提出可主动、私密、自进化的大模型智能体框架，突破传统助手被动响应局限。
Galaxy: A Cognition-Centered Framework for Proactive, Privacy-Preserving, and Self-Evolving LLM Agents
- 构建认知-系统一体化的'认知森林'结构，实现认知与设计闭环融合。
- 实测性能超越多个前沿基准，支持主动行为与个性化能力生成。
- 适合研究智能体自主性、隐私保护及持续进化方向的开发者和学者。
智能个人助理（IPAs）如Siri和Google Assistant旨在增强人类能力并代为执行任务。大语言模型（LLM）智能体的出现为IPA发展带来新机遇。尽管响应式能力已广泛研究，主动行为仍鲜有探索。如何设计具备主动性、隐私保护和自进化能力的IPA仍是重大挑战，其核心在于LLM智能体的认知架构。本文提出Cognition Forest——一种将认知建模与系统设计对齐的语义结构，将二者统一为自我强化循环而非分离处理。基于此，我们构建Galaxy框架，支持多维度交互与个性化能力生成。基于Galaxy实现了两个协作智能体：KoRa，一个增强认知的生成型智能体，兼具响应与主动技能；Kernel，一个基于元认知的元智能体，实现Galaxy的自进化与隐私保护。实验表明，Galaxy在多个先进基准上表现更优。消融实验与真实场景交互案例验证了其有效性。
原文摘要 · Abstract (English)
Intelligent personal assistants (IPAs) such as Siri and Google Assistant are designed to enhance human capabilities and perform tasks on behalf of users. The emergence of LLM agents brings new opportunities for the development of IPAs. While responsive capabilities have been widely studied, proactive behaviors remain underexplored. Designing an IPA that is proactive, privacy-preserving, and capable of self-evolution remains a significant challenge. Designing such IPAs relies on the cognitive architecture of LLM agents. This work proposes Cognition Forest, a semantic structure designed to align cognitive modeling with system-level design. We unify cognitive architecture and system design into a self-reinforcing loop instead of treating them separately. Based on this principle, we present Galaxy, a framework that supports multidimensional interactions and personalized capability generation. Two cooperative agents are implemented based on Galaxy: KoRa, a cognition-enhanced generative agent that supports both responsive and proactive skills; and Kernel, a meta-cognition-based meta-agent that enables Galaxy's self-evolution and privacy preservation. Experimental results show that Galaxy outperforms multiple state-of-the-art benchmarks. Ablation studies and real-world interaction cases validate the effectiveness of Galaxy.
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。