{"total":20,"rows":[{"id":"2603.20633","title":"Seed1.8 Model Card: Towards Generalized Real-World Agency","created":"2026-03-21","cited_by_count":50,"area":null},{"id":"2602.16763","title":"When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation","created":"2026-02-18","cited_by_count":33,"area":null},{"id":"2509.21016","title":"RL Grokking Recipe: How Does RL Unlock and Transfer New Algorithms in LLMs?","created":"2025-09-25","cited_by_count":23,"area":null},{"id":"2512.15699","title":"FrontierCS: Evolving Challenges for Evolving Intelligence","created":"2025-12-17","cited_by_count":23,"area":null},{"id":"2507.20439","title":"When Prompts Go Wrong: Evaluating Code Model Robustness to Ambiguous, Contradictory, and Incomplete Task Descriptions","created":"2025-07-27","cited_by_count":11,"area":null},{"id":"2510.12803","title":"AutoCode: LLMs as Problem Setters for Competitive Programming","created":"2025-09-29","cited_by_count":11,"area":null},{"id":"2510.00332","title":"When Hallucination Costs Millions: Benchmarking AI Agents in High-Stakes Adversarial Financial Markets","created":"2025-09-30","cited_by_count":5,"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":"2607.19653","title":"PerfAgent: Profiler-Guided Iterative Refinement for Repository-Level Code Optimization","created":"2026-07-22","cited_by_count":3,"area":null},{"id":"2601.01739","title":"K-EXAONE Technical Report","created":"2026-01-05","cited_by_count":2,"area":null},{"id":"2605.16358","title":"LEAF: A Living Benchmark for Event-Augmented Forecasting","created":"2026-05-09","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":"2606.20517","title":"Multi-LCB: Extending LiveCodeBench to Multiple Programming Languages","created":"2026-06-18","cited_by_count":2,"area":null},{"id":"2602.02523","title":"TabularMath: Evaluating Computational Extrapolation in Tabular Learning via Program-Verified Synthesis","created":"2026-01-25","cited_by_count":1,"area":null},{"id":"2605.15607","title":"Syntax Without Semantics: Teaching Large Language Models to Code in an Unseen Language","created":"2026-05-15","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":"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":"2606.25450","title":"The Generalization Spectrum: A Chromatographic Approach to Evaluating Learning Algorithms","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2609.29410","title":"Large Language Models for Programming: Actually Fixing or Reimplementing Incorrect Code?","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}