closed-loop-learning

Tag

Cards List
#closed-loop-learning

Know What You Don't Know: Agentic Data Synthesis by Evolving Generation Space for Closed-Loop Learning

arXiv cs.AI ↗ · 2026-10-12 Cached

AWS AI 研究人员提出 EvoSyn,一个由学习反馈驱动的多智能体框架,通过演化生成空间实现闭环数据合成,在 τ²-Bench 和 CAR-Bench 上比最强基线平均提升 13.3 个任务成功率点。

0 favorites 0 likes
#closed-loop-learning

DriveZero: End-to-End Driving Beyond Human Demonstrations

Hugging Face Daily Papers ↗ · 2026-09-05 Cached

DriveZero is an end-to-end autonomous driving system that combines a vision foundation model for perception with reinforcement learning for action, achieving driving behaviors beyond human demonstrations and state-of-the-art performance on benchmarks like nuPlan and NAVSIM.

0 favorites 0 likes
#closed-loop-learning

MMG2Skill: Can Agents Distill In-the-Wild Guides into Self-Evolving Skills?

Hugging Face Daily Papers ↗ · 2026-06-01 Cached

MMG2Skill converts web-based procedural guides into executable skills for agents through closed-loop learning, improving performance across GUI control, gameplay, and card play tasks with macro-average gains of +12.8 to +25.3 percentage points.

0 favorites 0 likes
← Back to home

Submit Feedback