{"total":7,"rows":[{"id":"2506.00233","title":"Ethical AI: Towards Defining a Collective Evaluation Framework","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2509.01058","title":"Speaking at the Right Level: Literacy-Controlled Counterspeech Generation with RAG-RL","created":"2025-09-01","cited_by_count":3,"area":null},{"id":"2511.19355","title":"Leveraging LLMs for reward function design in reinforcement learning control tasks","created":"2025-11-24","cited_by_count":2,"area":null},{"id":"2504.19480","title":"An Automated Reinforcement Learning Reward Design Framework with Large Language Model for Cooperative Platoon Coordination","created":"2025-04-28","cited_by_count":1,"area":null},{"id":"2510.20408","title":"Balancing Specialization and Centralization: A Multi-Agent Reinforcement Learning Benchmark for Sequential Industrial Control","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2512.09897","title":"SCOPE: Language Models as One-Time Teacher for Hierarchical Planning in Text Environments","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2605.14246","title":"Action-Conditioned Risk Gating for Safety-Critical Control under Partial Observability","created":"2026-05-14","cited_by_count":0,"area":null}],"next_cursor":null}