SWE-bench Lite
Emerging58papers using it
2024first seen
Papers using SWE-bench Lite (58)
- Alibaba LingmaAgent: Improving Automated Issue Resolution via
Comprehensive Repository ExplorationSWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub
Issue ResolutionUTBoost: Rigorous Evaluation of Coding Agents on SWE-BenchSWE-bench Goes Live!Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent SkillsTriage: Routing Software Engineering Tasks to Cost-Effective LLM Tiers via Code Quality SignalsAgentForge: Execution-Grounded Multi-Agent LLM Framework for Autonomous Software EngineeringRepoRepair: Leveraging Code Documentation for Repository-Level Automated Program RepairSWE-Adept: An LLM-Based Agentic Framework for Deep Codebase Analysis and Structured Issue ResolutionCodeScout: An Effective Recipe for Reinforcement Learning of Code Search AgentsMonte Carlo Tree Search for Execution-Guided Program Repair with Large Language ModelsWhat's in a Benchmark? The Case of SWE-Bench in Automated Program RepairPull Requests as a Training Signal for Repo-Level Code EditingSWE Context Bench: A Benchmark for Context Learning in CodingDebug2Fix: Can Interactive Debugging Help Coding Agents Fix More Bugs?RGFL: Reasoning Guided Fault Localization for Automated Program Repair Using Large Language ModelsFrom Historical Patches to Repair Plans: Outcome-Conditioned Reasoning for Repository-Level Program RepairBOAD: Discovering Hierarchical Software Engineering Agents via Bandit OptimizationDPO-F+: Aligning Code Repair Feedback with Developers' PreferencesInfCode: Adversarial Iterative Refinement of Tests and Patches for Reliable Software Issue ResolutionLLM Assisted Coding with Metamorphic Specification Mutation AgentImproving Code Localization with Repository MemoryREFINE: Enhancing Program Repair Agents through Context-Aware Patch RefinementSIADAFIX: issue description response for adaptive program repairHuxley-G\"odel Machine: Human-Level Coding Agent Development by an Approximation of the Optimal Self-Improving MachineCoreThink: A Symbolic Reasoning Layer to reason over Long Horizon Tasks with LLMsTowards Explorative IRBL: Combining Semantic Retrieval with LLM-driven Iterative Code ExplorationMeta-RAG on Large Codebases Using Code SummarizationKodezi Chronos: A Debugging-First Language Model for Repository-Scale Code UnderstandingRepeton: Structured Bug Repair with ReAct-Guided Patch-and-Test CyclesMCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue ResolutionSemAgent: A Semantics Aware Program Repair AgentPAGENT: Learning to Patch Software Engineering AgentsCode Graph Model (CGM): A Graph-Integrated Large Language Model for
Repository-Level Software Engineering TasksCode Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering TasksSweRank: Software Issue Localization with Code RankingSWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World BugsSEAlign: Alignment Training for Software Engineering AgentEnhancing repository-level software repair via repository-aware knowledge graphsDARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by
Adaptive Tree TraversalOrcaLoca: An LLM Agent Framework for Software Issue LocalizationBridging Bug Localization and Issue Fixing: A Hierarchical Localization
Framework Leveraging Large Language ModelsSoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-TuningAutoCodeRover: Autonomous Program ImprovementAgentless: Demystifying LLM-based Software Engineering AgentsSWE-Bench+: Enhanced Coding Benchmark for LLMsTraining Software Engineering Agents and Verifiers with SWE-GymDiversity Empowers Intelligence: Integrating Expertise of Software
Engineering AgentsHyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks
at ScaleMASAI: Modular Architecture for Software-engineering AI AgentsSpecRover: Code Intent Extraction via LLMsSuperCoder2.0: Technical Report on Exploring the feasibility of LLMs as
Autonomous ProgrammerAgentless: Demystifying LLM-based Software Engineering AgentsTraining Software Engineering Agents and Verifiers with SWE-GymSWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub
Issue ResolutionSoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-TuningSweRank: Software Issue Localization with Code RankingSpec Kit Agents: Context-Grounded Agentic Workflows