Chain-of-Experience for Continual LLM Improvement

Humans continuously learn from experience, whereas conventional large language model (LLM) evaluations ignore the models' ability to improve through inference-time interaction.

Humans continuously learn from experience, whereas conventional large language model (LLM) evaluations ignore the models' ability to improve through inference-time interaction. In this paper, we study how LLMs learn from iterative experience at test time, a setting we refer to…