arXiv Artificial Intelligence

From Discovery to Decision: Finite-Budget Recoverability in LLM Voting

1 hour ago 02.10.2026 07:00 👁 1 views
From Discovery to Decision: Finite-Budget Recoverability in LLM Voting

Quick summary

arXiv:2610.01014v1 Announce Type: new Abstract: Voting over multiple LLM responses is a common primitive in test-time scaling and ensemble inference. Collecting more responses can expand the candidate pool and increase the chance that a correct answer is discovered. Under a fixed call budget, a discovered answer still needs to accumulate enough support within the remaining calls to become the final plurality winner, creating a discovery-to-decision gap. In this work, we characterize this gap through the realized vote state and remaining call budget. We derive a sharp recoverability threshold a

Key takeaways

  • arXiv:2610.01014v1 Announce Type: new Abstract: Voting over multiple LLM responses is a common primitive in test-time scaling and ensemble inference.
  • Collecting more responses can expand the candidate pool and increase the chance that a correct answer is discovered.
  • Under a fixed call budget, a discovered answer still needs to accumulate enough support within the remaining calls to become the final plurality winner, creating a discovery-to-decision gap.

Why it matters

The importance of “From Discovery to Decision: Finite-Budget Recoverability in LLM Voting” will be measured by what changes in practice. User behavior, access conditions, verifiable performance and responsible-use outcomes are the signals worth following.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗