{"total":77,"rows":[{"id":"2509.16941","title":"SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?","created":"2025-09-21","cited_by_count":279,"area":null},{"id":"2411.07763","title":"Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows","created":"2024-11-12","cited_by_count":232,"area":null},{"id":"2504.02605","title":"Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving","created":"2025-04-03","cited_by_count":171,"area":null},{"id":"2406.01304","title":"CodeR: Issue Resolving with Multi-Agent and Task Graphs","created":"2024-06-03","cited_by_count":91,"area":null},{"id":"2408.03910","title":"CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases","created":"2024-08-07","cited_by_count":65,"area":null},{"id":"2408.05534","title":"Can LLMs Replace Manual Annotation of Software Engineering Artifacts?","created":"2024-08-10","cited_by_count":42,"area":null},{"id":"2601.01426","title":"SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving","created":"2026-01-04","cited_by_count":31,"area":null},{"id":"2503.07701","title":"Automated Benchmark Generation for Repository-Level Coding Tasks","created":"2025-03-10","cited_by_count":29,"area":null},{"id":"2505.16901","title":"Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks","created":"2025-05-22","cited_by_count":27,"area":null},{"id":"2412.03578","title":"PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedback","created":"2024-11-18","cited_by_count":24,"area":null},{"id":"2503.22424","title":"Issue Localization via LLM-Driven Iterative Code Graph Searching","created":"2025-03-28","cited_by_count":22,"area":null},{"id":"2504.14757","title":"SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs","created":"2025-04-20","cited_by_count":22,"area":null},{"id":"2510.01003","title":"Improving Code Localization with Repository Memory","created":"2025-10-01","cited_by_count":20,"area":null},{"id":"2607.13988","title":"TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents","created":"2026-07-15","cited_by_count":16,"area":null},{"id":"2506.22419","title":"The Automated LLM Speedrunning Benchmark: Reproducing NanoGPT Improvements","created":"2025-06-27","cited_by_count":15,"area":null},{"id":"2605.12925","title":"AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation","created":"2026-05-13","cited_by_count":15,"area":null},{"id":"2601.20882","title":"DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle","created":"2026-01-27","cited_by_count":11,"area":null},{"id":"2408.03519","title":"RepoMasterEval: Evaluating Code Completion via Real-World Repositories","created":"2024-08-07","cited_by_count":10,"area":null},{"id":"2409.00921","title":"Statically Contextualizing Large Language Models with Typed Holes","created":"2024-09-02","cited_by_count":9,"area":null},{"id":"2409.18952","title":"RepairBench: Leaderboard of Frontier Models for Program Repair","created":"2024-09-27","cited_by_count":9,"area":null},{"id":"2408.12056","title":"Enhancing Automated Program Repair with Solution Design","created":"2024-08-22","cited_by_count":8,"area":null},{"id":"2606.12344","title":"Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks","created":"2026-06-10","cited_by_count":8,"area":null},{"id":"2408.05941","title":"Multimodal Large Language Models for Phishing Webpage Detection and Identification","created":"2024-08-12","cited_by_count":7,"area":null},{"id":"2409.19894","title":"TransAgent: Enhancing LLM-Based Code Translation via Fine-Grained Execution Alignment","created":"2024-09-30","cited_by_count":7,"area":null},{"id":"2504.18050","title":"Validating Network Protocol Parsers with Traceable RFC Document Interpretation","created":"2025-04-25","cited_by_count":7,"area":null},{"id":"2506.10954","title":"SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks","created":"2025-06-12","cited_by_count":7,"area":null},{"id":"2511.16858","title":"Investigating Test Overfitting on SWE-bench","created":"2025-11-20","cited_by_count":6,"area":null},{"id":"2410.16655","title":"Memory-Efficient Large Language Models for Program Repair with Semantic-Guided Patch Generation","created":"2024-10-22","cited_by_count":5,"area":null},{"id":"2502.00519","title":"CoDocBench: A Dataset for Code-Documentation Alignment in Software Maintenance","created":"2025-02-01","cited_by_count":5,"area":null},{"id":"2504.13515","title":"Large Language Models for Validating Network Protocol Parsers","created":"2025-04-18","cited_by_count":5,"area":null},{"id":"2604.06742","title":"Evaluating LLM-Based 0-to-1 Software Generation in End-to-End CLI Tool Scenarios","created":"2026-04-08","cited_by_count":5,"area":null},{"id":"2508.02611","title":"Meta-RAG on Large Codebases Using Code Summarization","created":"2025-08-04","cited_by_count":4,"area":null},{"id":"2509.16187","title":"MatchFixAgent: Language-Agnostic Autonomous Repository-Level Code Translation Validation and Repair","created":"2025-09-19","cited_by_count":4,"area":null},{"id":"2509.25242","title":"A Benchmark for Localizing Code and Non-Code Issues in Software Projects","created":"2025-09-26","cited_by_count":4,"area":null},{"id":"2412.18750","title":"Order Matters! An Empirical Study on Large Language Models' Input Order Bias in Software Fault Localization","created":"2024-12-25","cited_by_count":3,"area":null},{"id":"2509.24091","title":"PerfBench: Can Agents Resolve Real-World Performance Bugs?","created":"2025-09-28","cited_by_count":3,"area":null},{"id":"2511.16005","title":"InfCode-C++: Intent-Guided Semantic Retrieval and AST-Structured Search for C++ Issue Resolution","created":"2025-11-20","cited_by_count":3,"area":null},{"id":"2605.04532","title":"Accountable Agents in Software Engineering: An Analysis of Terms of Service and a Research Roadmap","created":"2026-05-06","cited_by_count":3,"area":null},{"id":"2606.30963","title":"Loc2Repair: A Framework for Evaluating the Impact of File-Level Issue Localization in Repo-Level LLM Repair","created":"2026-06-29","cited_by_count":3,"area":null},{"id":"2607.19843","title":"Beyond Fail-to-Pass: Iterative Hardening of Co-Generated Bug Reproduction Tests and Fixes","created":"2026-07-22","cited_by_count":3,"area":null},{"id":"2408.03827","title":"Automated Code Fix Suggestions for Accessibility Issues in Mobile Apps","created":"2024-08-07","cited_by_count":2,"area":null},{"id":"2501.12339","title":"Treefix: Enabling Execution with a Tree of Prefixes","created":"2025-01-21","cited_by_count":2,"area":null},{"id":"2505.19887","title":"Deconstructing Obfuscation: A four-dimensional framework for evaluating Large Language Models assembly code deobfuscation capabilities","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2509.24148","title":"TENET: One Step Toward Test-Driven Development for Repository-Level Code Generation","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2603.00058","title":"PaperRepro: Automated Computational Reproducibility Assessment for Social Science Papers","created":"2026-02-10","cited_by_count":2,"area":null},{"id":"2603.26458","title":"Can AI Models Direct Each Other? Organizational Structure as a Probe into Training Limitations","created":"2026-03-27","cited_by_count":2,"area":null},{"id":"2609.04075","title":"PatchBench: Evaluating AI Agents for Vulnerability Patching","created":"2026-09-03","cited_by_count":2,"area":null},{"id":"2503.09020","title":"Enhancing the Non-Functional Quality Compliance of LLM-Generated Code through Quality-Aware Preference Learning","created":"2025-03-12","cited_by_count":1,"area":null},{"id":"2509.17314","title":"Clotho: Measuring Task-Specific Pre-Generation Test Adequacy for LLM Inputs","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2510.13561","title":"OpenDerisk: An Industrial Framework for AI-Driven SRE, with Design, Implementation, and Case Studies","created":"2025-10-15","cited_by_count":1,"area":null},{"id":"2510.17163","title":"TREAT: A Code LLMs Trustworthiness / Reliability Evaluation and Testing Framework","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2602.07457","title":"Pull Requests as a Training Signal for Repo-Level Code Editing","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2603.11356","title":"Resolving Java Code Repository Issues with iSWE Agent","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2605.17561","title":"Automated Root-Cause Subclassification and No-Code Fix Generation for Invalid Bug Reports","created":"2026-05-17","cited_by_count":1,"area":null},{"id":"2606.13733","title":"How Task Structure Limits Multi-Agent Success: An Information-Theoretic Analysis","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2607.05842","title":"Beyond Refusal: A Same-Lineage Study of Aligned and Abliterated LLMs for Vulnerability Analysis","created":"2026-07-07","cited_by_count":1,"area":null},{"id":"2609.21293","title":"GameASG-Bench: Benchmarking Autonomous Software Generation for Game Development","created":"2026-09-18","cited_by_count":1,"area":null},{"id":"2507.12482","title":"Kodezi Chronos: A Debugging-First Language Model for Repository-Scale Code Understanding","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2508.16071","title":"From Benchmark Data To Applicable Program Repair: An Experience Report","created":"2025-08-22","cited_by_count":0,"area":null},{"id":"2511.14002","title":"FlakyGuard: Automatically Fixing Flaky Tests at Industry Scale","created":"2025-11-18","cited_by_count":0,"area":null},{"id":"2512.08492","title":"Autonomous Issue Resolver: Towards Zero-Touch Code Maintenance","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2601.18119","title":"Beyond Text-to-SQL: Can LLMs Really Debug Enterprise ETL SQL?","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2603.24946","title":"MobileDev-Bench: A Benchmark for Issue Resolution in Mobile Application Development","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2604.12108","title":"LLM-Based Automated Diagnosis Of Integration Test Failures At Google","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2605.04624","title":"AuditRepairBench: A Paired-Execution Trace Corpus for Evaluator-Channel Ranking Instability in Agent Repair","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.05949","title":"MAS-Algorithm: A Workflow for Solving Algorithmic Programming Problems with a Multi-Agent System","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2606.02798","title":"BehaviorBench: Modeling Real-World User Decisions from Behavioral Traces","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.26490","title":"An Empirical Study of LLM-Generated Specifications for VeriFast","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.02057","title":"Prompt Coverage Adequacy","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2608.14574","title":"From Reactive to Autonomous: Evolution of AI Operations in Cloud Network Infrastructure","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2608.21964","title":"Repo2Skill-Evo: Repository Skills Go Stale in Silence","created":"2026-08-22","cited_by_count":0,"area":null},{"id":"2609.10397","title":"Retrofitting Code Using LLMs to Support Exceptional Behavior","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.20130","title":"AdaRepair-Mem: Adaptive Experience Orchestration for Repository-Level Program Repair","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.26480","title":"FeatLens: Feature-Guided Dynamic Code Graph Construction and Retrieval for Repository-Level Code Generation","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.37216","title":"CRJudgeBench: Can AI Detect Plausible but Invalid Code Reviews?","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.12343","title":"Reasoning-Informed Visual Editing","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.20245","title":"P2Patch: Exploit-Guided Vulnerability Repair","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}