When Should Multi-Round RAG Stop? Structured Stopping Judgments and Retrieval Reduction in Search-R1

• URL: http://arxiv.org/abs/2608.13237v1
• Date: Thu, 13 Aug 2026 13:42:48 GMT
• Title: When Should Multi-Round RAG Stop? Structured Stopping Judgments and Retrieval Reduction in Search-R1
• Abstract summary: Multi-round retrieval-augmented generation (RAG) must decide when to stop searching as evidence accumulates.<n>We adapt S2G-RAG's structured sufficiency-and-gap judgment to a frozen Search-R1 pipeline.<n>We train a Qwen3.5-2B judge on 3,009 states from 900 disjoint HotpotQA questions.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-round retrieval-augmented generation (RAG) must decide when to stop searching as evidence accumulates. Because the deployed policy is determined by the first STOP on each trajectory, this is a sequential selection problem rather than an independent state-classification task. We adapt S2G-RAG's structured sufficiency-and-gap judgment to a frozen Search-R1 pipeline and train a Qwen3.5-2B judge on 3,009 states from 900 disjoint HotpotQA questions. Search-R1's reasoner, retriever, corpus, prompt, and search budget remain unchanged, while the judge checkpoint and stopping threshold are selected on grouped validation and frozen before confirmatory evaluation. On the confirmatory test set, the resulting policy reduces retrieval calls by 77 (3.70\%) relative to Native Search-R1, while Official Exact Match decreases by 0.625 percentage points. Thus, the trained S2G-style structured judge reduces retrieval while broadly preserving answer accuracy. The result does not imply unchanged or improved accuracy, safe stopping, or lower total inference cost.

Related papers

• Small Language Models as Judges for Rubric-Based Reinforcement Learning [57.707881387886516]
  We study whether smaller language models can serve as efficient and reliable rubric-based judges.<n>We compare three ways of extracting criterion-level judgments from small models: Generative verdicts, Yes/No Logprob margins, and Probe judges.<n>Across both datasets, the Qwen3-1.7B Probe judge achieves the strongest criterion-level agreement among these methods.
  arXiv  Detail & Related papers  (2026-08-30T20:00:17Z)
• Same Agent, Different Answers: A Repeat-Aware Audit of Corpus-Induced Answer Churn in Retrieval-Augmented QA [0.4351760066527804]
  A retrieval-augmented QA system can return different answers after an index expansion even when its requested model identifier, prompt, retrieval policy, evidence depth, rendering, and exposed generation controls are held fixed.<n>We call the hidden phenomenon accuracy-blind answer churn and introduce the emphSnapshot Compatibility Audit, which estimates excess answer churn by subtracting same-snapshot repeat disagreement from cross-snapshot disagreement.
  arXiv  Detail & Related papers  (2026-08-24T06:40:09Z)
• BOUND: Brief-Guided Corrective Preference Distillation at Search-Control Boundaries [82.41764922522565]
  BOUND is a brief-guided corrective preference distillation framework for persistent search drift.<n>It outperforms Trajectory SFT by 5.6 EM points on Bamboogle and 4.8 accuracy points on BrowseComp-Plus.
  arXiv  Detail & Related papers  (2026-08-09T15:32:16Z)
• Know Before You Fetch: Calibrated Retrieval-Budget Allocation for Retrieval-Augmented Generation [10.60293484295824]
  We formulate adaptive RAG as calibrated retrieval-budget allocation.<n>We calibrate sequence log-probability and prefix-logit uncertainty signals into probabilities of correctness.<n>For sequence log-probability, ECE drops from 0.275 to 0.062 on TriviaQA, 0.643 to 0.009 on NQ, and 0.711 to 0.031 on MS MARCO.
  arXiv  Detail & Related papers  (2026-06-29T08:36:33Z)
• R$^2$-Searcher: Calibrating Retrieval and Reasoning Boundaries for Agentic Search [59.034878430183305]
  R$2$-Searcher explicitly explores and calibrates the retrieval and reasoning boundaries.<n>We show that R$2$-Searcher significantly outperforms state-of-the-art agentic search methods in answer accuracy and retrieval-reasoning quality.
  arXiv  Detail & Related papers  (2026-06-26T19:44:34Z)
• When Retrieval Metrics Mislead: Measuring Policy Signal in Long-Horizon Tool-Use Agents [13.484205922478163]
  Exact-match retrieval recall is often used as a proxy for whether a retriever supplies useful policy context to a downstream decision model.<n>We test this proxy for pre-action policy classification in tau-bench using Qwen2.5-3B/7B classifiers.
  arXiv  Detail & Related papers  (2026-06-22T20:57:11Z)
• TASR: Training-Free Adaptive Stopping for Iterative Retrieval [12.177557521540082]
  Iterative retrieval-augmented generation agents commonly overspend by continuing to retrieve after the model has converged on an answer.<n>We propose TASR (Training-Free Adaptive Stopping Rule), a one-line predicate that fires when the model repeats its previous-round normalized answer.
  arXiv  Detail & Related papers  (2026-06-11T18:35:14Z)
• Step-wise Rubric Rewards for LLM Reasoning [72.17879367869503]
  Reinforcement Learning with Verifiable Rewards (RLVR) is widely used to improve reasoning in large language models.<n>We find 18.2% of steps in correct responses are wrong yet positively rewarded.<n>Across six mathematical reasoning benchmarks, SRaR improves average accuracy over RaR by 3.57 points.
  arXiv  Detail & Related papers  (2026-05-17T07:08:14Z)
• SURE-RAG: Sufficiency and Uncertainty-Aware Evidence Verification for Selective Retrieval-Augmented Generation [6.604874054866016]
  We present SURE-RAG, a transparent aggregation protocol built on the observation that evidence sufficiency is a set-level property.<n>A shared pair-level claim-evidence verifier produces local relation distributions, which SURE-RAG aggregates into interpretable answer-level signals.<n>We evaluate on HotpotQA-RAG v3, a controlled multi-hop benchmark, under an artifact-aware protocol.
  arXiv  Detail & Related papers  (2026-05-05T09:05:40Z)
• Controlling Authority Retrieval: A Missing Retrieval Objective for Authority-Governed Knowledge [0.0]
  We call this CAR: retrieving the currently active authority for a semantic anchor q, that is, front(cl(A_k(q))).<n>We evaluate three real-world datasets: security advisories, SCOTUS overruling pairs, and FDA drug records.<n>A GPT-4omini experiment shows RAG produces explicit "not patched" claims for 39% of queries where a patch exists.
  arXiv  Detail & Related papers  (2026-04-15T23:56:35Z)
• PAR$^2$-RAG: Planned Active Retrieval and Reasoning for Multi-Hop Question Answering [57.89576196160413]
  Large language models (LLMs) remain brittle on multi-hop question answering (MHQA)<n>We propose textbfPlanned Active Retrieval and Reasoning RAG (PAR$2$-RAG), a two-stage framework that separates emphcoverage from emphcommitment.
  arXiv  Detail & Related papers  (2026-03-30T23:52:54Z)
• ReFIT: Relevance Feedback from a Reranker during Inference [109.33278799999582]
  Retrieve-and-rerank is a prevalent framework in neural information retrieval. We propose to leverage the reranker to improve recall by making it provide relevance feedback to the retriever at inference time.
  arXiv  Detail & Related papers  (2023-05-19T15:30:33Z)
• Certified Error Control of Candidate Set Pruning for Two-Stage Relevance Ranking [57.42241521034744]
  We propose the concept of certified error control of candidate set pruning for relevance ranking. Our method successfully prunes the first-stage retrieved candidate sets to improve the second-stage reranking speed.
  arXiv  Detail & Related papers  (2022-05-19T16:00:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.