–9 and Table 9) shows that the gains are not solely due to averaging at inference. These results suggest additional benefits from training g and learning stable representations through f.
Appendix C.3 (Figures 11–12) also compares the main methods using measured inference time, including head and averaging costs, for EqR with the prefix and for DT. The results suggest that ImR can improve accuracy at comparable inference times within the evaluated range.