Beyond Fail-to-Pass: Iterative Hardening of Co-Generated Bug Reproduction Tests and Fixes

• URL: http://arxiv.org/abs/2607.19843v1
• Date: Wed, 22 Jul 2026 07:30:07 GMT
• Title: Beyond Fail-to-Pass: Iterative Hardening of Co-Generated Bug Reproduction Tests and Fixes
• Abstract summary: 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.
• Score: 55.114939648705395
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) have made automated program repair (APR) increasingly practical for real-world bugs, but repairing directly from bug reports remains underconstrained. Bug reproduction tests (BRTs) help close this gap by turning a bug report into an executable, bug-specific signal that can guide repair and validate candidate patches. Existing work has therefore studied BRT generation as a core subproblem in APR and mainly evaluates a generated BRT using the fail-to-pass (F->P) criterion, which requires the test to fail on the buggy code but pass on the golden fix. We show that F->P alone is insufficient when the goal of a BRT is to improve downstream repair. In particular, some F->P BRTs are lax, reproducing the observed symptom yet still admitting plausible-but-incorrect patches. We formalize this missing quality dimension by separating F->P BRTs into rigorous and lax ones, and show empirically that only the former consistently improve repair success. We further find that co-generation introduces test--fix error coupling, where the in-trajectory fail-to-pass (F->P) check can pass even when both the generated patch and generated test are wrong. Based on these findings, we propose CoHarden, a co-generation framework that uses the Lax signal as an in-loop convergence criterion. CoHarden first generates a test before any fix, then iteratively hardens the test and fix against surviving mutation patches until the generated test no longer admits Lax regressions. Experiments show that CoHarden reaches 69.4% Resolved and 78.9% F->P on SWE-bench Verified, outperforming the strongest fix-only and cogeneration baselines by +9.6 and +7.9 percentage points in Resolved, respectively, with consistent gains across LLM backbones and benchmarks.

Related papers

• ExecCritic: Learn to Test, Test to Improve for Coding Agents [68.42713285082912]
  Execution feedback can guide coding agents toward correct repository repairs, but only when the tests capture the behavior requested by the issue.<n>We introduce ExecCritic, combining a test--verify--revise scaffold with a role-specific reinforcement learning recipe for training agents within it.<n>The scaffold separates test construction from source-code repair: a Test agent independently generates repository-native tests, a fail-closed harness qualifies and freezes them, and a Repair agent revises source code from their execution feedback without changing the tests.
  arXiv  Detail & Related papers  (2026-09-08T17:53:37Z)
• 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)
• FailForge: Distilling Procedural Competence from Persistent Failures into Code Agents [49.519184792774304]
  FailForge is an agentic framework that converts failed rollouts into training signal.<n>FailForge recovers over 26% of previously failed instances at marginal additional cost.
  arXiv  Detail & Related papers  (2026-08-09T08:22:57Z)
• AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents [83.37969790806069]
  LLM agent failures are difficult to debug because the step where an error surfaces is often not the one that caused it.<n>We present Agent DebuggerX, an open-source framework that organizes debug as a closed loop of Detect, Attribute, Recover, and Rerun.<n>At its core, Deep Debugger performs multi-turn root-cause diagnosis through global trajectory understanding.
  arXiv  Detail & Related papers  (2026-07-21T06:21:13Z)
• SWE-Doctor: Guiding Software Engineering Agents with Runtime Diagnosis from Multi-Faceted Bug Reproduction Tests [18.192718828200782]
  We propose SWE-Doctor, a software issue resolution agent that guides patch generation with runtime diagnoses derived from multi-faceted BRT executions.<n>SWE-Doctor consistently outperforms existing agents across all 10 LLM-benchmark combinations.
  arXiv  Detail & Related papers  (2026-07-01T14:27:12Z)
• Are Benchmark Tests Strong Enough? Mutation-Guided Diagnosis and Augmentation of Regression Suites [49.16055123488827]
  Insufficiently strong test suites can admit plausible yet semantically incorrect patches, inflating reported success rates.<n>We introduce STING, a framework for targeted test augmentation that uses semantically altered program variants as diagnostic stressors.<n>STING produces 1,014 validated tests spanning 211 instances and increases patch-region line and branch coverage by 10.8% and 9.5%.
  arXiv  Detail & Related papers  (2026-04-02T01:13:40Z)
• Outrunning LLM Cutoffs: A Live Kernel Crash Resolution Benchmark for All [57.23434868678603]
  Live-kBench is an evaluation framework for self-evolving benchmarks that scrapes and evaluates agents on freshly discovered kernel bugs.<n> kEnv is an agent-agnostic crash-resolution environment for kernel compilation, execution, and feedback.<n>Using kEnv, we benchmark three state-of-the-art agents, showing that they resolve 74% of crashes on the first attempt.
  arXiv  Detail & Related papers  (2026-02-02T19:06:15Z)
• Dynamic Cogeneration of Bug Reproduction Test in Agentic Program Repair [4.994693185232122]
  Bug Reproduction Tests (BRTs) have been used in many agentic Automated Program Repair (APR) systems.<n>In practice, when developers submit a patch, they often implement the BRT alongside the fix.<n>Cogeneration allows the APR agent to generate BRTs for at least as many bugs as a dedicated BRT agent.
  arXiv  Detail & Related papers  (2026-01-27T01:02:57Z)
• DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems [48.971606069204825]
  DoVer is an intervention-driven debug framework for large language model (LLM)-based multi-agent systems.<n>It augments hypothesis generation with active verification through targeted interventions.<n>DoVer flips 18-28% of failed trials into successes, achieves up to 16% milestone progress, and validates or refutes 30-60% of failure hypotheses.
  arXiv  Detail & Related papers  (2025-12-07T09:23:48Z)
• Repair-R1: Better Test Before Repair [2.982543556561469]
  APR aims to automatically locate program defects, generate patches and validate the repairs.<n>Current APR methods typically utilize test cases only during the inference stage.<n>We propose Repair-R1, which introduces test cases into the model's training phase and shifts test generation to precede repair.
  arXiv  Detail & Related papers  (2025-07-30T17:24:05Z)
• AssertFlip: Reproducing Bugs via Inversion of LLM-Generated Passing Tests [0.7564784873669823]
  We introduce AssertFlip, a technique for automatically generating Bug Reproducible Tests (BRTs) using large language models (LLMs)<n>AssertFlip first generates passing tests on the buggy behaviour and then inverts these tests to fail when the bug is present.<n>Our results show that AssertFlip outperforms all known techniques in the leaderboard of SWT-Bench, a benchmark curated for BRTs.
  arXiv  Detail & Related papers  (2025-07-23T14:19:55Z)
• Agentic Bug Reproduction for Effective Automated Program Repair at Google [9.64193881099048]
  This paper investigates automated BRT generation within an industry setting, specifically at Google.<n>We adapt and evaluate a state-of-the-art BRT generation technique, LIBRO, and present our agent-based approach, BRT Agent.<n>Our results show that providing BRTs to the APR system results in 30% more bugs with plausible fixes.
  arXiv  Detail & Related papers  (2025-02-03T20:57:17Z)
• 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.