{"total":22,"rows":[{"id":"2502.10517","title":"KernelBench: Can LLMs Write Efficient GPU Kernels?","created":"2025-02-14","cited_by_count":225,"area":null},{"id":"2407.01502","title":"AI Agents That Matter","created":"2024-07-01","cited_by_count":219,"area":null},{"id":"2409.00138","title":"PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action","created":"2024-08-29","cited_by_count":171,"area":null},{"id":"2506.09050","title":"ALE-Bench: A Benchmark for Long-Horizon Objective-Driven Algorithm Engineering","created":"2025-06-10","cited_by_count":39,"area":null},{"id":"2603.04370","title":"$\\tau$-Knowledge: Evaluating Conversational Agents over Unstructured Knowledge","created":"2026-03-04","cited_by_count":39,"area":null},{"id":"2505.16667","title":"ELABORATION: A Comprehensive Benchmark on Human-LLM Competitive Programming","created":"2025-05-22","cited_by_count":16,"area":null},{"id":"2604.11806","title":"Detecting Safety Violations Across Many Agent Traces","created":"2026-04-13","cited_by_count":14,"area":null},{"id":"2504.04332","title":"IMPersona: Evaluating Individual Level LM Impersonation","created":"2025-04-06","cited_by_count":11,"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":"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":"2506.05579","title":"When Models Know More Than They Can Explain: Quantifying Knowledge Transfer in Human-AI Collaboration","created":"2025-06-05","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":"2510.17715","title":"QueST: Incentivizing LLMs to Generate Difficult Problems","created":"2025-10-20","cited_by_count":4,"area":null},{"id":"2505.12925","title":"CPRet: A Dataset, Benchmark, and Model for Retrieval in Competitive Programming","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2510.08702","title":"Scaling Laws for Code: A More Data-Hungry Regime","created":"2025-10-09","cited_by_count":3,"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":"2409.03402","title":"Game On: Towards Language Models as RL Experimenters","created":"2024-09-05","cited_by_count":1,"area":null},{"id":"2511.03898","title":"Secure Code Generation at Scale with Reflexion","created":"2025-11-05","cited_by_count":1,"area":null},{"id":"2601.11332","title":"Idea First, Code Later: Disentangling Problem Solving from Code Generation in Evaluating LLMs for Competitive Programming","created":"2026-01-16","cited_by_count":1,"area":null},{"id":"2602.16038","title":"Heuristic Search as Language-Guided Program Optimization","created":"2026-02-17","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":"2606.27369","title":"Reinforcement Learning without Ground-Truth Solutions can Improve LLMs","created":"2026-06-25","cited_by_count":0,"area":null}],"next_cursor":null}