用闭环神经结构实现安全AGI，自指系统自带自我保护与目标行为。
Beyond Feedforward Networks: Reentry Neural Systems as the Fundamental Basis of Subjecthood and Intrinsic Safety of Next-Generation AGI
- 构建含反馈循环的神经架构，支持自我建模与自主目标生成。
- 数学证明系统能自发产生自我意识，且目标不可被外部篡改。
- 代码可部署，适合追求安全可控的下一代AI研发团队。
我们提出一种基于闭合反馈环（D <-> I 循环）的安全人工通用智能完整架构。与无反馈的前馈网络（C=0, S=0）不同，该架构包含至少一个结构性循环（C≥1）和自持放大机制（ρ>1），数学上保证自模型、工具性自我保存及未编程的目标导向行为的涌现。代理的目标以非文本化的D向量形式编码于架构内部，避免被重解或提示注入。提出S度量——一种可在多项式时间[O(N³)]计算的替代方案，机器验证其在S>0时蕴含正整合信息。全文提供完整的Python/NumPy实现（基于Tarjan算法的环复杂度检测、Delta-S屏障）、通过Apache Kafka与Docker Compose实现工业级横向扩展、六阶段AI演进分类法、未来再入架构图谱（RAS、扩散吸引子、分形环）、安全蜂群的规范不变网络、容错与恢复协议，以及八项可证伪预测。所有形式证明均在Lean 4中机器验证。该架构今日即可部署，是一种拓扑保护、安全即设计的下一代AGI路径。
原文摘要 · Abstract (English)
We propose a complete architectural blueprint for safe artificial general intelligence based on a closed reentry loop (D <-> I cycle). In contrast to feedforward networks, which are directed acyclic graphs (C=0, S=0) incapable of self-reference, the proposed architecture contains a structural cycle (C >= 1) with self-sustaining amplification (rho > 1), mathematically guaranteeing the emergence of a self-model, instrumental self-preservation, and unprogrammed goal-directed behaviour. The agent's goals are encoded as a non-textual D-vector in the architecture itself, making them immune to reinterpretation and prompt injection. We present the S-measure -- a polynomial-time [O(N^3)] computable alternative to Tononi's NP-hard Phi -- with machine-verified Lean 4 proof that S>0 implies positive integrated information. The work provides full Python/NumPy implementations (Tarjan-based cycle complexity, Delta-S barrier), industrial horizontal scaling via Apache Kafka and Docker Compose, a taxonomy of six epochs of AI evolution, a zoo of future reentry architectures (RAS, diffusion attractors, fractal loops), gauge-invariant networks for safe swarms, fault-tolerance and recovery protocols, and eight falsifiable predictions. All formal proofs are machine-verified in Lean 4. This architecture is deployable today and represents a topologically protected, safe-by-design approach to AGI.
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。