Do Self-Evolving Agents Forget? Capability Degradation and Preservation in Lifelong LLM Agent Adaptation

2026-05-10

AI Summary

This study addresses a critical challenge in the continuous self-evolution of large language model agents: the tendency to lose previously acquired capabilities while adapting to new tasks. The authors formally identify and term this phenomenon “capability erosion in self-evolution.” To mitigate this issue across four key dimensions—workflow, skills, model parameters, and memory—they propose a general Capability-Preserving Evolution (CPE) principle that explicitly constrains destructive capability drift, thereby enabling the acquisition of new competencies without compromising prior performance. Experimental results demonstrate that CPE significantly enhances stability in models such as GPT-5.1, increasing the retention rate of simple tasks in workflow evolution from 41.8% to 52.8% while simultaneously improving adaptability to complex tasks.

Abstract

Recent advances in LLM agents enable systems that autonomously refine workflows, accumulate reusable skills, self-train their underlying models, and maintain persistent memory. However, we show that such self-evolution is often non-monotonic: adapting to new task distributions can progressively degrade previously acquired capabilities across all major evolution channels. We identify this phenomenon as \emph{capability erosion under self-evolution} and show that it consistently emerges across workflow, skill, model, and memory evolution. To mitigate this issue, we propose \emph{Capability-Preserving Evolution} (CPE), a general stabilization principle that constrains destructive capability drift during continual adaptation. Across all four evolution dimensions, CPE consistently improves retained capability stability while preserving adaptation performance. For example, in workflow evolution, CPE improves retained simple-task performance from 41.8\% to 52.8\% under GPT-5.1 optimization while simultaneously achieving stronger complex-task adaptation. Our findings suggest that stable long-horizon self-evolving agents require not only acquiring new capabilities, but also explicitly preserving previously learned ones during continual adaptation.

Problem

• capability erosion
• self-evolving agents
• lifelong adaptation
• LLM agents
• capability degradation

Innovation

• capability erosion
• self-evolving agents
• lifelong adaptation
• Capability-Preserving Evolution
• continual learning