{"total":42,"rows":[{"id":"2502.12115","title":"SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?","created":"2025-02-17","cited_by_count":105,"area":null},{"id":"2507.09089","title":"Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity","created":"2025-07-12","cited_by_count":101,"area":null},{"id":"2506.03524","title":"Seed-Coder: Let the Code Model Curate Data for Itself","created":"2025-06-04","cited_by_count":49,"area":null},{"id":"2505.11792","title":"Solver-Informed RL: Grounding Large Language Models for Authentic Optimization Modeling","created":"2025-05-17","cited_by_count":45,"area":null},{"id":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","cited_by_count":28,"area":null},{"id":"2512.15699","title":"FrontierCS: Evolving Challenges for Evolving Intelligence","created":"2025-12-17","cited_by_count":23,"area":null},{"id":"2508.08228","title":"LL3M: Large Language 3D Modelers","created":"2025-08-11","cited_by_count":20,"area":null},{"id":"2504.15254","title":"CRUST-Bench: A Comprehensive Benchmark for C-to-safe-Rust Transpilation","created":"2025-04-21","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":"2504.21751","title":"CodeFlowBench: A Multi-turn, Iterative Benchmark for Complex Code Generation","created":"2025-04-30","cited_by_count":17,"area":null},{"id":"2508.16402","title":"AetherCode: Evaluating LLMs' Ability to Win In Premier Programming Competitions","created":"2025-08-22","cited_by_count":11,"area":null},{"id":"2503.16922","title":"RustEvo^2: An Evolving Benchmark for API Evolution in LLM-based Rust Code Generation","created":"2025-03-21","cited_by_count":10,"area":null},{"id":"2506.06821","title":"Can LLMs Generate Reliable Test Case Generators? A Study on Competition-Level Programming Problems","created":"2025-06-07","cited_by_count":9,"area":null},{"id":"2601.19697","title":"AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completion","created":"2026-01-27","cited_by_count":7,"area":null},{"id":"2505.12331","title":"OSS-Bench: Benchmark Generator for Coding LLMs","created":"2025-05-18","cited_by_count":6,"area":null},{"id":"2508.07932","title":"\\(X\\)-evolve: Solution space evolution powered by large language models","created":"2025-08-11","cited_by_count":6,"area":null},{"id":"2506.01074","title":"How Programming Concepts and Neurons Are Shared in Code Language Models","created":"2025-06-01","cited_by_count":5,"area":null},{"id":"2507.22462","title":"IFEvalCode: Controlled Code Generation","created":"2025-07-30","cited_by_count":5,"area":null},{"id":"2602.16066","title":"Improving Interactive In-Context Learning from Natural Language Feedback","created":"2026-02-17","cited_by_count":5,"area":null},{"id":"2503.05860","title":"Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2510.09595","title":"LiveOIBench: Can Large Language Models Outperform Human Contestants in Informatics Olympiads?","created":"2025-10-10","cited_by_count":4,"area":null},{"id":"2605.24812","title":"CoRe-Code: Collaborative Reinforcement Learning for Code Generation","created":"2026-05-24","cited_by_count":4,"area":null},{"id":"2507.13337","title":"FormulaOne: Measuring the Depth of Algorithmic Reasoning Beyond Competitive Programming","created":"2025-07-17","cited_by_count":3,"area":null},{"id":"2503.06885","title":"ProBench: Judging Multimodal Foundation Models on Open-ended Multi-domain Expert Tasks","created":"2025-03-10","cited_by_count":2,"area":null},{"id":"2606.12864","title":"Beyond Problem Solving: UOJ-Bench for Evaluating Code Generation, Hacking, and Repair in Competitive Programming","created":"2026-06-11","cited_by_count":2,"area":null},{"id":"2503.07884","title":"LLMIA: An Out-of-the-Box Index Advisor via In-Context Learning with LLMs","created":"2025-03-10","cited_by_count":1,"area":null},{"id":"2507.03162","title":"MateInfoUB: A Real-World Benchmark for Testing LLMs in Competitive, Multilingual, and Multimodal Educational Tasks","created":"2025-07-03","cited_by_count":1,"area":null},{"id":"2509.23510","title":"Model Consistency as a Cheap yet Predictive Proxy for LLM Elo Scores","created":"2025-09-27","cited_by_count":1,"area":null},{"id":"2510.18895","title":"CosmoCore Affective Dream-Replay Reinforcement Learning for Code Generation","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2606.13982","title":"Adaptive Nucleus Truncation for Long-Form Reasoning","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2509.04442","title":"Delta Activations: A Representation for Finetuned Large Language Models","created":"2025-09-04","cited_by_count":0,"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":"2603.13761","title":"Level Up: Defining and Exploiting Transitional Problems for Curriculum Learning","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2603.14463","title":"An Industrial-Scale Insurance LLM Achieving Verifiable Domain Mastery and Hallucination Control without Competence Trade-offs","created":"2026-03-15","cited_by_count":0,"area":null},{"id":"2605.05949","title":"MAS-Algorithm: A Workflow for Solving Algorithmic Programming Problems with a Multi-Agent System","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.12384","title":"Scalable Token-Level Hallucination Detection in Large Language Models","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.30394","title":"CodeGolf Bench: A Multi-Language Benchmark for Evaluating Concise Code Generation Capabilities of Large Language Models","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.25450","title":"The Generalization Spectrum: A Chromatographic Approach to Evaluating Learning Algorithms","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2607.14181","title":"Quantize with Confidence? An Empirical Study of Quantization for Code Generation","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2607.26457","title":"DHRCL:Training Code LLMs with Dense Hierarchical Rewards and Curriculum Learning","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2609.21259","title":"CogGym: Towards Large-Scale Comparative Evaluation of Human and Machine Cognition","created":"2026-09-18","cited_by_count":0,"area":null}],"next_cursor":null}