{"total":47,"rows":[{"id":"2504.02605","title":"Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving","created":"2025-04-03","cited_by_count":171,"area":null},{"id":"2506.02548","title":"CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale","created":"2025-06-03","cited_by_count":78,"area":null},{"id":"2504.04030","title":"OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs","created":"2025-04-05","cited_by_count":60,"area":null},{"id":"2502.11844","title":"BaxBench: Can LLMs Generate Correct and Secure Backends?","created":"2025-02-17","cited_by_count":41,"area":null},{"id":"2504.09246","title":"Type-Constrained Code Generation with Language Models","created":"2025-04-12","cited_by_count":35,"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":"2507.10535","title":"CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks","created":"2025-07-14","cited_by_count":33,"area":null},{"id":"2607.08964","title":"Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading","created":"2026-07-09","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":"2502.05368","title":"Otter: Generating Tests from Issues to Validate SWE Patches","created":"2025-02-07","cited_by_count":25,"area":null},{"id":"2511.06090","title":"SWE-fficiency: Can Language Models Optimize Real-World Repositories on Real Workloads?","created":"2025-11-08","cited_by_count":21,"area":null},{"id":"2504.12110","title":"Towards LLM Agents for Earth Observation","created":"2025-04-16","cited_by_count":17,"area":null},{"id":"2508.10111","title":"Constrained Decoding of Diffusion LLMs with Context-Free Grammars","created":"2025-08-13","cited_by_count":14,"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":"2603.01203","title":"How Well Does Agent Development Reflect Real-World Work?","created":"2026-03-01","cited_by_count":10,"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":"2502.08806","title":"CLOVER: A Test Case Generation Benchmark with Coverage, Long-Context, and Verification","created":"2025-02-12","cited_by_count":8,"area":null},{"id":"2508.00408","title":"Benchmarking LLMs for Unit Test Generation from Real-World Functions","created":"2025-08-01","cited_by_count":8,"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":"2511.16858","title":"Investigating Test Overfitting on SWE-bench","created":"2025-11-20","cited_by_count":6,"area":null},{"id":"2602.10471","title":"TestExplora: Benchmarking LLMs for Proactive Bug Discovery via Repository-Level Test Generation","created":"2026-02-11","cited_by_count":5,"area":null},{"id":"2502.06556","title":"MultiFileTest: A Multi-File-Level LLM Unit Test Generation Benchmark and Impact of Error Fixing Mechanisms","created":"2025-02-10","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":"2510.08720","title":"How Many Code and Test Cases Are Enough? Evaluating Test Cases Generation from a Binary-Matrix Perspective","created":"2025-10-09","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":"2601.20886","title":"IDE-Bench: Evaluating Large Language Models as IDE Agents on Real-World Software Engineering Tasks","created":"2026-01-28","cited_by_count":4,"area":null},{"id":"2604.12268","title":"CodeSpecBench: Benchmarking LLMs for Executable Behavioral Specification Generation","created":"2026-04-14","cited_by_count":4,"area":null},{"id":"2602.06098","title":"A Theoretical Analysis of Test-Driven Code Generation","created":"2026-02-05","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":"2512.01396","title":"BackportBench: A Multilingual Benchmark for Automated Backporting of Patches","created":"2025-12-01","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":"2607.02469","title":"TestEvo-Bench: An Executable and Live Benchmark for Test and Code Co-Evolution","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.02854","title":"EvoOtter: Evolutionary Reproduction Test Generator","created":"2026-07-03","cited_by_count":1,"area":null},{"id":"2406.15676","title":"Inferring Pluggable Types with Machine Learning","created":"2024-06-21","cited_by_count":0,"area":null},{"id":"2511.10868","title":"Go-UT-Bench: A Fine-Tuning Dataset for LLM-Based Unit Test Generation in Go","created":"2025-11-14","cited_by_count":0,"area":null},{"id":"2601.18241","title":"TAM-Eval: Evaluating LLMs for Automated Unit Test Maintenance","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2601.21070","title":"Towards Comprehensive Benchmarking Infrastructure for LLMs In Software Engineering","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2602.13611","title":"From What to How: Bridging User Requirements with Software Development Using Large Language Models","created":"2026-02-14","cited_by_count":0,"area":null},{"id":"2604.14867","title":"Vibe-Coding: Feedback-Based Automated Verification with no Human Code Inspection, a Feasibility Study","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2604.17351","title":"SOCIA-EVO: Automated Simulator Construction via Dual-Anchored Bi-Level Optimization","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2605.15238","title":"Hydra: Efficient, Correct Code Generation via Checkpoint-and-Rollback Support","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.15815","title":"BootstrapAgent: Distilling Repository Setup into Reusable Agent Knowledge","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2607.05032","title":"Multi-Large Language Model Orchestrated Severity Assessment of Clinical Records (MOSAIC)","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2609.38606","title":"SecureVibe: Making Vibe Coding More Secure","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39086","title":"Trustworthy Runtime Error Healing in Real-World Repositories: A Benchmark and Guardrail","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.10242","title":"TestGRAD: Evolving Test Suites via Failure Pattern Momentum for SWE-Agent Ensemble","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}