{"total":23,"rows":[{"id":"2505.24034","title":"LlamaRL: A Distributed Asynchronous Reinforcement Learning Framework for Efficient Large-scale LLM Training","created":"2025-05-29","cited_by_count":42,"area":null},{"id":"2505.19628","title":"HomeBench: Evaluating LLMs in Smart Homes with Valid and Invalid Instructions Across Single and Multiple Devices","created":"2025-05-26","cited_by_count":15,"area":null},{"id":"2509.25651","title":"AutoLabs: Cognitive Multi-Agent Systems with Self-Correction for Autonomous Chemical Experimentation","created":"2025-09-30","cited_by_count":15,"area":null},{"id":"2507.10800","title":"ThinkingViT: Matryoshka Thinking Vision Transformer for Elastic Inference","created":"2025-07-14","cited_by_count":7,"area":null},{"id":"2508.16599","title":"Humans Perceive Wrong Narratives from AI Reasoning Texts","created":"2025-08-09","cited_by_count":6,"area":null},{"id":"2509.18776","title":"AECBench: A Hierarchical Benchmark for Knowledge Evaluation of Large Language Models in the AEC Field","created":"2025-09-23","cited_by_count":6,"area":null},{"id":"2510.14717","title":"Seesaw: Accelerating Training by Balancing Learning Rate and Batch Size Scheduling","created":"2025-10-16","cited_by_count":6,"area":null},{"id":"2503.24364","title":"Query and Conquer: Execution-Guided SQL Generation","created":"2025-03-31","cited_by_count":5,"area":null},{"id":"2505.11449","title":"LLMs unlock new paths to monetizing exploits","created":"2025-05-16","cited_by_count":5,"area":null},{"id":"2505.20573","title":"Collision- and Reachability-Aware Multi-Robot Control with Grounded LLM Planners","created":"2025-05-26","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":"2510.05016","title":"Large Language Models Achieve Gold Medal Performance at the International Olympiad on Astronomy & Astrophysics (IOAA)","created":"2025-10-06","cited_by_count":3,"area":null},{"id":"2506.11021","title":"Eliminating Hallucination-Induced Errors in LLM Code Generation with Functional Clustering","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2506.18315","title":"Effective LLM Code Refinement via Property-Oriented and Structurally Minimal Feedback","created":"2025-06-23","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":"2506.05990","title":"Leveraging Generative AI for Enhancing Automated Assessment in Programming Education Contests","created":"2025-06-06","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":"2507.06138","title":"Coding Triangle: How Does Large Language Model Understand Code?","created":"2025-07-08","cited_by_count":1,"area":null},{"id":"2603.01973","title":"CharacterFlywheel: Scaling Iterative Improvement of Engaging and Steerable LLMs in Production","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2506.04965","title":"From Struggle (06-2024) to Mastery (02-2025) LLMs Conquer Advanced Algorithm Exams and Pave the Way for Editorial Generation","created":"2025-06-05","cited_by_count":0,"area":null},{"id":"2602.18492","title":"Vibe Coding on Trial: Operating Characteristics of Unanimous LLM Juries","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2608.21543","title":"presto: Efficient, Training-free, and Open-world Object Placement via Imaginary Search","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2610.04261","title":"Playing social deduction games with reinforcement fine-tuned large language models","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}