{"total":22,"rows":[{"id":"2507.23361","title":"SWE-Exp: Experience-Driven Software Issue Resolution","created":"2025-07-31","cited_by_count":65,"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":"2503.22424","title":"Issue Localization via LLM-Driven Iterative Code Graph Searching","created":"2025-03-28","cited_by_count":22,"area":null},{"id":"2503.11917","title":"A Framework for Evaluating Emerging Cyberattack Capabilities of AI","created":"2025-03-14","cited_by_count":16,"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":"2511.16858","title":"Investigating Test Overfitting on SWE-bench","created":"2025-11-20","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":"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":"2509.26161","title":"90% Faster, 100% Code-Free: MLLM-Driven Zero-Code 3D Game Development","created":"2025-09-30","cited_by_count":4,"area":null},{"id":"2505.24715","title":"CoRet: Improved Retriever for Code Editing","created":"2025-05-30","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":"2508.13257","title":"ViTAD: Timing Violation-Aware Debugging of RTL Code using Large Language Models","created":"2025-08-18","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":"2608.12004","title":"RealisticTritonBench: A Benchmark for Triton-Kernel Generation in Real-World AI Frameworks","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2506.13182","title":"From Empirical Evaluation to Context-Aware Enhancement: Repairing Regression Errors with LLMs","created":"2025-06-16","cited_by_count":1,"area":null},{"id":"2603.27333","title":"ComBench: A Repo-level Real-world Benchmark for Compilation Error Repair","created":"2026-03-28","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":"2604.12108","title":"LLM-Based Automated Diagnosis Of Integration Test Failures At Google","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2607.00700","title":"LLVM-Bench: Benchmarking and Advancing Large Language Models for LLVM Compiler Issue Resolution","created":"2026-07-01","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":"2610.17184","title":"DuoDiscover: Scaling Autonomous Discovery Beyond the Evaluation Bottleneck","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}