From a Prompt to Repertoires: Evolving Functional REpertoires Enable LLM Continual Learning

Key points

• Continual learning remains challenging for large language models, which must enable models to acquire new skills and knowledge without degrading existing capabilities.1
• This raises a natural question: Can prompt optimization, as an efficient adaptation approach, be directly applied to continual learning?1
• We further instantiate EFRE in a minimal agent system and observe consistent improvements across different backbone models.1
• Overall, these results demonstrate EFRE's strong performance in continual learning for large language models and highlight its substantial potential for continual learning in advanced agent systems.1

Sources (1)

• [1]From a Prompt to Repertoires: Evolving Functional REpertoires Enable LLM Continual Learning
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 07:06 AM

  To address these limitations, we propose Evolving Functional REpertoires (EFRE), which replaces a single prompt with a repertoire of functions that evolves as new tasks arrive: compatible updates refine existing functions, while conflicting updates trigger the emergence of new ones.

  Continual learning remains challenging for large language models, which must enable models to acquire new skills and knowledge without degrading existing capabilities.

Extractive summary: sentences quoted from the sources.