cs.AINov 2, 2026

Value-Conditioned Proposal Acquisition for Test-Time Reasoning

Authors: Zeyan Li, Jianfeng Xu

Organizations: Shanghai Jiao Tong University Shanghai, China

Abstract

Sampling and selection spend test-time compute inside a candidate pool, but they cannot recover a correct answer that never enters it. We introduce ValueFormation, a test-time policy that decides after each primary-model draw whether to stop, continue sampling, or acquire one proposal from a heterogeneous reasoning specialist. The three actions are compared on one cost-regularized value scale learned from vote-state features; the calibration is frozen across tasks and primary models, and acquired proposals are accepted only through a frozen posterior comparison. On held-out MATH-500, one Llama-fitted calibration improves over the strongest of eight identically evaluated baselines by more than fifteen points for each of three 8B primaries and transfers unchanged to Qwen3-14B. Removing acquisition lowers Llama MATH accuracy by 20.43 points, while same-trace and same-access replays attribute the gain to state-conditioned acquisition rather than specialist access alone. Where primary coverage is high, as on GSM8K, acquisition is rare and gains mainly come from cheaper allocation; on MBPP, a fixed code route attains the top accuracy at the lowest interaction cost. Varying the token price monotonically reduces calls without retraining.

Figures & tables

Explore similar work

Oct 19, 2026

BOSS: Token-Budgeted Online Sampling and Selection for LLM Reasoning

Test-time scaling can improve LLM reasoning, but existing approaches typically adapt generation or apply answer selection after a predetermined generation schedule. We study within-instance allocation: under a hard per-instance prompt-plus-completion token cap, when should inference stop, generate another candidate, or spend residual tokens adjudicating candidates already observed? BOSS is a training-free policy for this three-way decision, with worst-case budget checks before every generation and judge call. Its key contribution is online generation-adjudication allocation under one shared token ledger. Across two Llama-3.1 models and four reasoning benchmarks, BOSS attains the highest accuracy in 22 of 24 model-task-budget cells under the common hard cap. At Llama-3.1-8B and B=4k, it reaches 60.5 macro-average accuracy versus 58.6 for Adaptive-Consistency, 59.1 for TALE-EP, and 58.9 for fixed-schedule League. On identical Stage-I candidate pools, randomized A/B judging with repeated voting improves plurality from 58.4 to 60.3, with the full BOSS selector reaching 60.5. Approximately matched-cost controls further characterize how the benefit of adjudication changes with available inference budget. Together, these results establish generation-adjudication allocation as a distinct design axis for reasoning under strict per-instance caps.
May 26, 2026

Uncertainty-Aware Budget Allocation for Adaptive Test-Time Reasoning

Sampling multiple responses improves language model reasoning, but uniform compute allocation is inefficient because easy questions are over-sampled while hard questions remain under-explored. We propose Uncertainty-Aware Budget Allocation (UAB), a concave integer optimization framework that reallocates a fixed sampling budget using uncertainty estimated from the initial samples themselves. In Phase-1, every question receives a small fixed number of generations. Their answer disagreement, measured by vote entropy, provides a difficulty signal while these generations contribute to the final vote. In Phase-2, the remaining budget is allocated by a marginal-greedy algorithm that optimally solves a concave coverage-maximization surrogate, concentrating samples on questions whose initial answers disagree. Across five open-weight models (1.5B--27B parameters) and five reasoning benchmarks of varying difficulty, UAB improves average accuracy by +2.3%+2.3\% over uniform allocation, and achieves gains of up to +5.5%+5.5\% on individual benchmarks, with the largest gains in low-resource settings. Moreover, UAB meets the target budget exactly and requires no auxiliary model or additional LLM calls. Code is publicly available at https://github.com/manhitv/UAB.
Aug 6, 2026

Refining Over Resampling: Test-Time Self-Correction for LLM Reasoning

Test-time scaling improves LLM reasoning by using additional inference compute, but wider sampling alone can suffer from diminishing returns: new rollouts often repeat existing answer patterns instead of adding useful reasoning diversity. Verifier-based selection offers an alternative, but its performance depends on the calibration of an external reward model. We propose a verifier-free breadth--depth refinement framework that uses test-time compute to both explore and improve candidate solutions. The method samples multiple independent reasoning rollouts, refines each rollout through iterative self-critique and self-correction, and aggregates the refined answers by majority voting. Breadth preserves diverse initial attempts, while depth repairs local reasoning errors before aggregation. Across AIME24, AIME25, AMC, OlympiadBench, and MATH500, our method consistently improves over greedy decoding, majority voting, verifier-based best-of-NN, beam search, and lookahead decoding across multiple open-weight models. For instance, with Qwen2.5-1.5B, accuracy increases from the strongest verifier-based baseline to 58.0%58.0\% on MATH500, and from 25.0%25.0\% to 32.5%32.5\% on AMC. These results show that test-time compute can be more effective when used to refine sampled trajectories rather than only to sample more candidates or rely on verifier-guided selection.