{"total":10,"rows":[{"id":"2504.01014","title":"AnimeGamer: Infinite Anime Life Simulation with Next Game State Prediction","created":"2025-04-01","cited_by_count":7,"area":null},{"id":"2601.03509","title":"Evolving Programmatic Skill Networks","created":"2026-01-07","cited_by_count":7,"area":null},{"id":"2410.11711","title":"Zero-shot Model-based Reinforcement Learning using Large Language Models","created":"2024-10-15","cited_by_count":6,"area":null},{"id":"2603.09036","title":"SCALAR: Learning and Composing Skills through LLM Guided Symbolic Planning and Deep RL Grounding","created":"2026-03-10","cited_by_count":5,"area":null},{"id":"2604.09107","title":"TensorHub: Scalable and Elastic Weight Transfer for LLM RL Training","created":"2026-04-10","cited_by_count":4,"area":null},{"id":"2607.22832","title":"MEMENTO: Memory-Guided Memetic Code-as-Policy Evolution","created":"2026-07-24","cited_by_count":3,"area":null},{"id":"2503.21263","title":"Cultivating Game Sense for Yourself: Making VLMs Gaming Experts","created":"2025-03-27","cited_by_count":1,"area":null},{"id":"2607.10546","title":"LLM-PDESR: Robust PDE Discovery via Subdomain Weighted Residuals and LLM-Guided Symbolic Hypothesis Generation","created":"2026-07-12","cited_by_count":1,"area":null},{"id":"2409.18014","title":"Role-RL: Online Long-Context Processing with Role Reinforcement Learning for Distinct LLMs in Their Optimal Roles","created":"2024-09-26","cited_by_count":0,"area":null},{"id":"2604.15357","title":"Taming Asynchronous CPU-GPU Coupling for Frequency-aware Latency Estimation on Mobile Edge","created":"2026-04-11","cited_by_count":0,"area":null}],"next_cursor":null}