{"total":35,"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":"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":"2512.17419","title":"SWE-Bench++: A Framework for the Scalable Generation of Software Engineering Benchmarks from Open-Source Repositories","created":"2025-12-19","cited_by_count":28,"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":"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":"2506.01372","title":"AI Scientists Fail Without Strong Implementation Capability","created":"2025-06-02","cited_by_count":21,"area":null},{"id":"2602.02361","title":"SWE-Universe: Scale Real-World Verifiable Environments to Millions","created":"2026-02-02","cited_by_count":19,"area":null},{"id":"2505.08253","title":"Evaluating LLM Metrics Through Real-World Capabilities","created":"2025-05-13","cited_by_count":18,"area":null},{"id":"2601.08778","title":"Pervasive Annotation Errors Break Text-to-SQL Benchmarks and Leaderboards","created":"2026-01-13","cited_by_count":13,"area":null},{"id":"2411.13323","title":"Are Large Language Models Memorizing Bug Benchmarks?","created":"2024-11-20","cited_by_count":12,"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":"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":"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":"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":"2505.04670","title":"LLM Code Customization with Visual Results: A Benchmark on TikZ","created":"2025-05-07","cited_by_count":5,"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":"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":"2605.26321","title":"Anchor: Mitigating Artifact Drift in Agent Benchmark Generation","created":"2026-05-25","cited_by_count":5,"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":"2602.04296","title":"ProxyWar: Dynamic Assessment of LLM Code Generation in Game Arenas","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2604.06111","title":"AgentCE-Bench: Agent Configurable Evaluation with Scalable Horizons and Controllable Difficulty under Lightweight Environments","created":"2026-04-07","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":"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":"2504.21276","title":"Assessing LLM code generation quality through path planning tasks","created":"2025-04-30","cited_by_count":2,"area":null},{"id":"2508.02473","title":"NES: An Instruction-Free, Low-Latency Next Edit Suggestion Framework Powered by Learned Historical Editing Trajectories","created":"2025-08-04","cited_by_count":2,"area":null},{"id":"2603.20380","title":"Herding CATs: ALARA for Agent Harness Engineering in Portable Composable Multi-Agent Teams","created":"2026-03-20","cited_by_count":2,"area":null},{"id":"2603.21454","title":"Cross-Context Verification: Hierarchical Detection of Benchmark Contamination through Session-Isolated Analysis","created":"2026-03-23","cited_by_count":2,"area":null},{"id":"2608.13566","title":"Don't Claim Benchmark-Oriented Optimization Improves General Coding Capability -- Diverse Evaluation Is Required","created":"2026-06-26","cited_by_count":2,"area":null},{"id":"2602.18453","title":"LLM-Assisted Replication for Quantitative Social Science","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2607.28587","title":"PAIChecker: Uncovering and Checking PR-Issue Misalignment in SWE-Bench-Like Benchmarks","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2607.28887","title":"To Add Is Machine, To Delete Is Human: Measuring and Mitigating Deletion Avoidance in LLM Code Editing","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2503.04784","title":"KunlunBaize: LLM with Multi-Scale Convolution and Multi-Token Prediction Under TransformerX Framework","created":"2025-02-27","cited_by_count":0,"area":null},{"id":"2604.27551","title":"Beyond the Training Distribution: Mapping Generalization Boundaries in Neural Program Synthesis","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2606.05770","title":"Human Oversight and Overload: Two Hidden and Costly Burdens of AI-Assisted Software Engineering","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.25973","title":"Helpful or Harmful? Evaluating LLM-Assisted Vulnerability Patching via a Human Study","created":"2026-06-24","cited_by_count":0,"area":null}],"next_cursor":null}