Verify, Repair, Repeat, or Stop? Robust Stopping for Noisy Verify-Repair Loops in LLM Agents

• URL: http://arxiv.org/abs/2607.17641v1
• Date: Mon, 20 Jul 2026 07:52:36 GMT
• Title: Verify, Repair, Repeat, or Stop? Robust Stopping for Noisy Verify-Repair Loops in LLM Agents
• Abstract summary: We propose VRR-Stop, a robust stopping framework for noisy verify-repair-repeat loops.<n>VRR-Stop improves final true validity by 60.6 percentage points over fixed five-round repair at an average cost of 0.72 repair rounds.
• Score: 8.346035588810516
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Verify-repair loops are a standard means for large language model (LLM) agents to correct faulty plans in code generation, mathematical reasoning, and tool use. When both the verifier and the repairer are noisy, repair can damage already-correct plans, and reported acceptance keeps rising while true validity falls, so existing methods lack a principled basis for deciding when repair should stop. We propose VRR-Stop, a robust stopping framework for noisy verify-repair-repeat (VRR) loops. A four-parameter noise model separates verifier false acceptance and false rejection from the repair and damage behavior of the repairer. Belief filtering turns repeated verification votes into an estimate of committed validity, and the loop commits or repairs according to the sign of the true marginal gain, which requires only sign identifiability rather than accurate recovery of all parameters. When verifier discrimination approaches zero, calibration itself fails and estimation error can flip the stopping sign, so we pair VRR-Stop with VRR-Guard, an estimation-free fallback that replaces the incumbent candidate only under a sufficient verification margin. On a GSM8K stress setting, VRR-Stop improves final true validity by 60.6 percentage points over fixed five-round repair at an average cost of 0.72 repair rounds. Across settings, stopping reliability is governed jointly by verifier discrimination and the decision margin rather than by the absolute size of estimation error.

Related papers

• Independent Patch Verification for Coding Agents with a Bidirectional Reconstruct-and-Verify Framework [49.16055123488827]
  coding agents powered by large language models can now generate code patches directly from bug reports.<n>No mechanism independently verifies whether it truly resolves the reported problem.<n>We propose RETRACE, a training-free post-generation verification framework.
  arXiv  Detail & Related papers  (2026-08-09T22:59:13Z)
• SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute [62.3458279176813]
  Self-Verifying Refinement is an oracle-free multi-turn reinforcement learning framework.<n>It learns to use self-verification as a compute-control policy.<n>It achieves a macro-average accuracy of 0.563 with only 2.99 inference turns on average.
  arXiv  Detail & Related papers  (2026-07-30T16:20:58Z)
• Beyond Fail-to-Pass: Iterative Hardening of Co-Generated Bug Reproduction Tests and Fixes [55.114939648705395]
  Large language models (LLMs) have made automated program repair increasingly practical for real-world bugs.<n>Bug reproduction tests (BRTs) help close this gap by turning a bug report into an executable, bug-specific signal.<n>We propose CoHarden, a co-generation framework that uses the Lax signal as an in-loop convergence criterion.
  arXiv  Detail & Related papers  (2026-07-22T07:30:07Z)
• Characterizing and Bridging the Diagnostic Gap in eBPF Verifier Rejections [5.3302893005312955]
  eBPF lets developers run custom programs inside the Linux kernel.<n>When the verifier rejects a program, the unclear error makes repair challenging.<n>We present bpfix, which reconstructs where the proof was established and where it was lost from the verifier log.
  arXiv  Detail & Related papers  (2026-07-02T20:33:32Z)
• Denoising Iterative Self-Correction: Structured Verification Loops for Reliable LLM Reasoning [5.634990956257954]
  Large language models produce fluent but often incorrect multi-step reasoning, and naive correction methods risk degrading already-correct answers.<n>We introduce Denoising Iterative Self-Correction (DISC), a test-time procedure that treats verification question outputs as noisy measurements of where a solution may be corrupted.<n>A binary judgment gate controls correction precision by blocking rewrites that would damage already-correct answers while the verifier and corrector together repair errors.
  arXiv  Detail & Related papers  (2026-06-19T20:23:14Z)
• Repair Before Veto: Repair-Augmented Constraint Learning for Contextual Decisions [6.016090674751934]
  We introduce Repair-Augmented Constraint Learning (RACL), a contextual decision framework that lifts known repair operators into the semantics.<n>A candidate is accepted when an affordable repair makes it feasible and preferred enough; otherwise the system returns a structured rejection credit and, when applicable, a repair plan.<n>Across controlled and DB1B-derived benchmarks, RACL recovers the intended credit and repair structure.
  arXiv  Detail & Related papers  (2026-06-01T14:38:04Z)
• Conformal Certification of Reasoning Trace Prefixes [30.432255322700126]
  We introduce CROP (Conformal Reasoning Output Prefixes), a verifier-agnostic calibration procedure for clean- annotated certification.<n>We demonstrate that CROP over- and under-withholding, improving downstream repair accuracy by preserving valid intermediate reasoning.
  arXiv  Detail & Related papers  (2026-05-28T15:31:42Z)
• Guarded Repair for Harm-Aware Post-hoc Replacement of LLM Mathematical Reasoning [0.0]
  GuardedRepair is a best-of-N repair framework that diagnoses cached reasoning traces, selectively triggers repair, and accepts answer-changing candidates.<n>We show that GuardedRepair substantially improves the fixed/broken tradeoff, while also revealing that replacement risk is reduced rather than eliminated.
  arXiv  Detail & Related papers  (2026-05-23T14:51:13Z)
• IMPACT-CYCLE: A Contract-Based Multi-Agent System for Claim-Level Supervisory Correction of Long-Video Semantic Memory [73.22944697933603]
  Existing pipelines produce opaque, end-to-end outputs that expose no intermediate state for inspection.<n>We present IMPACT-Cycle, a supervisory multi-agent system that reformulates long-video understanding as a multimodal iterative claim-level maintenance.
  arXiv  Detail & Related papers  (2026-04-22T03:03:33Z)
• Outcome-Conditioned Reasoning Distillation for Resolving Software Issues [49.16055123488827]
  We present an Outcome-Conditioned Reasoning Distillation(O-CRD) framework that uses resolved in-repository issues with verified patches as supervision.<n>Starting from a historical fix, the method reconstructs a stage-wise repair trace backward from the verified outcome.<n>On SWE-Bench Lite, this approach increases Pass@1 by 10.4% with GPT-4o, 8.6% with DeepSeek-V3, and 10.3% with GPT-5.
  arXiv  Detail & Related papers  (2026-01-30T18:25:39Z)
• CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal [84.71254539482369]
  Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures.<n>We present CARE, a failure-centric post-training framework for multimodal reasoning that turns errors into supervision.<n> CARE improves accuracy and training smoothness while explicitly increasing the share of learning signal that comes from failures.
  arXiv  Detail & Related papers  (2025-12-22T16:34:21Z)
• Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers [90.50039419576807]
  Reinforcement Learning with Verifiable Rewards (RLVR) trains policies against automated verifiers to avoid costly human labeling.<n>To reduce vulnerability to verifier hacking, many RLVR systems collapse rewards to binary $0,1$ during training.<n>This choice carries a cost: it introduces textitfalse negatives (rejecting correct answers, FNs) and textitfalse positives (accepting incorrect ones, FPs)
  arXiv  Detail & Related papers  (2025-10-01T13:56:44Z)
• Specification-Guided Repair of Arithmetic Errors in Dafny Programs using LLMs [79.74676890436174]
  We present an APR tool for Dafny that uses formal specifications as oracles for fault localization and repair.<n>We localize faults through a series of steps, which include using Hoare logic to determine the state of each statement within the program.<n>Our tool achieves 89.6% fault localization coverage and GPT-4o mini yields the highest repair success rate of 74.18%.
  arXiv  Detail & Related papers  (2025-07-04T15:36:12Z)
• Latent Veracity Inference for Identifying Errors in Stepwise Reasoning [78.29317733206643]
  We introduce Veracity Search (VS), a discrete search algorithm over veracity assignments.<n>It performs otherwise intractable inference in the posterior distribution over latent veracity values.<n>It generalizes VS, enabling accurate zero-shot veracity inference in novel contexts.
  arXiv  Detail & Related papers  (2025-05-17T04:16:36Z)
• Error Correction by Paying Attention to Both Acoustic and Confidence References for Automatic Speech Recognition [52.624909026294105]
  We propose a non-autoregressive speech error correction method. A Confidence Module measures the uncertainty of each word of the N-best ASR hypotheses. The proposed system reduces the error rate by 21% compared with the ASR model.
  arXiv  Detail & Related papers  (2024-06-29T17:56:28Z)

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.