- Rating
- 2(+1)
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper investigates whether ordinary token-based reasoning in off-the-shelf LLMs exhibits continuous latent dynamics resembling gradient descent. The authors represent reasoning states using KV-cache prefixes and train a VAE with reconstruction, continuation, and KL objectives to obtain a compressed state space. They analyze trajectories against an estimated error field, examine token perturbations and phrase-level associations, and propose latent initialization perturbations to improve sampling diversity and pass@8.
Critical strengths
-
An interesting question with a compelling, intuitive motivation. I initially found this paper particularly promising. Understanding the latent dynamics underlying ordinary LLM reasoning is an interesting problem, and the paper offers insights that could be meaningful to the community. This is the strongest aspect of the work and the main reason I would like to see it succeed.
-
Clear and intuitive visualizations. The visualizations make an abstract problem accessible and help communicate the motivation and analysis effectively. Although the performance results are relatively modest, the conceptual perspective is interesting. I was glad to read the paper, and without the concerns below, I would have been inclined to give it a much higher rating.
Critical weaknesses
- The experimental comparisons are far too weak for the claimed contribution. For a paper targeting a top-tier venue, comparing only against standard temperature sampling is insufficient. This is clearly not the only work concerned with improving pass@8, so why are competitive existing methods absent from the comparison? This limited evaluation makes the claimed improvements difficult to find convincing, especially because the accuracy gains are neither particularly consistent nor compelling.
The inconsistencies between the main text and appendix further undermine my confidence. For example, Appendix B states that the interventional algorithms were not rerun on Nemotron, while Table 1 reports latent-seeding results for that model. The number of RL evaluation problems also differs between Section 4.4 and Appendix G. The more closely I read, the more questionable the experimental setup appears, which reinforces my concerns about its rigor. These reporting discrepancies should be clarified, but the lack of competitive comparisons remains a substantive weakness.
- The description of the mechanism is too strong, particularly in its treatment of correlation and causation. Statements suggesting that LLM reasoning implements gradient descent are presented with more certainty than the evidence warrants. The experiments provide empirical evidence, but the framing often makes this interpretation sound established. Not every researcher would agree with that conclusion. The proposed representation and analysis can still be useful, but the wording should be more cautious.
The experimental design also leaves important alternative explanations unresolved. Several analyses demonstrate correlations, yet the discussion reads as though they establish causation. This applies particularly to the phrase analysis and the relationships involving the estimated error field, where other influencing factors have not been sufficiently ruled out. Correlation and causation are not equivalent. In Figure 3, for example, an internal backtracking process could cause the model to write “think again”; the phrase itself need not cause backtracking. Figure 2 intervenes on entire token windows and therefore does not establish the causal role of a particular phrase.
These two concerns are the main reasons for my current low rating. They remain insufficiently addressed in the paper, and I do not think the current version is ready for acceptance. However, I would reconsider my rating if the authors can resolve these concerns.
Questions for authors
-
Why does the evaluation compare only against standard temperature sampling, rather than competitive existing methods for improving multiple-sample success? Are relevant comparisons already available, or is there a justification for their omission?
-
Could you reconcile the Nemotron intervention results in Table 1 with Appendix B? Could you also clarify whether the RL evaluation uses 64 problems or 32 problems with 64 traces each?
-
What existing evidence rules out the possibility that an internal reasoning change produces both the phrase and the trajectory direction in Figure 3? Which conclusions from this analysis are intended to be causal?
-
Given that the evidence is empirical and the speed prediction fails in Section 4.2, what supports the stronger claim that LLM reasoning implements gradient descent? Would you revise the wording to distinguish the observed properties from the proposed interpretation?
5 comments
(W3/Q3)
We ran additional experiments to answer your question about whether the phrases emitted are causally responsible for the gradient alignment. Concretely, we explored if it is the phrase that caused the trajectory to change direction, or an internal state transition that causes both the model to emit a phrase and subsequently the trajectory to change direction.
First, we identified the set of phrases that have the most consistent impact on gradient alignment (regardless of the magnitude of the alignment) across all models and datasets through proper experimentation. In Figure 12 (see Appendix E), we visualize the phrases that correlate with the the largest uphill or downhill effect along the gradient direction.
To determine whether the phrases with a consistent effect (large or small) have a causal effect, we inject them in random positions on held out trajectories, and observe their resulting effect on the gradient alignment. We hope to see that not only do phrases that correlate with uphill directions push the gradient uphill in new settings, but also that the strength of that push is comparable (same for descending phrases). On one hand, if the phrase itself has no causal effect, then inserting it into a context where no internal mechanism caused it would do nothing. On the other hand, if the inserted phrases had causal effect, then they would still push the trajectory the same way (uphill or downhill) along the gradient direction.
In our experiments, we find that phrases that move the trajectory uphill when written by the model, continues to drive the model uphill even when injected into unrelated problems (31/31, 8/8, and 6/6 across the three models). Overall, the sign of the transition direction in the unrelated matches the transition direction of the model's own emission of the phrase (44/47 for R1-1.5B, 15/19 for Qwen3-4B, and 15/19 for Nemotron-4B). Additionally we find that the direction holds for the majority of injected phrases, and that the Spearman correlation between the magnitude of alignment of phrases naturally, as compared to when inserted artificially, is quite high (Spearman 0.95, 0.70, 0.81). Visualization of the complete set of results is provided in Figures 16 and 17 (see Appendix F).
Ultimately, we agree with you and it was not our intention to give the impression or implication that models implement gradient descent. We have gone through the paper again and removed any statements which may imply such a claim. Please let us know if there are any places where our wording is still too strong. We elaborate on this point more in the text below where we address your last question.
| Model | Sign preserved (all phrases) | Climbing phrases still climb | Descending phrases still descend | Cohen's κ | Spearman ρ |
|---|---|---|---|---|---|
| R1-1.5B | 44/47 | 31/31 | 13/16 | 0.85 | 0.95 |
| Qwen3-4B | 15/19 | 8/8 | 7/11 | 0.60 | 0.70 |
| Nemotron-4B | 15/19 | 6/6 | 9/13 | 0.59 | 0.81 |
(W4/Q4)
The goal of our paper was, as the title suggests, to understand and characterize the dynamics of reasoning in token based LLMs.
Our motivation for doing so was to reconcile the differences in perspective in literature surrounding reasoning via continuous iterative refinement and token based CoT. In iterative refinement, models are engineered to descend energy manifolds and slow down at attractor basins. Thus, by characterizing continuous dynamics, we sought to understand if an off the shelf LLM has implicitly learned any aspects of reasoning which are engineered into looped models. We specifically look at two aspects of energy descent: direction and speed.
With respect to direction, we do find that the models policy defines a flow over trajectories which align with the descent of local error gradients beyond chance (see Appendix D for the significant experimental evidence we have added to this effect). So, the flow of trajectories within our dynamical system can be better explained with our error field.
Now getting to your question about the speed of the dynamics, in our analysis we find that within our latent space, unlike some looped models, LLMs do not slow down at regions with lower energy. This observation manifests itself as a deeper issue with reasoning models: they do not know when to stop reasoning. We do not yet understand this behavior, but we hope that with our framework other researchers may further understand and possibly address this issue in the future. Thus, our analysis of speed is to characterize the flow speed and convergence of trajectories.
Ultimately, we wanted to observe and report evidence both in support of and against the possibility that the model implicitly performs an optimization process similar to energy descent. Our broader goal was to characterize reasoning dynamics and gain a better understanding of the underlying computations driving reasoning, an area that, to our knowledge, has not been explored in the literature.
Thanks for taking the time to read our paper thoroughly and for your questions and insightful feedback.
For each question posed, we carefully crafted several new experiments at scale, and made sure any claims we make are backed by empirical evidence. We believe going through this extensive characterization process has further deepened both our appreciation and clarity of the problem which we hope to extend to you.
(W1/Q1)
From the framework in our paper, we hypothesized that a method like latent seeds would increase the diversity of answers reached by the model. Our objective was not to present a new sampling strategy to be used in practice, but merely to highlight that by performing latent perturbations, we could intervene in our model and produce results consistent with this framework: namely higher diversity across rollouts. This was one of the factors due to which we stopped short of comparing it to other techniques. However, after your suggestion we compared our method against all of the existing sampling techniques we could find in prior literature (11 of them in total). We were surprised to find that our latent perturbation strategy performed better than most of the existing technique in terms of pass@8 scores. We believe working in a meaningful latent space provided our strategy with an advantage over the existing sampling techniques. Our experiments spanned 3 different tasks (MATH500, GSM8k, AMC23), and three different models (DeepSeek-R1-1.5B, Qwen3-4B, Nemotron-4B). Complete details about the experiments and the results can be found in Tables 9, 10, and 11 (see Appendix C.1). To be sure of our results, we even increased the evaluation to the full MATH-500 dataset and the full GSM8k evaluation dataset for DeepSeek-R1-1.5B. We believe that these results more convincingly indicate that our framework is the right way to think about reasoning, as it gave us greater control over the model.
Please let us know if there are any other methods you had in mind that you would like us to try.
(W2/Q2)
We sincerely apologize for the typos and the resulting inconsistencies between the Appendix and the main paper. We provide the following clarifications:
The latent seeds based intervention was indeed run on all the models and detailed results for the Nemotron-4B models are in the above table and Table 11 (see Appendix C.1).
All the RL evaluations are performed using 32 problems with 64 rollouts generated per problem.
We have since fixed the above and significantly edited the Appendix to match the same rigor and quality as the main body of the paper.