- Rating
- 2
- Confidence
- 4(+1)
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes Adaptive Utility-Rational Allocation (AURA), a training-free framework for controlling the reasoning length of large language models. AURA combines a certainty score based on confidence, entropy, coherence, and answer stability with risk-aware safeguards, auxiliary verification, and batch-level token-price adaptation. The stopping decision is formulated by comparing an estimated benefit of further reasoning against its computational cost.
Critical strengths
-
Based on the experimental results, AURA achieved significant token savings on MATH-500 compared to baselines, while maintaining comparable observation accuracy. The paired confidence intervals supported the reduction in token usage, and the service time measurements provided further evidence of the computational advantage.
-
The paper conducted extensive experiments in various different aspects. These analyses provide useful insights into the roles of certainty score, stopping safeguards, auxiliary verification, and budget feedback in adaptive reasoning.
Critical weaknesses
-
Please focus on Sections 3.2–3.5 and Appendix A.1–A.2. The stopping rule compares a certainty-based proxy for loss reduction with a token cost scaled by . However, this paper does not clearly explain how the is selected or whether is calibrated to the loss reduction. The theoretical results assume bounded estimation errors, but not establish that these errors are small in practice. Consequently, it is unclear whether the proposed approach performs meaningful utility optimization or merely implements a heuristically tuned certainty threshold. It is not clear whether the proposed method has achieved meaningful utility optimization, or merely determined a certain threshold for heuristic tuning.
-
As acknowledged by the authors, the proposed stopping rule is equivalent to a certainty threshold when the token price and cost estimate are fixed. Table 4 shows that replacing the four-feature certainty score with confidence alone yields nearly identical accuracy and token usage on MATH-500, while keeping the remaining controller components unchanged. This raises concerns about the additional value of the proposed score composition.
Questions for authors
-
How are the initial token price and utility scale selected? Is there empirical evidence that the proxy accurately estimates the improvement from further reasoning? How sensitive is the stopping performance to these choices?
-
The proposed risk safeguards rely on heuristic scores. What quantitative reliability guarantees, if any, can these safeguards provide? I think the recent paper about efficient reasoning with risk control may provide some insight. For example, see Anytime Safe PAC Efficient Reasoning, ICML, 2026.
3 comments
I thank the authors for their clarifications, which partially address my concerns and confusion, and also make the paper clearer. But, my main concern remains unresolved:
The authors explicitly acknowledge that the continuation-value proxy is a stopping statistic rather than a calibrated estimate of the loss reduction. The theories are based on bounded estimation errors, but there is no empirical evidence that these conditions hold in practice. Consequently, I think the proposed utility-based formulation is essentially a development-tuned certainty threshold with heuristic safeguards and budget feedback, rather than a well-justified utility optimization method.
I also understand that authors regard the controller as the main contribution. But I think that my main concern is closely related to the controller. These concerns are unlikely to be resolved during the discussion, as they may pertain to fundamental theoretical aspects or even the reconfiguration of methodologies. I therefore maintain my original rating of 2.
Thank you for the follow-up. We agree with your description of the mechanism: AURA is a development-tuned certainty threshold with safeguards and budget feedback, and the revision introduces it in these terms (abstract; Sec. 3). The claim of the paper is empirical, lower cost at the same observed accuracy with no trained halting policy, and the proposition is stated as a conditional result (Sec. 3.5). What our first reply did not make clear is what the utility form is used for. It is used for two things, and neither requires a calibrated proxy.
The first is the price. Eq. 1 is, up to a constant, the Lagrangian of minimizing the expected loss under an average-token budget, with as the multiplier, and Eq. 6 is a projected dual update on . For this update to move the cost toward the budget, a higher price must not increase the mean cost. This holds for any stopping statistic, calibrated or not: a higher price lowers the threshold , the safeguards do not depend on the price, and the halt can only move earlier. In Table 5, the update removes the remaining overshoot on both tasks.
The second is the proposition. It does not need itself to approximate the loss reduction . Let be any strictly increasing function, fixed across states, with . Because is equivalent to , the rule of Eq. 5 is the one-step rule for the proxy at the price , and the proposition gives agreement with the exact one-step decision at that price whenever . The condition is therefore on how well certainty ranks states by remaining value, not on the level of the proxy. The level only fixes which price corresponds to which threshold, and AURA does not take the price as given: the budget update moves it. We will state this in Sec. 3.5 and add its proof to App. A.2.
The formulation thus justifies the form of the rule, a certainty threshold whose level is set by a token price, and the mechanism that sets the price. Whether certainty ranks states well is an empirical question, and the submission tests it through outcomes: if the ranking were poor, halting on it would lose accuracy that further reasoning recovers. Under the same controller, the score variants that use 41.8 to 74.9 more tokens reach 93.12–93.20%, against 93.20% (Table 4). At matched tokens, a halting policy learned from trajectories is not observed to do better: AURA minus the RL halter is 0.08 pp [−0.60, 0.76] on MATH-500 and 0.6 pp [−2.1, 3.4] on GPQA-Diamond (Tables 2 and 15).
The other components do not use the level of the proxy either: the safeguards are eligibility conditions, the checks add observations, and the price update uses token counts. The safeguards and checks are there because certainty can be misleading when the model is confidently wrong (Sec. 3.3).
We would be glad to discuss any remaining points.
Response to Reviewer 1PTm
We sincerely thank Reviewer 1PTm for the careful reading and constructive review. Below, we address each point. Tables R1 and R2 are in the general response.
[W1 & Q1] Utility optimization or a tuned certainty threshold; how the price and utility scale are selected; calibration of the proxy
What the rule is. At a fixed price it is a certainty threshold, ϑ=1−λd^/κ, as Sec. 3.2 states. The score (1−Ct)κt serves as a stopping statistic (Sec. 3.2) rather than as a calibrated estimate of the loss reduction, and App. A.2 gives the conditions under which the proposition holds. The abstract now states that the rule is a threshold on a certainty statistic, and Sec. 3.2 describes the score in these terms.
What the utility form adds. It ties the threshold to a token price, and the price is what the batch update moves. Eq. 6 is a projected dual update on the multiplier of an average-budget constraint. The threshold is therefore steered toward the target budget from token counts alone, with no correctness labels. In Table 5, this removes the remaining overshoot: from 6.0 to 0.0 tokens on MATH-500 and from 3.0 to 0.0 on TeleQuAD.
How the two quantities are selected. The utility scale is chosen on the 500-problem development split from {0.75,1,1.25}; the selected value is 1 (App. A.1). With a block cost of 64 tokens, the initial price 0.00150 gives a threshold of 0.904, and 0.00152 gives 0.90272 in the matched setting. The initial price is a starting value that depends on the evaluation setting (App. A.1), and the batch update then moves it toward the target budget. The development search covered the utility scale, the weight of the development risk criterion, the risk threshold, and the consecutive count (81 configurations, App. A.1). Only the ratio λd^/κ enters Eq. 5. The three candidate scales therefore correspond to thresholds 0.872, 0.904 and 0.923 at the initial price. Under the price update, the scale also sets the size of each threshold step, ηd^/κ per token of overrun, whereas the threshold at which the mean cost equals the target does not depend on it.
Sensitivity. With κ=1, a 100-token overrun in a batch raises the price by 0.0001 and lowers the threshold by 0.0064 (App. A.1). In the submission, the ±5% minimum-token-offset diagnostic gives 92.8–93.2% at 626–666 tokens (Table 9), and eight half-weight and double-weight perturbations give 646.0–686.7 tokens (App. A.3.5).
Calibration. The paper does not rely on a calibration claim, since the score is used as a stopping statistic that is compared with a price.
[W2] The value of the four-term score when confidence alone reproduces it
We agree, and the submission reports it. On MATH-500, confidence-only differs from the full score at 3 of 2,500 halts (0.00 pp [−0.12, 0.12]; −0.1 tokens [−0.3, 0.2]). On TeleQuAD, it uses 10.5 fewer tokens [8.3, 12.7] with no established EM difference (0.6 pp [−0.5, 1.8]). We have made confidence-only the default score and present the four-term score as a variant.
The contribution we claim is the controller, not the score. The guards add 0.8 pp on both tasks, probes and verification add 0.4–0.5 pp, and price feedback removes the budget overshoot (Table 5; Table R1). Entropy and stability remain in use as inputs to the risk checks, not as score terms.
[Q2] Reliability guarantees for the heuristic safeguards
Thank you for this question and for the pointer to B-PAC reasoning (Yu et al., ICML 2026), which Sec. 2 now discusses. The safeguards are evaluated empirically in the paper (Table 5). B-PAC reasoning routes queries between a thinking and a non-thinking model and controls the resulting performance loss with anytime-valid guarantees under partial feedback, whereas AURA decides within one reasoning trace and targets an average token budget. A possible extension, which we have not established, is to use AURA's certainty or risk score as the uncertainty score of such a procedure, and to calibrate the stopping threshold on the development split so that the accuracy loss relative to full-budget reasoning is at most α with probability at least 1−δ.
We hope these clarifications address your concerns, and we are happy to answer any remaining questions.