W1. The evidence does not sufficiently establish the claimed mechanisms.
The core concern is that the contrastive term acts, by construction, as gated entropy minimization, while its claimed role in improving semantic use of the input context remains insufficiently established. Specifically, the negative-prompt branch in Eq. (3) is detached (Sec. 3.2). For a fixed generated trajectory and selected set (S), the contrastive loss gradient away from the hinge boundary is
∇θLcontrast=∣S∣1∑t∈S1[Hpos,t>Hneg,t]∇θHpos,t,
where Hpos,t and Hneg,t are the predictive entropies under the original and negative prompts, respectively.
The term therefore uses negative-prompt entropy to minimize gate entropy on the positive branch. A model that ignores the prompt under the same response prefix can have Hpos,t=Hneg,t at all selected positions and incur zero contrast loss. The objective thus admits context-insensitive zero-loss solutions. Its one-sided form also provides no gradient when Hpos,t<Hneg,t. The illustrative token-level examples in Appendix D.1 do not resolve this ambiguity or establish the stronger claim that the objective "enforces strict context adherence."
The interpretation of Hneg as a neutral baseline also requires further validation. PAD replacement may affect predictive entropy through an atypical input structure and removal of semantic information. Table 12 demonstrates sensitivity to negative-prompt construction, but does not isolate improved context use from changes in the entropy baseline and hinge activation pattern.
Similarly, the enrichment of natural-language tokens in Table 9 does not establish their causal importance to reasoning. Table 11 supports selective updating over updating all tokens, but does not isolate the importance of selecting high-entropy positions from the effects of restricting and reweighting the updated positions.
W2. Baseline competitiveness and tuning need clearer justification.
TLM and TTSV fall substantially below Vanilla in several settings in Table 1. For Qwen3-4B-Base, TLM achieves 1.86% accuracy on GPQA compared with 22.1% for Vanilla, while TTSV achieves 3.33% on AIME24 compared with 10.0% for Vanilla. These comparisons demonstrate that SUTA avoids the degradation observed with these baselines, but provide a more limited basis for establishing an advantage over competitive adaptation alternatives. SUTA’s improvements over Vanilla remain meaningful, although their magnitude varies across tasks and models. Improvements on the coding benchmarks are generally modest, as illustrated by LCB v5 (13.5% to 14.5%) and MBPP+ (65.9% to 67.3%) on Qwen3-4B-Base.
Appendix B.1 states that the published default settings were used for TLM and TTSV. Please clarify whether any model-specific tuning was performed, how the suitability of these settings was assessed, and whether comparable tuning budgets and validation procedures were used across methods. A comparison with a directly related entropy-minimization method discussed in Appendix A, where compatible with the same online setting and adaptation budget, would further strengthen the empirical evaluation.
We thank the reviewer for the comments on the positioning of our contribution and on the title; below we specify the differences from related work.
The difference from both works lies mainly in how the supervision signal is formed: 80/20 Rule depends on ground-truth rewards from the environment, and SPINE on a voted self-consistency reward obtained from multiple samples of the same problem; our method requires neither rewards nor voting, with the signal taken directly from trajectories the model generates on streaming data.
Table: Setting comparison with 80/20 Rule and SPINE
Within this setting, our work makes two contributions: (a) it carries the observation about high-entropy positions over to label-free online adaptation and specifies the conditions under which it holds—positions the model has already resolved are not updated, avoiding the injection of bias; and (b) it introduces a negative-prompt contrastive term and a frozen-reference constraint, targeting context use and capability forgetting in label-free self-training respectively (Tables 3 and 10). On the gain of Lcontrast: adding it on top of Ladapt+Lkl raises accuracy from 73.6% to 75.2% (+1.6 points); added on top of Ladapt alone it gives 1.0 point (73.0% → 74.0%, Table 3). This magnitude is consistent with its role as a constraint that limits degradation, whose effect shows up in output behaviour and stability (Tables 10 and Figure 4) rather than in the average-accuracy increment.
We understand the reviewer's concern about the scope of the title, and would like to explain how it was chosen. The title follows from an experimental observation: under the same label-free streaming setting, SUTA is at or above Vanilla on all 8 benchmarks, whereas the compared methods degrade substantially—TLM (i.e. [3]) on Qwen3-4B-Base drops from 22.1% to 1.86% on GPQA, from 65.9% to 38.2% on MBPP+, and from 63.0% to 53.0% on MATH-500. It is precisely this contrast that led us to the possibility of self-improvement during deployment, which earlier methods do not exhibit. "Towards Online Adaptation" therefore expresses that this direction is viable and worth pursuing; it does not claim that online adaptation is introduced here, nor that the problem has been solved.
Our specific novelty claims are stated in the three contributions in Section 1: selective updating at high-entropy positions, the information-gain contrastive term, and the frozen-prior constraint. None of them concerns the online-adaptation setting itself; rather, within that setting they determine where updates are applied and how accumulated drift is limited. If our method merely followed [3], the two should behave similarly under the same setting and budget; the results in Table 1 show that this is not the case, and the difference comes from the selectivity of the updated positions.
Best regards