研究发现大模型代理对经验依赖不忠，压缩经验常被忽视。
Large Language Model Agents Are Not Always Faithful Self-Evolvers
- 通过控制实验检验模型对原始与压缩经验的依赖程度。
- 压缩经验常被忽略，即使只有压缩经验可用时也如此。
- 适合关注大模型自我进化可靠性的研究人员参考。
自进化大语言模型（LLM）代理通过积累和重用过往经验持续改进，但其行为是否真正依赖这些经验尚不明确。本文首次系统性地探究了自进化LLM代理中经验忠实性的问题，即代理决策对所给经验的因果依赖性。我们对四种代表性框架在13种不同LLM主干和9个环境中的表现进行了全面评估，采用对原始和压缩形式经验的受控因果干预。分析发现显著不对称：代理始终依赖原始经验，却常常忽视或误解压缩经验，即便压缩经验是唯一提供的信息。这一差距在单/多代理配置及不同模型规模下均存在。我们追溯其成因于三方面：压缩内容的语义局限、内部处理偏差抑制经验使用，以及预训练先验已足够满足的任务场景。这些发现挑战了当前自进化方法的普遍假设，强调需发展更忠实可靠的经验证据整合方式。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。