Learning from Supervision with Semantic and Episodic Memory: A Reflective Approach to Agent Adaptation

ArXi:2510.19897v2 Announce Type: replace-cross We investigate how agents built on pretrained large language models (LLMs) can learn target classification functions from labeled examples without parameter updates. While conventional approaches like fine-tuning are often costly, inflexible, and opaque, we propose a memory-augmented framework that leverages LLM-generated critiques grounded in labeled data. Our framework uses episodic memory to instance-level critiques - capturing specific past experiences - and semantic memory to distill these into reusable, task-level guidance.