HALT: Verification-Aware Stopping for Retrieval-Augmented Search Agents

2026-08-03

AI Summary

This work addresses the redundancy, latency, and interference caused by continuous retrieval in retrieval-augmented search agents for multi-hop question answering. It proposes HALT, a lightweight verification-aware stopping strategy that formulates the stopping decision as an evidence coverage problem: retrieval terminates only when accumulated evidence sufficiently supports all expected sub-question claims. HALT is the first approach to tie the stopping mechanism directly to claim–evidence alignment rather than relying on generator confidence, and it distinguishes between deployable scenarios and diagnostic upper bounds, enabling runtime control without retraining. Evaluated on three multi-hop QA benchmarks, HALT substantially reduces redundant retrieval while largely preserving exact-match accuracy; using automatically generated claims already yields significant cost savings, while oracle claims reveal even greater optimization potential.

Abstract

Retrieval-augmented search agents answer multi-hop questions by repeatedly issuing search queries and accumulating evidence. This creates a stopping problem: after the necessary evidence has appeared, further retrieval often adds cost, latency, and distracting context rather than useful information. We frame stopping as evidence coverage rather than generator confidence, and introduce HALT, a lightweight verification-aware policy that leaves the search agent unchanged. Given expected hop claims, HALT stops only when cumulative evidence supports each required claim. Across three multi-hop QA benchmarks, HALT reduces redundant search while largely preserving exact match. We separate a deployable setting, where hop claims are generated from the question, from a diagnostic upper bound that uses gold supporting-fact annotations: generated claims give smaller but still exact-match-preserving savings, while gold claims show the larger savings available when hop targets are clean. Baseline comparisons and ablations show that this behavior is driven by claim-evidence alignment rather than generic sufficiency, fixed stop positions, or lexical overlap. Open-corpus pilots further suggest that HALT abstains when coverage cannot be reliably verified. Overall, evidence coverage provides a practical runtime control signal for improving retrieval-augmented agents without retraining or modifying the host agent.

Problem

• retrieval-augmented search agents
• stopping problem
• evidence coverage
• multi-hop QA
• redundant retrieval

Innovation

• retrieval-augmented generation
• stopping policy
• evidence coverage
• multi-hop QA
• verification-aware