Tag
SERA（Self-Evaluating Recursive Agents）提出一个联合训练单一策略以实现子任务分解、执行与评估的框架，通过可验证结果对齐评估准则并引入叶覆盖奖励，显著优于递归智能体基线，表明学会评估能提升求解能力。
Cursor AI describes its recursive agent system for scaling training of its Composer model, using a fleet of agents that self-manage and alert humans when issues arise. The system enables parallel experiments and accelerates research, treating researcher time as the scarcest resource.
RAO (Recursive Agent Optimization) is an end-to-end reinforcement learning approach for training LLM agents to spawn, delegate to, and coordinate with recursive copies of themselves, turning recursive inference into a learned capability.