RepairAgent autonomously repairs 164 bugs on Defects4J including 39 not fixed by prior techniques by treating an LLM as an agent that invokes tools via a finite state machine and dynamic prompts.
Tbar: revisiting template-based automated program repair,
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 1
dataset 1
citation-polarity summary
representative citing papers
VulKey reaches 31.5% repair accuracy on real C/C++ vulnerabilities by matching hierarchical expert patterns to guide LLM patch generation, beating prior baselines by 7.6%.
CodeCureAgent achieves 96.8% plausible fixes and 86.3% correct fixes for 1,000 SonarQube warnings across 106 Java projects using an agentic LLM framework.
A black-box LLM approach for fault localization in system-level test code that estimates execution traces from failure logs to rank potential faults with reduced inference cost.
IntentTester migrates tests across libraries using TDL abstraction and multi-agent LLM synthesis, achieving 85% correctness and 74% effectiveness versus 51% and 43% for baselines on nine projects in JSON, HTML, and Time domains.
SpecTune improves LLM-based automated program repair by deriving localized postconditions at execution checkpoints and using alpha and beta signals to produce precise fault-localization and patch-generation guidance.
ContentFuzz rewrites posts with LLM guidance from stance model confidence to flip machine labels without altering human intent, tested across four models and three datasets in two languages.
PrevaRank ranks plausible patches from APR tools using similarity to historic fix features, improving correct fix placement in top ranks on Defects4J bugs.
RAVEN combines agentic RAG, iterative repair, and a cross-file Curator Agent to achieve 83.13% repair success on diverse real-world CVEs using local open-source LLMs.
Proposes the CBDT framework as a minimum viable digital twin for CI builds to enable real-time monitoring, ML modeling, and prescriptive optimization of build duration, failures, and flakiness.
A literature survey of 164 papers on software fairness reveals gaps in requirements engineering, intersectional measures, unstructured data, and white-box ML methods.
citing papers explorer
-
RepairAgent: An Autonomous, LLM-Based Agent for Program Repair
RepairAgent autonomously repairs 164 bugs on Defects4J including 39 not fixed by prior techniques by treating an LLM as an agent that invokes tools via a finite state machine and dynamic prompts.
-
VulKey: Automated Vulnerability Repair Guided by Domain-Specific Repair Patterns
VulKey reaches 31.5% repair accuracy on real C/C++ vulnerabilities by matching hierarchical expert patterns to guide LLM patch generation, beating prior baselines by 7.6%.
-
CodeCureAgent: Automatic Classification and Repair of Static Analysis Warnings
CodeCureAgent achieves 96.8% plausible fixes and 86.3% correct fixes for 1,000 SonarQube warnings across 106 Java projects using an agentic LLM framework.
-
Efficient Black-Box Fault Localization for System-Level Test Code Using Large Language Models
A black-box LLM approach for fault localization in system-level test code that estimates execution traces from failure logs to rank potential faults with reduced inference cost.
-
IntentTester: Intent-Driven Multi-agent Framework for Cross-Library Test Migration
IntentTester migrates tests across libraries using TDL abstraction and multi-agent LLM synthesis, achieving 85% correctness and 74% effectiveness versus 51% and 43% for baselines on nine projects in JSON, HTML, and Time domains.
-
Enhancing Program Repair with Specification Guidance and Intermediate Behavioral Signals
SpecTune improves LLM-based automated program repair by deriving localized postconditions at execution checkpoints and using alpha and beta signals to produce precise fault-localization and patch-generation guidance.
-
Content Fuzzing for Escaping Information Cocoons on Digital Social Media
ContentFuzz rewrites posts with LLM guidance from stance model confidence to flip machine labels without altering human intent, tested across four models and three datasets in two languages.
-
Ranking Plausible Patches by Historic Feature Frequencies
PrevaRank ranks plausible patches from APR tools using similarity to historic fix features, improving correct fix placement in top ranks on Defects4J bugs.
-
RAVEN: Agentic RAG for Automated Vulnerability Repair
RAVEN combines agentic RAG, iterative repair, and a cross-file Curator Agent to achieve 83.13% repair success on diverse real-world CVEs using local open-source LLMs.
-
Towards Build Optimization Using Digital Twins
Proposes the CBDT framework as a minimum viable digital twin for CI builds to enable real-time monitoring, ML modeling, and prescriptive optimization of build duration, failures, and flakiness.
-
Software Fairness: An Analysis and Survey
A literature survey of 164 papers on software fairness reveals gaps in requirements engineering, intersectional measures, unstructured data, and white-box ML methods.