MiA-Signature：面向长上下文理解的全局激活近似方法

MiA-Signature: Approximating Global Activation for Long-Context Understanding

May 7, 2026

作者: Yuqing Li, Jiangnan Li, Mo Yu, Zheng Lin, Weiping Wang, Jie Zhou

cs.AI

摘要

认知科学领域日益增多的研究表明，可报告的意识访问与分布式记忆系统上的全局激活相关，但这种激活仅能部分访问，因为个体无法直接访问或枚举所有被激活的内容。这种张力暗示了一种合理机制：认知可能依赖于一种紧凑的表征，该表征能近似模拟激活对下游处理的全局影响。受此启发，我们提出心智景观激活特征（MiA-Signature）的概念，即由查询引发的全局激活模式的压缩表征。在大型语言模型系统中，这通过基于子模函数的高层概念选择来实现，这些概念覆盖被激活的上下文空间，并可选择性地通过工作记忆进行轻量级迭代更新来优化。最终得到的MiA-Signature作为条件信号，能在保持计算可行性的同时近似模拟完整激活状态的效果。将MiA-Signature集成到检索增强生成和智能体系统中，在多项长上下文理解任务上实现了持续的性能提升。

English

A growing body of work in cognitive science suggests that reportable conscious access is associated with global ignition over distributed memory systems, while such activation is only partially accessible as individuals cannot directly access or enumerate all activated contents. This tension suggests a plausible mechanism that cognition may rely on a compact representation that approximates the global influence of activation on downstream processing. Inspired by this idea, we introduce the concept of Mindscape Activation Signature (MiA-Signature), a compressed representation of the global activation pattern induced by a query. In LLM systems, this is instantiated via submodular-based selection of high-level concepts that cover the activated context space, optionally refined through lightweight iterative updates using working memory. The resulting MiA-Signature serves as a conditioning signal that approximates the effect of the full activation state while remaining computationally tractable. Integrating MiA-Signatures into both RAG and agentic systems yields consistent performance gains across multiple long-context understanding tasks.