Test-Time Scaling via Budgeted Multi-Attribute Verification

The paper introduces “BMA-GAI”, an algorithm for test-time scaling that jointly selects which candidates to inspect and which verification attributes to evaluate under a shared computational budget. It frames the problem as multi-attribute good-arm identification, where each candidate is an arm evaluated across several costly attributes, aiming to certify as many candidates as possible whose mean scores exceed thresholds on all attributes. The authors provide asymptotic coverage guarantees, an information-theoretic converse, and demonstrate that “BMA-GAI” allocates verification resources more efficiently and certifies more high-quality candidates than competing methods on synthetic benchmarks and an LLM answer-verification task.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• benchmarks