MSSR: Memory-Aware Adaptive Replay for Continual LLM Fine-Tuning

ArXi:2603.09892v1 Announce Type: cross Continual fine-tuning of large language models (LLMs) is becoming increasingly crucial as these models are deployed in dynamic environments where tasks and data distributions evolve over time. While strong adaptability enables rapid acquisition of new knowledge, it also exposes LLMs to catastrophic forgetting, where previously learned skills degrade during sequential