| title | Think Again or Think Longer? Selective Verification for Budget-Aware Reasoning |
|---|---|
| authors | Sajib Acharjee Dip, Dawei Zhou, Liqing Zhang |
| date | 2026-06-18 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2606.19808 |
| affiliation | Virginia Polytechnic Institute and State University |
| upvotes | 2 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Test-time reasoning is increasingly used as a serving-time control knob, but extra reasoning is not uniformly valuable: it can repair failed attempts, waste compute on already-correct answers, or introduce harmful answer changes. We study this as a deployment allocation problem rather than a new-verifier problem. We introduce \sevra, Selective Verification for Reasoning Allocation, a serving-layer controller that decides whether to preserve a frozen solver's initial answer or invoke active verification. Using a frozen Qwen3-4B solver, we log intervention outcomes and train recoverability-aware gates from serving-visible attempt state. On \mathfive, selective verification reaches 76.3\% accuracy, compared with 75.5\% for always verifying, while reducing post-generation tokens by 26.8\% and harmful flips from 2.2\% to 1.0\%. However, an 8,192-token initial solve reaches 76.0\% accuracy with 28\% fewer total model tokens, showing that selective recovery is useful but not the best tested cost frontier. In frozen transfer to \gsm, the selective policy verifies only 3.0\% of examples, improves accuracy from 93.4\% to 94.5\%, and reduces verification tokens by 91.2\% relative to always verifying; again, a longer initial solve matches its accuracy with fewer realized tokens. On CommonsenseQA, always-on verification hurts, while Self-Consistency@5 improves accuracy at about five times the realized token cost. The resulting deployment rule is: tune the initial budget first, then use selective recovery when explicit checks, bounded retries, auditability, or regression-risk control matter. |
cite
@misc{dip2026think,
title={Think Again or Think Longer? Selective Verification for Budget-Aware Reasoning},
author={Sajib Acharjee Dip and Dawei Zhou and Liqing Zhang},
year={2026},
eprint={2606.19808},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2606.19808}
}