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 41–50 of 132 papers

TitleStatusHype
Automated C/C++ Program Repair for High-Level Synthesis via Large Language Models—0
Agentless: Demystifying LLM-based Software Engineering AgentsCode7
NARRepair: Non-Autoregressive Code Generation Model for Automatic Program Repair—0
SemCoder: Training Code Language Models with Comprehensive Semantics ReasoningCode1
Benchmarking Educational Program RepairCode0
Automated Program Repair: Emerging trends pose and expose problems for benchmarks—0
Automatic Programming: Large Language Models and Beyond—0
NExT: Teaching Large Language Models to Reason about Code Execution—0
Aligning the Objective of LLM-based Program RepairCode1
AutoCodeRover: Autonomous Program ImprovementCode7
Show:102550
← PrevPage 5 of 14Next →
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