الباحثون

Junkai Ma

المنشورات 2

نسخة أولية وصول مفتوح

Principles that Guide, Actions that Inform: Agent Evolution via Knowledge Abstraction

Bowen Ye, Yongchao Xu, Junkai Ma وآخرون · 2026

Large language model (LLM) agents have demonstrated strong capabilities in interactive environments, yet their ability to continually evolve from experience remains limited. Although fine-tuning enables adaptation, its dependence on parameter access and high computational costs restrict its flexibility, especially for …

المؤلفون المشاركون