发表机构
KAIST（韩国科学技术院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
CoVeR通过冻结句子嵌入覆盖率阈值门控验证器调用，在保持答案准确性的同时削减62-68%的调用，且无需LLM参与路由。
AI 中文摘要
智能体检索系统会发出一个搜索查询序列，并且必须在每一步决定目前收集到的证据是否足以停止。将该决策委托给LLM验证器或提示判断器可以使停止变得可靠，但验证器随后会在每个检索步骤后重新处理不断增长的证据，这会产生大量的重复成本。我们表明，这些调用中的大部分可以被跳过，而不会实质性地改变答案准确性：对冻结的句子嵌入覆盖率边际设置一个单一阈值，即可检测出证据仍然明显不完整的那些状态，并且仅在模糊的剩余部分调用验证器，我们将这一门控称为CoVeR（基于覆盖率的验证器路由）。在三个多跳问答基准上，在全面运行之前固定评估协议的情况下，CoVeR门控智能体在答案准确性上与全预算智能体和始终验证基线相差不到一个EM点。它削减了62-68%的验证器调用，在饱和状态下削减了93%。基于证据计数、词汇重叠或BM25相关性的路由器，无论是单独使用还是组合学习，都会产生较弱的整体权衡；该门控可以跨决策者和智能体规模进行迁移而无需重新调整，其起草器可以蒸馏到冻结编码器之上的一个921k参数头部，从而在路由循环中不留下任何LLM。相同的信号不能替代验证：匹配一个声明远比决定该声明得到支持要容易得多。
英文摘要
An agentic retrieval system issues a sequence of search queries and must decide, at each step, whether the evidence collected so far is enough to stop. Delegating that decision to an LLM verifier or a prompt judge makes stopping reliable, but the verifier then reprocesses the growing evidence after every retrieval step, a substantial repeated cost. We show that most of these calls can be skipped without materially changing answer accuracy: a single threshold on a frozen sentence-embedding coverage margin detects the states in which the evidence is still plainly incomplete, and the verifier is called only on the ambiguous remainder, a gate we call CoVeR (Coverage-based Verifier Routing). Across three multi-hop QA benchmarks, with the evaluation protocol fixed before the full-scale run, the CoVeR-gated agent matches the answer accuracy of both the full-budget agent and the always-verify baseline within a fraction of an EM point. It cuts 62-68% of verifier calls, and 93% in a saturated regime. Routers built on evidence counts, lexical overlap, or BM25 relevance, alone or learned in combination, give weaker overall trade-offs, the gate transfers without re-tuning across deciders and agent scales, and its drafter distills into a 921k-parameter head atop the frozen encoder, leaving no LLM in the routing loop. The same signal cannot replace verification: matching a claim is far easier than deciding the claim is supported.
Comments34 pages, 4 figures. Preprint. Under review
