SWE-bench Lite

'SWE-bench Lite' is a dataset/benchmark used to evaluate the performance of software engineering tools and techniques, specifically in the context of assessing the effectiveness of augmentation hooks in improving baseline performance metrics.

Papers using SWE-bench Lite (54)

Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration2024 · 7 citesSWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution2025 · 4 citesMeta-RAG on Large Codebases Using Code Summarization2025 · 1 citesUTBoost: Rigorous Evaluation of Coding Agents on SWE-Bench2025 · 1 citesSWE-bench Goes Live!2025 · 1 citesFunction-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models2026Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills2026Triage: Routing Software Engineering Tasks to Cost-Effective LLM Tiers via Code Quality Signals2026AgentForge: Execution-Grounded Multi-Agent LLM Framework for Autonomous Software Engineering2026Spec Kit Agents: Context-Grounded Agentic Workflows2026RepoRepair: Leveraging Code Documentation for Repository-Level Automated Program Repair2026SWE-Adept: An LLM-Based Agentic Framework for Deep Codebase Analysis and Structured Issue Resolution2026CodeScout: An Effective Recipe for Reinforcement Learning of Code Search Agents2026Monte Carlo Tree Search for Execution-Guided Program Repair with Large Language Models2026What's in a Benchmark? The Case of SWE-Bench in Automated Program Repair2026Pull Requests as a Training Signal for Repo-Level Code Editing2026SWE Context Bench: A Benchmark for Context Learning in Coding2026Debug2Fix: Can Interactive Debugging Help Coding Agents Fix More Bugs?2026RGFL: Reasoning Guided Fault Localization for Automated Program Repair Using Large Language Models2026From Historical Patches to Repair Plans: Outcome-Conditioned Reasoning for Repository-Level Program Repair2026BOAD: Discovering Hierarchical Software Engineering Agents via Bandit Optimization2025DPO-F+: Aligning Code Repair Feedback with Developers' Preferences2025InfCode: Adversarial Iterative Refinement of Tests and Patches for Reliable Software Issue Resolution2025LLM Assisted Coding with Metamorphic Specification Mutation Agent2025Improving Code Localization with Repository Memory2025REFINE: Enhancing Program Repair Agents through Context-Aware Patch Refinement2025SIADAFIX: issue description response for adaptive program repair2025Huxley-G\"odel Machine: Human-Level Coding Agent Development by an Approximation of the Optimal Self-Improving Machine2025CoreThink: A Symbolic Reasoning Layer to reason over Long Horizon Tasks with LLMs2025Towards Explorative IRBL: Combining Semantic Retrieval with LLM-driven Iterative Code Exploration2025Kodezi Chronos: A Debugging-First Language Model for Repository-Scale Code Understanding2025Repeton: Structured Bug Repair with ReAct-Guided Patch-and-Test Cycles2025MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution2025SemAgent: A Semantics Aware Program Repair Agent2025PAGENT: Learning to Patch Software Engineering Agents2025Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks2025Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks2025SweRank: Software Issue Localization with Code Ranking2025SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs2025SEAlign: Alignment Training for Software Engineering Agent2025Enhancing repository-level software repair via repository-aware knowledge graphs2025DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal2025OrcaLoca: An LLM Agent Framework for Software Issue Localization2025Bridging Bug Localization and Issue Fixing: A Hierarchical Localization Framework Leveraging Large Language Models2025SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning2025AutoCodeRover: Autonomous Program Improvement2024 · 101 citesAgentless: Demystifying LLM-based Software Engineering Agents2024 · 16 citesSWE-Bench+: Enhanced Coding Benchmark for LLMs2024 · 5 citesTraining Software Engineering Agents and Verifiers with SWE-Gym2024 · 1 citesDiversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents2024 · 1 citesHyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale2024 · 1 citesMASAI: Modular Architecture for Software-engineering AI Agents2024SpecRover: Code Intent Extraction via LLMs2024SuperCoder2.0: Technical Report on Exploring the feasibility of LLMs as Autonomous Programmer2024