{"total":37,"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":"2603.20633","title":"Seed1.8 Model Card: Towards Generalized Real-World Agency","created":"2026-03-21","cited_by_count":50,"area":null},{"id":"2606.07682","title":"SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?","created":"2026-06-05","cited_by_count":23,"area":null},{"id":"2608.05466","title":"Recursive Synthesis for Long-Horizon Terminal Tasks","created":"2026-08-05","cited_by_count":19,"area":null},{"id":"2506.18951","title":"SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications","created":"2025-06-23","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":"2507.09108","title":"SPICE: An Automated SWE-Bench Labeling Pipeline for Issue Clarity, Test Coverage, and Effort Estimation","created":"2025-07-12","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":"2507.11059","title":"SWE-MERA: A Dynamic Benchmark for Agenticly Evaluating Large Language Models on Software Engineering Tasks","created":"2025-07-15","cited_by_count":9,"area":null},{"id":"2603.13428","title":"SWE-Milestone: Evaluating AI Agents on Continuous Software Evolution","created":"2026-03-13","cited_by_count":8,"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":"2505.23932","title":"SwingArena: Competitive Programming Arena for Long-context GitHub Issue Solving","created":"2025-05-29","cited_by_count":5,"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":"2601.22859","title":"MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software Engineering","created":"2026-01-30","cited_by_count":4,"area":null},{"id":"2605.22175","title":"SWE-Mutation: Can LLMs Generate Reliable Test Suites in Software Engineering?","created":"2026-05-21","cited_by_count":4,"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":"2603.06739","title":"ResearchEnvBench: Benchmarking Agents on Environment Synthesis for Research Code Execution","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2604.16625","title":"AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation","created":"2026-04-17","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":"2606.15300","title":"CODA-BENCH: Can Code Agents Handle Data-Intensive Tasks?","created":"2026-06-13","cited_by_count":3,"area":null},{"id":"2607.19653","title":"PerfAgent: Profiler-Guided Iterative Refinement for Repository-Level Code Optimization","created":"2026-07-22","cited_by_count":3,"area":null},{"id":"2609.17930","title":"Locating Hidden Failures Makes Long-Horizon Agents More Reliable","created":"2026-09-15","cited_by_count":3,"area":null},{"id":"2604.20398","title":"WebGen-R1: Incentivizing Large Language Models to Generate Functional and Aesthetic Websites with Reinforcement Learning","created":"2026-04-22","cited_by_count":2,"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":"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":"2512.21010","title":"LLM Swiss Round: Aggregating Multi-Benchmark Performance via Competitive Swiss-System Dynamics","created":"2025-12-24","cited_by_count":0,"area":null},{"id":"2602.11674","title":"Benchmark Health Index: A Systematic Framework for Benchmarking the Benchmarks of LLMs","created":"2026-02-12","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":"2606.21869","title":"The Language-Energy Divide: Measuring Energy Costs of Multilingual LLM Inference","created":"2026-06-20","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":"2607.25873","title":"How Do LLMs Read Bug Reports? An Empirical Study of Attention in LLMs for Automated Program Repair","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.02685","title":"BulkPR-Bench: Benchmarking Queue-Level Governance of Interacting Pull Requests","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2609.32662","title":"AsynCodeBench: Benchmarking Collaboration of Asynchronous Multi-Agent Systems in Software Engineering","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.36675","title":"G\\\"odel Forest: Balancing Search Depth and Breadth for Data-Centric Recursive Self-Improvement","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.05099","title":"Small Agents with Semantic Search: Efficient Multilingual Code Localization","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.20038","title":"SWE-Nexus: Automated Composition of Software Engineering Tasks from Test Execution","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}