SOTAVerified

Code Repair

Papers

Showing 110 of 39 papers

TitleStatusHype
AutoCoder: Enhancing Code Large Language Model with AIEV-InstructCode4
Agent KB: Leveraging Cross-Domain Experience for Agentic Problem SolvingCode3
OctoPack: Instruction Tuning Code Large Language ModelsCode3
SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code AgentsCode2
Guiding Language Models of Code with Global Context using MonitorsCode2
Fortran2CPP: Automating Fortran-to-C++ Translation using LLMs via Multi-Turn Dialogue and Dual-Agent IntegrationCode1
COAST: Enhancing the Code Debugging Ability of LLMs through Communicative Agent Based Data SynthesisCode1
INTERVENOR: Prompting the Coding Ability of Large Language Models with the Interactive Chain of RepairCode1
Learning Performance-Improving Code EditsCode1
Break-It-Fix-It: Unsupervised Learning for Program RepairCode1
Show:102550
← PrevPage 1 of 4Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1NSEditAccuracy (medium)13.87Unverified
2CodeBERTAccuracy (medium)5.2Unverified