SOURCE-LINKED INTELLIGENCE

Beyond Confidence: Test-Time Scaling for Multi-Turn Search Agents via Retrieval Grounding

arXiv · AI, language, vision and robotics · article · Aug 25, 2026 · UTC

Confidence-based voting aggregates parallel LLM rollouts by weighting each with internal signals such as token log probabilities, and has been actively studied for single-turn reasoning. However, modern LLMs increasingly act as multi-turn search agents that retrieve and condition on external documents. In this paper, we show that confidence-based voting transfers poorly to this multi-turn setting, and identify the underlying failure reason as copy inflation: when retrieved documents are appended to an agent's context, tokens copied from those documents receive systematically inflated log proba

Read original source ↗ Open in workspace

recordType

paper

region

Global