الباحثون

Baihang Liu

المنشورات 1

نسخة أولية وصول مفتوح

Use and Disuse: Intent-Structured Experience Consolidation for Memory and Learning in LLM Agents

Xiangyi Zeng, Baihang Liu, Xutong Wang وآخرون · 2026

The evolution of Large Language Model agents from single-task execution to long-term autonomous operation highlights the critical challenge of transforming continuous experiences into reusable knowledge. To address this, we propose Hippocam, a hierarchical memory and continual learning architecture. Hippocam draws insp …

المؤلفون المشاركون