Independent Patch Verification for Coding Agents with a Bidirectional Reconstruct-and-Verify Framework

• URL: http://arxiv.org/abs/2608.08950v1
• Date: Sun, 09 Aug 2026 22:59:13 GMT
• Title: Independent Patch Verification for Coding Agents with a Bidirectional Reconstruct-and-Verify Framework
• Abstract summary: 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.
• Score: 49.16055123488827
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Autonomous coding agents powered by large language models can now generate code patches directly from bug reports, but a fundamental gap remains: once a patch is produced, no mechanism independently verifies whether it truly resolves the reported problem. Prior work has sought to address this through iterative self-refinement and inference-time scaling, but these approaches either review the patch under the same interpretation that produced it or broaden candidate generation without verifying individual patches, and neither provides an explicit verification signal for assessing patch correctness. We propose RETRACE, a training-free post-generation verification framework that derives such a signal through bidirectional reconstruction and reconciliation. When a coding agent generates a candidate patch for an issue, RETRACE performs forward reconstruction to build an explicit repair rationale from the issue and the agent's trajectory; backward reconstruction then independently infers, from the patch and its trajectory alone and without access to the original issue, a description of the problem the patch appears to address, and compares this reconstruction against the original issue to produce an alignment verdict; a reconciliation stage then checks the consistency between the forward rationale and the patch, diagnoses the source of any misalignment, and either submits the patch or produces targeted revision guidance. Evaluated on SWE-bench Verified with two backbones (GPT-5-mini and MiniMax-2.5), RETRACE lifts Pass@1 by 7.0% and 3.6% respectively on the mini-SWE-agent scaffold, and delivers comparable gains on OpenHands without modification. Ablation experiments show that both the forward and backward stages contribute to the overall improvement and that adding reconciliation yields further gains.

Related papers

• Claim Plane: Enforceable Change Intents and Dynamic Scope for Parallel Coding Agents [1.4721615285883427]
  This paper presents Claim Plane, a model-agnostic coordination architecture that treats concurrent software change as a pre-write admission problem.<n>A deterministic control plane atomically admits compatible intents, constrains same-file parallelism to declared regions, serializes unresolved overlap, tracks dependency invalidation, and fails closed on ambiguous authority.<n>During execution, a contingent mutation does not reserve write ownership initially; the first attempted mutation triggers atomic scope promotion and re-admission against the current active set.
  arXiv  Detail & Related papers  (2026-07-24T02:30:50Z)
• AuditWeave: A Tamper-Evident, Auditor-Navigable Evidence Layer for AI-Assisted and Data-Transformation Workflows [0.0]
  AuditWeave is a lightweight Python library that records the steps of AI-assisted and data-transformation into a single hash-chained ledger.<n>We describe the design and evaluate recording overhead, scalability, and tamper-detection correctness on the reference implementation.
  arXiv  Detail & Related papers  (2026-06-14T21:46:04Z)
• EviACT: An Evidence-to-Action Framework for Agentic Program Repair [21.78498442884825]
  EviACT is an agentic APR framework that coordinates three evidence-driven guardrails across repair stages.<n>It improves resolve rate over the strongest reported comparable baselines by 1.6-6.0 percentage points.<n>It shows 70.1-88.6% lower reported per-bug API cost where baseline costs are available.
  arXiv  Detail & Related papers  (2026-05-26T16:17:47Z)
• ContraFix: Agentic Vulnerability Repair via Differential Runtime Evidence and Skill Reuse [10.503895811137095]
  Large language model (LLM) agents are increasingly used for automated vulnerability repair.<n>Recent empirical results show that these agents still struggle with real-world vulnerabilities.<n>We present ContraFix, an agentic framework that couples runtime evidence with reusable repair skills.
  arXiv  Detail & Related papers  (2026-05-17T13:48:25Z)
• 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)
• Beyond Crash-to-Patch: Patch Evolution for Linux Kernel Repair [2.267311896805228]
  Linux kernel fixes undergo iterative revision on mailing lists before acceptance, with reviewer feedback shaping correctness, handling, and API compliance.<n>We present a large-scale study of kernel patch evolution, reconstructing 6946 syzbot-linked bug-fix lifecycles.<n>We develop PatchAdvisor, a repair framework that integrates retrieval-based memory with a fine-tuned diagnostic advisor to guide a coding agent toward reviewer-aligned patches.
  arXiv  Detail & Related papers  (2026-04-04T20:23:32Z)
• 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)
• Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction [58.51530390018909]
  Large Language Model based multi-agent systems excel at collaborative problem solving but remain brittle to cascading errors.<n>We present MASC, a metacognitive framework that endows MAS with real-time, unsupervised, step-level error detection and self-correction.
  arXiv  Detail & Related papers  (2025-10-16T05:35:37Z)
• RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair [75.40584530380589]
  We propose a novel Retrieval-Augmented Patch Generation framework (RAP-Gen) RAP-Gen explicitly leveraging relevant fix patterns retrieved from a list of previous bug-fix pairs. We evaluate RAP-Gen on three benchmarks in two programming languages, including the TFix benchmark in JavaScript, and Code Refinement and Defects4J benchmarks in Java.
  arXiv  Detail & Related papers  (2023-09-12T08:52:56Z)

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.