AINeutralarXiv – CS AI · 10h ago6/10
🧠
Do Self-Evolving Agents Forget? Capability Degradation and Preservation in Lifelong LLM Agent Adaptation
Researchers identify capability erosion in self-evolving LLM agents, where systems adapting to new tasks progressively lose previously learned abilities across workflow, skill, model, and memory dimensions. The study proposes Capability-Preserving Evolution (CPE), a stabilization framework that maintains performance on existing tasks while enabling new adaptations, demonstrating improvements in retained capability stability across all evolution channels.
🧠 GPT-5