{"total":105,"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":"2410.14684","title":"RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph","created":"2024-10-03","cited_by_count":91,"area":null},{"id":"2504.17192","title":"Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning","created":"2025-04-24","cited_by_count":70,"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":"2507.23361","title":"SWE-Exp: Experience-Driven Software Issue Resolution","created":"2025-07-31","cited_by_count":65,"area":null},{"id":"2410.24198","title":"SelfCodeAlign: Self-Alignment for Code Generation","created":"2024-10-31","cited_by_count":62,"area":null},{"id":"2412.01007","title":"CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking","created":"2024-12-01","cited_by_count":37,"area":null},{"id":"2412.02883","title":"TDD-Bench Verified: Can LLMs Generate Tests for Issues Before They Get Resolved?","created":"2024-12-03","cited_by_count":34,"area":null},{"id":"2410.06107","title":"Towards AI-Native Software Engineering (SE 3.0): A Vision and a Challenge Roadmap","created":"2024-10-08","cited_by_count":30,"area":null},{"id":"2510.19898","title":"BugPilot: Complex Bug Generation for Efficient Learning of SWE Skills","created":"2025-10-22","cited_by_count":30,"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":"2502.05368","title":"Otter: Generating Tests from Issues to Validate SWE Patches","created":"2025-02-07","cited_by_count":25,"area":null},{"id":"2509.06917","title":"Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents","created":"2025-09-08","cited_by_count":23,"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":"2504.05408","title":"Frontier AI's Impact on the Cybersecurity Landscape","created":"2025-04-07","cited_by_count":21,"area":null},{"id":"2512.14012","title":"Professional Software Developers Don't Vibe, They Control: AI Agent Use for Coding in 2025","created":"2025-12-16","cited_by_count":20,"area":null},{"id":"2412.14234","title":"Syzygy: Dual Code-Test C to (safe) Rust Translation using LLMs and Dynamic Analysis","created":"2024-12-18","cited_by_count":16,"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":"2605.12925","title":"AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation","created":"2026-05-13","cited_by_count":15,"area":null},{"id":"2603.13023","title":"daVinci-Env: Open SWE Environment Synthesis at Scale","created":"2026-03-13","cited_by_count":14,"area":null},{"id":"2411.13323","title":"Are Large Language Models Memorizing Bug Benchmarks?","created":"2024-11-20","cited_by_count":12,"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":"2411.13941","title":"LLMs as Continuous Learners: Improving the Reproduction of Defective Code in Software Issues","created":"2024-11-21","cited_by_count":10,"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":"2412.17315","title":"CodeV: Issue Resolving with Visual Data","created":"2024-12-23","cited_by_count":9,"area":null},{"id":"2503.04735","title":"How Personality Traits Shape LLM Risk-Taking Behaviour","created":"2025-02-03","cited_by_count":9,"area":null},{"id":"2511.05931","title":"Self-Abstraction from Grounded Experience for Plan-Guided Policy Refinement","created":"2025-11-08","cited_by_count":9,"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":"2502.15441","title":"On the Effectiveness of Large Language Models in Writing Alloy Formulas","created":"2025-02-21","cited_by_count":7,"area":null},{"id":"2505.10887","title":"InfantAgent-Next: A Multimodal Generalist Agent for Automated Computer Interaction","created":"2025-05-16","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":"2511.16004","title":"InfCode: Adversarial Iterative Refinement of Tests and Patches for Reliable Software Issue Resolution","created":"2025-11-20","cited_by_count":7,"area":null},{"id":"2505.11480","title":"SuperCoder: Assembly Program Superoptimization with Large Language Models","created":"2025-05-16","cited_by_count":6,"area":null},{"id":"2509.22237","title":"FeatBench: Towards More Realistic Evaluation of Feature-level Code Generation","created":"2025-09-26","cited_by_count":6,"area":null},{"id":"2601.13384","title":"From Completion to Editing: Unlocking Context-Aware Code Infilling via Search-and-Replace Instruction Tuning","created":"2026-01-19","cited_by_count":6,"area":null},{"id":"2603.01048","title":"RepoRepair: Leveraging Code Documentation for Repository-Level Automated Program Repair","created":"2026-03-01","cited_by_count":6,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2606.15932","title":"Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence","created":"2026-06-14","cited_by_count":6,"area":null},{"id":"2505.23932","title":"SwingArena: Competitive Programming Arena for Long-context GitHub Issue Solving","created":"2025-05-29","cited_by_count":5,"area":null},{"id":"2510.20211","title":"Automated Cloud Infrastructure-as-Code Reconciliation with AI Agents","created":"2025-10-23","cited_by_count":5,"area":null},{"id":"2604.02648","title":"GBQA: A Game Benchmark for Evaluating LLMs as Quality Assurance Engineers","created":"2026-04-03","cited_by_count":5,"area":null},{"id":"2605.22148","title":"Ratchet: How Reliable Must an LLM Judge Be to Retire a Skill?","created":"2026-05-21","cited_by_count":5,"area":null},{"id":"2412.03905","title":"Integrating Various Software Artifacts for Better LLM-based Bug Localization and Program Repair","created":"2024-12-05","cited_by_count":4,"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":"2509.25242","title":"A Benchmark for Localizing Code and Non-Code Issues in Software Projects","created":"2025-09-26","cited_by_count":4,"area":null},{"id":"2601.13713","title":"SWE-Tester: Training Open-Source LLMs for Issue Reproduction in Real-World Repositories","created":"2026-01-20","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":"2502.07128","title":"Cardiverse: Harnessing LLMs for Novel Card Game Prototyping","created":"2025-02-10","cited_by_count":3,"area":null},{"id":"2502.13966","title":"Where's the Bug? Attention Probing for Scalable Fault Localization","created":"2025-02-19","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":"2604.05481","title":"On the Role of Fault Localization Context for LLM-Based Program Repair","created":"2026-04-07","cited_by_count":3,"area":null},{"id":"2605.26177","title":"RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations","created":"2026-05-25","cited_by_count":3,"area":null},{"id":"2606.00750","title":"I-WebGenBench : Evaluating Interactivity in LLM-Generated Scientific Web Applications","created":"2026-05-30","cited_by_count":3,"area":null},{"id":"2608.11772","title":"Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction","created":"2026-08-12","cited_by_count":3,"area":null},{"id":"2501.12617","title":"Deep Learning-Based Identification of Inconsistent Method Names: How Far Are We?","created":"2025-01-22","cited_by_count":2,"area":null},{"id":"2510.10066","title":"OBsmith: LLM-Powered JavaScript Obfuscator Testing","created":"2025-10-11","cited_by_count":2,"area":null},{"id":"2603.05026","title":"RepoLaunch: Automating Build and Management of Code Repositories across Languages and Platforms","created":"2026-03-05","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":"2603.27296","title":"A Multi-agent AI System for Deep Learning Model Migration from TensorFlow to JAX","created":"2026-03-28","cited_by_count":2,"area":null},{"id":"2604.05963","title":"QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization","created":"2026-04-07","cited_by_count":2,"area":null},{"id":"2605.15222","title":"PerfCodeBench: Benchmarking LLMs for System-Level High-Performance Code Optimization","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2606.17454","title":"Dissecting model behavior through agent trajectories","created":"2026-06-16","cited_by_count":2,"area":null},{"id":"2607.26117","title":"Try Again, Don't Look Back: Blind Resampling Outperforms Self-Repair in Small Code Models","created":"2026-07-28","cited_by_count":2,"area":null},{"id":"2610.07557","title":"CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers?","created":"2026-10-06","cited_by_count":2,"area":null},{"id":"2410.16392","title":"Scaffolded Language Models with Language Supervision for Mixed-Autonomy: A Survey","created":"2024-10-21","cited_by_count":1,"area":null},{"id":"2502.08756","title":"From PowerPoint UI Sketches to Web-Based Applications: Pattern-Driven Code Generation for GIS Dashboard Development Using Knowledge-Augmented LLMs, Context-Aware Visual Prompting, and the React Framework","created":"2025-02-12","cited_by_count":1,"area":null},{"id":"2508.03487","title":"BitsAI-Fix: LLM-Driven Approach for Automated Lint Error Resolution in Practice","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2508.13948","title":"Prompt Orchestration Markup Language","created":"2025-08-19","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":"2510.22210","title":"LSPRAG: LSP-Guided RAG for Language-Agnostic Real-Time Unit Test Generation","created":"2025-10-25","cited_by_count":1,"area":null},{"id":"2512.01396","title":"BackportBench: A Multilingual Benchmark for Automated Backporting of Patches","created":"2025-12-01","cited_by_count":1,"area":null},{"id":"2601.10496","title":"Model See, Model Do? Exposure-Aware Evaluation of Bug-vs-Fix Preference in Code LLMs","created":"2026-01-15","cited_by_count":1,"area":null},{"id":"2602.01187","title":"Autoregressive, Yet Revisable: In Decoding Revision for Secure Code Generation","created":"2026-02-01","cited_by_count":1,"area":null},{"id":"2604.16021","title":"Neurosymbolic Repo-level Code Localization","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2604.19827","title":"More Is Different: Toward a Theory of Emergence in AI-Native Software Ecosystems","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2605.00382","title":"Social Bias in LLM-Generated Code: Benchmark and Mitigation","created":"2026-05-01","cited_by_count":1,"area":null},{"id":"2606.09956","title":"Multi-task LLMs for Bug Classification: Efficient Inference with Auxiliary Decoding Heads","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2607.04537","title":"Obey, Diverge, Collapse: Blind Obedience to Incorrect Instructions Drives Code LLMs to Irrecoverable Code Semantic Collapse","created":"2026-07-05","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":"2502.15872","title":"MutaGReP: Execution-Free Repository-Grounded Plan Search for Code-Use","created":"2025-02-21","cited_by_count":0,"area":null},{"id":"2508.06017","title":"Position: Intelligent Coding Systems Should Write Programs with Justifications","created":"2025-08-08","cited_by_count":0,"area":null},{"id":"2510.01453","title":"The Command Line GUIde: Graphical Interfaces from Man Pages via AI","created":"2025-10-01","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":"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":"2601.19568","title":"Learning Adaptive Parallel Execution for Efficient Code Localization","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2601.22461","title":"Toward Non-Expert Customized Congestion Control: Large Language Model-Assisted CCA Code Generation with eBPF Deployment","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.13921","title":"GREPO: A Benchmark for Graph Neural Networks on Repository-Level Bug Localization","created":"2026-02-14","cited_by_count":0,"area":null},{"id":"2603.22017","title":"Domain Adapted Large Language Models for Additive Manufacturing","created":"2026-03-23","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":"2605.01392","title":"Using LLMs in Software Design: An Empirical Study of GitHub and A Practitioner Survey","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2607.27283","title":"Benchmarking the Residual: What Long-Horizon Evaluations Add Beyond Matched Short-Task Performance","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2607.28645","title":"Looks Right, Works Right: A Project-Level Benchmark for Multi-Screen Mobile App Generation","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2609.00023","title":"ES-AHD: An Evolution Strategy Framework for Automatic Heuristic Design","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.14913","title":"Externalizing Requirement-to-Repair Artifacts as Observable Traces for LLM-Based Program Repair","created":"2026-09-14","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}],"next_cursor":"100"}