揭示大模型在智能体系统中的信息脆弱性边界，指导何时用模型能提升性能。
A Theory of LLM Information Susceptibility
- 构建多变量效用框架，分析大模型干预对策略性能敏感度的影响
- 实证验证跨不同领域与模型规模，发现共缩放架构可突破敏感度上限
- 提出嵌套结构可能是实现持续智能体自进化的必要条件
大型语言模型（LLMs）正越来越多地被用作智能体系统的优化模块，但此类模型介导改进的根本极限仍不清晰。本文提出一种大模型信息脆弱性理论，核心假设是当计算资源足够大时，固定大模型的介入不会增加策略集对预算的性能敏感度。我们建立了一个多变量效用函数框架，将该假设推广至具有多个协同变化预算通道的架构，并讨论了共缩放如何突破敏感度界限的条件。在结构多样、跨度一个数量级的模型规模和领域中，我们实证验证了该理论，发现嵌套式共缩放架构能开辟固定配置无法实现的响应通道。结果阐明了大模型干预何时有效、何时无效，表明统计物理工具可为人工智能系统设计提供预测性约束。若该敏感度假设普遍成立，理论暗示嵌套架构或为开放式智能体自我改进的必要结构条件。
原文摘要 · Abstract (English)
Large language models (LLMs) are increasingly deployed as optimization modules in agentic systems, yet the fundamental limits of such LLM-mediated improvement remain poorly understood. Here we propose a theory of LLM information susceptibility, centred on the hypothesis that when computational resources are sufficiently large, the intervention of a fixed LLM does not increase the performance susceptibility of a strategy set with respect to budget. We develop a multi-variable utility-function framework that generalizes this hypothesis to architectures with multiple co-varying budget channels, and discuss the conditions under which co-scaling can exceed the susceptibility bound. We validate the theory empirically across structurally diverse domains and model scales spanning an order of magnitude, and show that nested, co-scaling architectures open response channels unavailable to fixed configurations. These results clarify when LLM intervention helps and when it does not, demonstrating that tools from statistical physics can provide predictive constraints for the design of AI systems. If the susceptibility hypothesis holds generally, the theory suggests that nested architectures may be a necessary structural condition for open-ended agentic self-improvement.
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。