Outcome-Conditioned Reasoning Distillation for Resolving Software Issues

• URL: http://arxiv.org/abs/2601.23257v1
• Date: Fri, 30 Jan 2026 18:25:39 GMT
• Title: Outcome-Conditioned Reasoning Distillation for Resolving Software Issues
• Abstract summary: 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.
• Score: 49.16055123488827
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Software issue resolution in large repositories is a long-range decision process: choices made during localization shape the space of viable edits, and missteps can compound into incorrect patches. Despite this, many LLM-based repair pipelines still operate in a reset-and-solve manner, producing fresh reasoning for every new issue instead of carrying forward what worked in past fixes. This is wasteful because repositories routinely contain earlier issues with overlapping structure, failure modes, or constraints, where prior repair experience could provide useful guidance. Existing approaches typically harvest this signal through forward-time trial procedures, such as repeated refinement or search, incurring high inference cost while still risking divergence from the eventual correct patch. We present an Outcome-Conditioned Reasoning Distillation(O-CRD) framework that uses resolved in-repository issues with verified patches as supervision. Starting from a historical fix, the method reconstructs a stage-wise repair trace backward from the verified outcome, then reuses the distilled guidance at inference time to steer file/function localization and patch synthesis, without fine-tuning or online search. 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, indicating that outcome-conditioned reuse of verified repairs can replace costly forward exploration for software issue resolution.

Related papers

• REVISE: Validity-Guided Recovery for Online Revisions in Agent Workflows [5.5444120195759785]
  textscRevise is validity-guided for fine-grained recovery in structured agent.<n>It stops invalid work, preserves validity-established progress beyond the earliest conflict, and recomputes only the affected region.<n>It reduces model calls by 40.6--56.0% relative to full restart and by 31.3--43.6% relative to suffix recomputation.
  arXiv  Detail & Related papers  (2026-09-01T03:22:18Z)
• 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)
• 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)
• PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agents [62.36339598951133]
  We present PhoenixRepair, a multi-agent framework that explores multiple candidate edit locations and generates better patches.<n>PhoenixRepair achieves the largest relative improvement of 7.8% over SWE-agent under DeepSeek-V3.1, and attains the highest resolved rate of 76.0% Pass@1 under MiniMax-M2.5.
  arXiv  Detail & Related papers  (2026-07-21T08:49:30Z)
• DepRepair: LLM-Based Source-Code Repair for Dependency Breaking Changes [26.444574129479463]
  DepRepair is a single-call LLM approach that grounds repair in structured upstream evidence through three components.<n>It attains the highest executable pass rate on each backbone, achieving 89.5% with GPT-5.5 and 82.1% with Claude Opus 4.6.
  arXiv  Detail & Related papers  (2026-07-20T13:58:13Z)
• 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)
• Beyond Fixed Tests: Repository-Level Issue Resolution as Coevolution of Code and Behavioral Constraints [17.818522356206977]
  Most large language model (LLM)-based repair systems treat behavioral constraints as fixed during repair.<n>We propose Agent-CoEvo, a coevolutionary multi-agent framework in which candidate code patches and test patches are jointly explored and refined.<n>Agent-CoEvo consistently outperforms state-of-the-art agent-based and agentless baselines in both repair success and test reproduction quality.
  arXiv  Detail & Related papers  (2026-04-06T10:26:46Z)
• RepoRepair: Leveraging Code Documentation for Repository-Level Automated Program Repair [30.23781155493087]
  We propose RepoRepair, a novel documentation-enhanced approach for repository-level fault localization and program repair.<n>Our core insight is to leverage LLMs to generate hierarchical code documentation (from functions to files) for code repositories.<n>RepoRepair first employs a text-based LLM to generate file/function-level code documentation for repositories, which serves as auxiliary knowledge to guide fault localization.
  arXiv  Detail & Related papers  (2026-03-01T11:06:24Z)
• Pull Requests as a Training Signal for Repo-Level Code Editing [49.82435173554125]
  Clean Pull Request (Clean-PR) is a mid-training paradigm that leverages real-world GitHub pull requests as a training signal for repository-level editing.<n>We introduce a scalable pipeline that converts noisy pull request diffs into Search/Replace edit blocks through reconstruction and validation.<n>On SWE-bench, our model significantly outperforms the instruction-tuned baseline, achieving absolute improvements of 13.6% on SWE-bench Lite and 12.3% on SWE-bench Verified.
  arXiv  Detail & Related papers  (2026-02-07T09:22:25Z)
• TraceCoder: A Trace-Driven Multi-Agent Framework for Automated Debugging of LLM-Generated Code [11.207330722400764]
  We present TraceCoder, a framework that emulates the observe-analyze-repair process of human experts.<n>The framework first instruments the code with diagnostic probes to capture fine-grained runtime traces.<n>It then conducts causal analysis on these traces to accurately identify the root cause of the failure.
  arXiv  Detail & Related papers  (2026-02-06T16:59:48Z)
• R3A: Reliable RTL Repair Framework with Multi-Agent Fault Localization and Stochastic Tree-of-Thoughts Patch Generation [3.5576449247822506]
  We propose R3A, an automatic program repair framework upon the basic model to improve reliability.<n>Experiments show R3A can fix 90.6% of bugs in the RTL-repair dataset within a given time limit.
  arXiv  Detail & Related papers  (2025-11-25T09:08:48Z)
• REFINE: Enhancing Program Repair Agents through Context-Aware Patch Refinement [12.995571513415905]
  Large Language Models (LLMs) have recently shown strong potential in automatic program repair (APR)<n>LLMs often struggle to produce correct fixes due to limited understanding of code context and over-reliance on incomplete test suites.<n>We propose a novel patch refinement framework, Refine, that systematically transforms Draft Patches into correct ones.
  arXiv  Detail & Related papers  (2025-10-04T00:34:32Z)
• 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)
• Repeton: Structured Bug Repair with ReAct-Guided Patch-and-Test Cycles [1.387448620257867]
  Large Language Models (LLMs) have shown strong capabilities in code generation and comprehension, yet their application to complex software engineering tasks often suffers from low precision and limited interpretability.<n>We present Repeton, a fully open-source framework that leverages LLMs for precise and automated code manipulation in real-world Git.
  arXiv  Detail & Related papers  (2025-06-09T19:36:40Z)
• LLMs as Continuous Learners: Improving the Reproduction of Defective Code in Software Issues [62.12404317786005]
  EvoCoder is a continuous learning framework for issue code reproduction. Our results show a 20% improvement in issue reproduction rates over existing SOTA methods.
  arXiv  Detail & Related papers  (2024-11-21T08:49:23Z)
• 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)
• Patch Space Exploration using Static Analysis Feedback [8.13782364161157]
  We show how to automatically repair memory safety issues, by leveraging static analysis to guide repair. Our proposed approach learns what a desirable patch is by inspecting how close a patch is to fixing the bug. We make repair scalable by creating classes of equivalent patches according to the effect they have on the symbolic heap, and then invoking the validation oracle only once per class of patch equivalence.
  arXiv  Detail & Related papers  (2023-08-01T05:22:10Z)
• RCOT: Detecting and Rectifying Factual Inconsistency in Reasoning by Reversing Chain-of-Thought [56.558892336235914]
  Reversing Chain-of-Thought (RCoT) is a novel method to improve large language models' reasoning abilities. RCoT automatically detects and rectifys factual inconsistency in generated solutions. We show that manually written fine-grained feedback can dramatically improve LLMs' reasoning abilities.
  arXiv  Detail & Related papers  (2023-05-19T08:02:52Z)

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.