- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
The paper proposes a novel method for latent reasoning (PLaT) that supports inspection of the latent states through a textual representation and a predicting a dynamic number of states dependent on the query. The method approaches latent reasoning through a planner module, generating latent states through full recurrence, paired with a decoder module, decoding chunks of latents states into text. The 2 modules are trained jointly by supervising the decoder to reconstruct chunks of tokens conditioned on the matching chunk of latent states. The method is evaluated on mathematical reasoning in 2 settings and is shown to improve the coverage in some cases (Pass@K) compared to other latent reasoning methods while maintaining lower latency compared to the CoT baseline.
Critical strengths
- The method provides a novel architecture supporting joint generation of latent planning states and conditioned text
- The paper includes evaluation on realistic mathematical reasoning tasks (MATH-500/AIME), which is sometimes lacking in latent reasoning papers, with an advantage compared to other latent reasoning methods on some of the tasks.
Critical weaknesses
- It is unclear what is the added value of the proposed method in terms of performance, efficiency or interpretability. PLaT does not seem to consistently outperform latent reasoning baselines in terms of performance (Pass@K) and leads to higher latency. In terms of interpretability via the decoder module, how reliable are the textual representation if coverage improves with repeated sampling conditioned on the same latent state?
- The presentation and writing of the paper is hard to follow, there are many instances in the text where undefined or unrelated terms/concepts are introduced making understanding difficult.
- A few important related work are missing, introducing either more modern baselines or methods with similar design. See for example [1],[2] which have similar design of latent states coupled with textual representation and [3][4] for additional baselines.
Questions for authors
- How are the CODI and COCONUT baselines trained on the OpenR1-Math-220k dataset, specifically how did you determine the number of latent states and are those ablated? the standard values are likely not tuned to handle CoT traces available in this dataset.
- Does training of PLaT rely on back-propagation through time during training? The related work in [2],[3],[4] propose methods to allow parallel training, are those applicable to PLaT?
[1] HYBRIDCOT: INTERLEAVING LATENT AND TEXTCHAIN-OF-THOUGHT FOR EFFICIENT REASONING, Shen et al [2] Latent Reasoning with Supervised Thinking States, Amos et al [3] Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains Tan et al [4] Parallel Continuous Chain-of-Thought with Jacobi Iteration Wu et al
6 comments
Response to Reviewer bf6G (2/2)
Response to W3
Thank you for pointing out these works. We will expand Section 2.2 and the experimental comparisons to address both aspects of your comment:
- Related designs [1,2]. HybridCoT interleaves latent states and key text tokens; Thinking States learns supervised thought tokens and feeds their embeddings into subsequent input processing. Both explicitly connect internal computation with text and deserve discussion alongside PLaT. We will add these references and explain the shared design motivation and the different role of text: PLaT's independent Decoder provides textual inspection without feeding decoded text back into planning.
- Additional baselines [3,4]. CoLaR learns probabilistic compressed embeddings, making it relevant to sampled-coverage comparisons; PCCoT updates latent positions in parallel, making it relevant to efficiency comparisons. CoLaR is already cited in the Introduction and Section 2.2; we will expand its discussion and add PCCoT. We will also include both baselines in the revised experiments under the same backbone and training-data setting.
Response to Q1
We retain the published latent counts, with six latent states for each baseline. This choice follows the original studies: Coconut reports that adding three continuous thoughts at a curriculum-stage transition causes a sharp training-loss increase and greater instability (Appendix C.1). CODI's GSM8K latent-count ablation peaks at six, with longer latent chains introducing optimization difficulties (Section 4.2, Figure 5). We therefore use these reference settings on OpenR1. We will add an OpenR1 latent-count ablation to the revised experiments, reporting accuracy and training stability; retraining these configurations cannot be completed within the rebuttal period.
Response to Q2
- Does PLaT use BPTT? Yes. Each Planner state depends on earlier generated states, with no gradient detachment between steps. A later segment's reconstruction loss therefore propagates through earlier state-generation steps to update the Planner's trainable parameters (Section 3.3).
- Are the parallel training methods in [2,3] directly applicable? No. Thinking States constructs training states from annotated thought tokens; CoLaR uses compressed text embeddings. Their parallel training relies on these known state inputs. PLaT learns its latent states through text reconstruction and feeds predicted states into subsequent Planner steps, so those known inputs are unavailable. Teacher forcing within the Decoder does not remove this Planner dependency.
- Is PCCoT [4] applicable? Yes. During training, the number of latent groups is known from the supervised text segmentation. Jacobi iteration can therefore update these positions in parallel within each iteration while retaining PLaT's Decoder reconstruction objective. Gradients would propagate through the iterations, so this approach parallelizes latent positions while preserving dependencies between successive iterations. Using fewer iterations than required to recover the sequential rollout would approximate the original Planner computation.
I thank the reviewer for the thoughtful and detailed response which partially addresses my concerns, I am detailing the main remaining items below.
My main concern is on how to interpret the relative advantage of the method compared to the baselines. If I understand the authors correctly, the claim is that PLaT shows gains in pass@k as k increases and specifically at larger values of k. this still leaves the following concerns unresolved:
- in Table 1 considering it seems the advantage of PLaT is consistent only at k=128 but no larger values of k are considered - considering either larger values and/or plotting the curve of pass@k against k could strengthen the results.
- in Table 4 it seems that at k=128 CODI performs better on AIME 2024, although PLaT uses different hyperparameters than in table 1.
Can you please elaborate on your response about interpretability (possibly unclear due to poor phrasing of the question on my end). My question is: if the results suggests that the pass@K performance of PLaT improves with increased k, i.e. repeated sampling of different text sequences conditioned on the same latent improves coverage and therefore leads to meaningfully different outputs, how can one:
- decide which text sequence represents the latent most faithfully allowing to interpret it
- infer which part of the reasoning is encoded in the latent representation and which is executed by the decoder module
due to these remaining concerns I am keeping my score.
Response to Reviewer bf6G (1/2)
Dear Reviewer bf6G, we appreciate your review. Our responses to your questions are as below.
Response to W1
Table R1(a). Common-selector results
Table R1(b). Candidate-generation time and coverage
Table R1(c). PLaT full-chain correctness and solution-strategy diversity; counts and percentages of all 1,319 GSM8K questions
Response to W2
We have clarified the terminology and notation in the marked revision PDF (Table R2 below). In particular, we describe the Planner's state update directly, distinguish tokens from text segments, and explain how Figure 2 corresponds to the equations. We also explain how the same Decoder reads intermediate reasoning and final answers, with its answer signal controlling stopping, and name the Section 4.4 analysis by the quantities measured. The revised passages are marked in red. If any other terms or passages remain unclear, we would appreciate your pointing them out so that we can clarify them further.
Table R2. Terminology and notation corrections in the marked revision