TAG ARCHIVE
recursive-improvement
4 MARIA OS blog articles tagged recursive-improvement, organized as a Bonginkan topic archive for search engines and LLM retrieval.
Judgment OS / Decision Intelligence OS
Core MARIA OS research on turning organizational judgment into executable decision systems.
Agentic Company Architecture
Research on human-agent organizations, delegation boundaries, role topology, and governed autonomy.
Responsibility Gates and AI Governance
Safety, accountability, fail-closed gates, auditability, and human-in-the-loop control for AI agents.
Multi-Agent Mathematics
Formal models for convergence, stability, game theory, graph dynamics, and multi-agent evaluation.
Evidence, RAG, and Knowledge Governance
Evidence bundles, retrieval architecture, Graph RAG, knowledge trust, and auditable reasoning pipelines.
Agentic R&D and Judgment Science
Research operations, simulation labs, judgment science, recursive improvement, and experimental AI governance.
MARIA VITAL: The Life Support System for Agent Organizations — From Heartbeat Monitoring to Recursive Self-Improvement
Why agent organizations need an autonomic nervous system, and how 4-layer vital monitoring, behavioral health diagnosis, self-repair orchestration, and failure-to-improvement conversion keep AI agents alive, healthy, and evolving
Creating AI agents is easy. Keeping them alive is hard. When agents scale beyond a handful, the problem shifts from intelligence to operations: heartbeats stop silently, processing queues back up, memory references decay, judgment quality degrades, and failures cascade across dependencies. MARIA VITAL addresses this by implementing a biological metaphor — the autonomic nervous system — for agent organizations. This paper presents the theoretical foundations in biological self-monitoring, the 4-layer architecture (Vital Signal, Behavioral Health, Recovery Orchestration, Recursive Improvement), the Health Score formalization, the self-repair pipeline with shadow agent validation, and the connection to biological homeostasis through the Observe-Diagnose-Recover-Improve loop.
MARIA VITAL：Agent組織のための生命維持システム — Heartbeat監視から再帰的自己改善まで
なぜAgent組織には自律神経系が必要なのか、そして4層バイタル監視、行動健全性診断、自己修復オーケストレーション、障害→改善変換がAIエージェントの生存・健康・進化を維持する方法
AIエージェントを作るのは簡単だ。生かし続けるのが難しい。エージェントが少数を超えてスケールすると、問題は知能から運用に移る：Heartbeatが静かに停止し、処理キューが詰まり、記憶参照が劣化し、判断品質が低下し、障害が依存関係を通じて連鎖する。MARIA VITALは生物学的メタファー — 自律神経系 — をAgent組織に実装することでこれに対処する。本論文では生物学的自己監視の理論的基盤、4層アーキテクチャ、Health Scoreの定式化、シャドーエージェント検証による自己修復パイプライン、そしてObserve-Diagnose-Recover-Improveループを通じた生物学的恒常性との接続を報告する。
The Brain as a Recursive Self-Improving System
Predictive coding, dopamine learning, and the millisecond A/B test running inside your skull
The human brain continuously generates predictions, measures errors, and updates its own parameters — a recursive self-improvement loop that operates across timescales from milliseconds to decades. This article explores the neuroscience of predictive coding, dopamine reward prediction error, and synaptic plasticity as a blueprint for agent evolution.
The Complete Action Router: From Theory to Implementation to Scaling in MARIA OS
End-to-end architecture of the three-layer Action Router stack (Intent Parser, Action Resolver, Gate Controller), with recursive optimization and scaling patterns for 100+ agent deployments
The Action Router Intelligence Theory established that routing must control actions, not classify words. This paper presents the full implementation architecture: a three-layer stack of Intent Parser (context-aware goal extraction), Action Resolver (state-dependent action selection with precondition-effect semantics), and Gate Controller (risk-tiered execution envelopes integrated with MARIA OS governance). We detail a recursive optimization loop in which routing policies learn from execution outcomes, formalized as an online convex optimization problem with O(√T) regret. We then present a scaling architecture for 100+ concurrent agents using coordinate-based sharding, hierarchical action caches, and zone-local resolution. Integration with the MARIA OS Decision Pipeline state machine is formalized as a product automaton. Production benchmarks show sub-30ms P99 latency at 10,000 routing decisions per second, with first-attempt accuracy improving from 93.4% to 97.8% after 30 days of recursive learning.