SOTAVerified

Program Repair

Task of teaching ML models to modify an existing program to fix a bug in a given code.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 132 papers

TitleStatusHype
AutoCodeRover: Autonomous Program ImprovementCode7
Agentless: Demystifying LLM-based Software Engineering AgentsCode7
HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at ScaleCode3
RepairAgent: An Autonomous, LLM-Based Agent for Program RepairCode2
From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical DebuggingCode2
RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program RepairCode1
RepairBench: Leaderboard of Frontier Models for Program RepairCode1
SemCoder: Training Code Language Models with Comprehensive Semantics ReasoningCode1
Integrating Various Software Artifacts for Better LLM-based Bug Localization and Program RepairCode1
Graph-based, Self-Supervised Program Repair from Diagnostic FeedbackCode1
Planning-Driven Programming: A Large Language Model Programming WorkflowCode1
KNOD: Domain Knowledge Distilled Tree Decoder for Automated Program RepairCode1
CURE: Code-Aware Neural Machine Translation for Automatic Program RepairCode1
A Syntax-Guided Edit Decoder for Neural Program RepairCode1
Aligning the Objective of LLM-based Program RepairCode1
Break-It-Fix-It: Unsupervised Learning for Program RepairCode1
Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program RepairCode1
CoSIL: Software Issue Localization via LLM-Driven Code Repository Graph SearchingCode1
Enhancing Genetic Improvement Mutations Using Large Language ModelsCode1
Global Relational Models of Source CodeCode1
How Effective Are Neural Networks for Fixing Security VulnerabilitiesCode1
Neural Program Repair by Jointly Learning to Localize and RepairCode1
CoCoNuT: Combining Context-Aware Neural Translation Models using Ensemble for Program RepairCode1
o3-mini vs DeepSeek-R1: Which One is Safer?Code1
TFix: Learning to Fix Coding Errors with a Text-to-Text TransformerCode1
Show:102550
← PrevPage 1 of 6Next →
All datasetsDeepFixGitHub-PythonHumanEvalPackTFix's Code Patches Data

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DrRepair + BIFIAverage Success Rate71.7—Unverified
2DrRepairAverage Success Rate68.2—Unverified
3SampleFixAverage Success Rate45.3—Unverified
4RLAssistAverage Success Rate26.6—Unverified
#ModelMetricClaimedVerifiedStatus
1Transformer + BIFIAccuracy (%)90.5—Unverified
2TransformerAccuracy (%)62—Unverified
#ModelMetricClaimedVerifiedStatus
1MGDebugger (DeepSeek-Coder-V2-Lite)Pass@197.6—Unverified
#ModelMetricClaimedVerifiedStatus
1TFixError Removal678—Unverified