让大模型与用户共同进化，形成可自升级的集体智能
LLM-Assisted Iterative Evolution with Swarm Intelligence Toward SuperBrain
- 通过用户与大模型的持续互动构建个性化认知单元
- 多单元协同进化，实现任务性能与提示词的双向优化
- 支持可解释、可对齐的智能体集群，适合复杂决策场景
我们提出一种新型的SuperBrain框架，用于构建集体智能，其核心是大语言模型（LLMs）与人类用户的共同演化。不同于静态提示工程或孤立智能体模拟，该方法建立从子类脑到超类脑的动态演进路径：(1) 用户与大模型长期交互形成认知二元体，具备自适应学习记忆；(2) 通过遗传算法辅助的正向-反向演化，不断优化提示词与任务表现；(3) 多个子类脑基于群体智能协调，在多目标适应度空间中优化并交换提炼出的启发式规则；(4) 其标准化行为与认知特征融合为超类脑——一种具备抽象、泛化与自我改进能力的涌现型元智能。本文阐述理论框架，展示初步实现（如无人机调度、KU/KI关键词过滤），并提出跨二元体知识整合注册机制。本研究为可扩展、可解释且伦理对齐的集体人工智能提供了概念基础与架构路线。
原文摘要 · Abstract (English)
We propose a novel SuperBrain framework for collective intelligence, grounded in the co-evolution of large language models (LLMs) and human users. Unlike static prompt engineering or isolated agent simulations, our approach emphasizes a dynamic pathway from Subclass Brain to Superclass Brain: (1) A Subclass Brain arises from persistent, personalized interaction between a user and an LLM, forming a cognitive dyad with adaptive learning memory. (2) Through GA-assisted forward-backward evolution, these dyads iteratively refine prompts and task performance. (3) Multiple Subclass Brains coordinate via Swarm Intelligence, optimizing across multi-objective fitness landscapes and exchanging distilled heuristics. (4) Their standardized behaviors and cognitive signatures integrate into a Superclass Brain, an emergent meta-intelligence capable of abstraction, generalization and self-improvement. We outline the theoretical constructs, present initial implementations (e.g., UAV scheduling, KU/KI keyword filtering) and propose a registry for cross-dyad knowledge consolidation. This work provides both a conceptual foundation and an architectural roadmap toward scalable, explainable and ethically aligned collective AI.
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。