- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
SPARE learns when a frozen reasoning model has enough information to produce a useful final answer. It identifies answer-related anchors in complete trajectories, verifies an anchor with a readout, and generates dense weak supervision from nearby reasoning-unit endpoints. A linear probe predicts sufficiency from concatenated hidden states. GraphRACE calibrates a threshold-and-persistence stopping policy by reusing shared stopping-event readouts and selecting representative candidate policies. At inference, the frozen policy triggers one guided final answer without online correctness verification. Experiments on four backbones and 758 evaluation examples report substantial net completion-token savings with competitive and often improved accuracy, including a 16.4-point MATH improvement for the 2B backbone.
Critical strengths
-
The anchor-guided supervision is efficient: multiple weak labels are derived from a single verified anchor, avoiding intermediate-answer evaluation at every step. The controlled truncation study motivates the sufficiency-boundary hypothesis, and the fixed and random anchor comparisons support the labeling strategy.
-
The stopping framework is practical: a lightweight linear probe and an offline-calibrated policy require no model modification or online verification, GraphRACE reduces calibration cost, and the token accounting includes readout overhead. The reported accuracy–efficiency results are promising.
Critical weaknesses
-
The largest accuracy gain is not attributed. The 2B MATH result improves from 65.80% to 82.20% with about 50% fewer tokens, but the Full-Reasoning Readout control covers only 4B and 9B; DEER shows a similar gain, so adaptive stopping is not separated from answer elicitation or avoiding budget exhaustion. A matched 2B readout control, generation and scoring details, an error breakdown, and paired uncertainty are needed.
-
The supervision assumptions and GraphRACE are under-validated. The reported AUROC of 0.851 does not measure weak-label agreement or boundary-location error, and the boundary analysis covers one model and 200 MATH problems. The assumption that pre-anchor reasoning is insufficient and post-anchor reasoning is sufficient is also not directly tested. GraphRACE's components are not isolated against simpler calibration under matched budgets.
-
Generalization and presentation need work. All four models are Qwen-based and the tasks are mathematical and scientific, so other model families and reasoning tasks are needed.
Questions for authors
-
Can you explain the source of the 2B MATH gain and report a matched Full-Reasoning Readout control on 2B, including correct-to-wrong and wrong-to-correct transitions, paired uncertainty or additional seeds, and a breakdown of capped, unparseable, and incorrect baseline outputs? How does DEER's similar gain affect the attribution?
-
Beyond the reported detector AUROC, how well do the constructed weak labels agree with actual readout correctness, and how far are anchors and exits from the empirical boundaries? Can you also isolate GraphRACE's components against simpler calibration under matched budgets?
-
Can you evaluate SPARE on non-Qwen model families such as Llama or Gemma, and on reasoning tasks beyond math and science?
3 comments
Follow-up on the Authors' Response
Thank you for your response! Regarding Q1, we agree that the accuracy improvement of the 2B model can be primarily explained by Answer Elicitation, rather than being directly attributed to Adaptive Stopping. Regarding Q2, based on your additional experiments, we acknowledge that GraphRACE is beneficial overall. Regarding Q3, your experiments demonstrate cross-task generalization. However, the proposed method is still evaluated exclusively on Qwen-based models, leaving the question of cross-model-family generalization unanswered. We would therefore be inclined to raise our score from 2 to 2.5, if such a rating were available. However, ICLR does not offer a 2.5 rating.
Thank you for your follow-up and for highlighting the remaining question about model families. We trained and calibrated SPARE for NVIDIA Llama-3.1-Nemotron-Nano-4B-v1.1, a Llama-based backbone, using the same pipeline. We evaluated both Vanilla and SPARE on all 758 problems with greedy decoding in vLLM. Token counts include answer readout.
| Dataset | Vanilla → SPARE accuracy | Token savings |
|---|---|---|
| MATH500 | 90.60% → 90.80% | 28.32% |
| GPQA Diamond | 48.99% → 47.47% | 27.25% |
| AIME 2025 + 2026 (60 problems) | 56.67% → 56.67% | 22.13% |
| Overall (758 problems) | 77.04% → 76.78% | 26.87% |
Summed across batches, end-to-end online generation time fell from 10.30 to 6.94 GPU-hours, a 32.65% reduction. These results extend SPARE’s accuracy–efficiency evaluation to the Llama family.
R1. The source of the 2B gains and the DEER comparison [CW1, Q1]
To examine empty-final effects, the table reports MATH examples defined by a nonempty original Vanilla final answer. FullReader applies SPARE's readout protocol after full reasoning (revised Table 12).
On all MATH500 examples, 2B accuracy is 65.80%/85.20%/82.20% for Vanilla/FullReader/SPARE. Relative to Vanilla, SPARE's correct-to-wrong and wrong-to-correct proportions over all 500 examples are 1.40% and 17.80%.
Both DEER and SPARE dynamically select exits. DEER uses trial answers and confidence, while SPARE uses a hidden-state probe and persistence. In the main table, 2B DEER/SPARE accuracy is 71.37%/70.32%, with mean token costs of 15,313/10,074, illustrating the quality–cost trade-off between stopping signals.
R2. Weak supervision, sufficiency structure, and GraphRACE validation [CW2, Q2]
The supervision audit randomly samples 50 trajectories and 200 pre/post endpoints from the actual 4B training population, yielding readout accuracies of 43%/99%. On the same Math200 diagnostic, hidden-state and fitted position probes achieve AUROCs of 0.851 and 0.650. In the original nine-checkpoint analysis, 126 trajectories exhibit a strict single incorrect-to-correct transition and 12 differ at one checkpoint.
We also added four-model six-candidate simple calibration.
GraphRACE adds 16.34 percentage points of token savings at equal accuracy on 9B, and 9.34 points with a 0.40-point accuracy difference on 4B. Sections 4.1–4.3 now clarify correctness, anchor labels, exit positions, and selection within the fully evaluated, empirically feasible candidate pool; Table 5 reports the budget controls.
R3. Additional tasks, model backgrounds, and greedy deployment [CW3, Q3]
We evaluated four models on 500 examples from two BBH tasks and all 164 HumanEval+ problems using frozen mathematical probes and policies. Code is graded by official execution tests.
Code Plus pass@1 improves on all four models, with 31.59%–59.55% token savings. DeepSeek's R1 distillation covers reasoning patterns and post-training conditions different from native Qwen3.5. We plan to extend evaluation to Llama, Gemma, and other families.
We also generated from scratch on all 758 examples at temperature 0 in vLLM with continuous batching, concurrency 8, and CUDA Graphs. The three-model online results are as follows (new Table 4).
All three models improve accuracy and reduce tokens under greedy generation, showing benefits under fixed decoding and measured runtime acceleration.