Self-evolving large language model (LLM) agents continually improve by accumulating and reusing past experience, yet it remains unclear whether they faithfully rely on that experience to guide their behavior. We present the first systematic investigation of experience faithfulness, the causal dependence of an agent's decisions on the experience it is given, in self-evolving LLM agents. Using controlled causal interventions on both raw and condensed forms of experience, we comprehensively evaluate four representative frameworks across 13 LLM backbones and 9 environments. Our analysis uncovers a striking asymmetry: while agents consistently depend on raw experience, they often disregard or misinterpret condensed experience, even when it is the only experience provided. This gap persists across single- and multi-agent configurations and across backbone scales. We trace its underlying causes to three factors: the semantic limitations of condensed content, internal processing biases that suppress experience, and task regimes where pretrained priors already suffice. These findings challenge prevailing assumptions about self-evolving methods and underscore the need for more faithful and reliable approaches to experience integration.

翻译：自我进化的大型语言模型体通过积累和重用过往经验持续改进，但其行为是否真正忠实依赖于这些经验尚不明确。我们首次对自我进化LLM体中的经验忠实性——即决策对给定经验的因果依赖性——进行了系统性研究。通过对原始经验与精简经验实施受控因果干预，我们全面评估了13种LLM主干架构与9类环境下的四种代表性框架。分析揭示了一个显著的不对称性：体始终依赖原始经验，却经常忽视或曲解精简经验，即便后者是唯一可用的经验来源。这一差距在单智能体与多智能体配置及不同主干规模中持续存在。我们将其根本原因追溯至三个因素：精简内容的语义局限性、压制经验的内部处理偏差以及预训练先验已足的任务场景。这些发现挑战了关于自我进化方法的现有假设，并凸显了对更忠实可靠的经验整合方案的需求。