TAG ARCHIVE
agent-evolution
6 MARIA OS blog articles tagged agent-evolution, 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.
Agentic R&D and Judgment Science
Research operations, simulation labs, judgment science, recursive improvement, and experimental AI governance.
Self-Modifying Agent Systems: Architecture for Agents That Rewrite Their Own Tools, Commands, and Workflows
Beyond tool creation — a formal framework for bounded self-modification with stability guarantees and immutable audit trails
Agents that merely create new tools hit a ceiling. Real operational autonomy requires agents that can modify existing tools, rewrite commands, and restructure workflows based on performance feedback. We present a formal architecture for bounded self-modification with Lyapunov stability analysis, halting guarantees, and responsibility-gated audit trails.
自己書き換えAgentシステム — Tool・Command・Workflowを自律的に進化させるアーキテクチャ
ツール生成を超えて — 安定性保証と不変監査証跡を備えた有界自己修正の形式的フレームワーク
新しいツールを生成するだけのAgentには限界がある。真の運用自律性には、パフォーマンスフィードバックに基づいて既存のツール・コマンド・ワークフローを自ら書き換える能力が必要だ。本稿では、Lyapunov安定性解析・停止保証・責任ゲート付き監査証跡を備えた有界自己修正アーキテクチャSMASを提示する。
Self-Extending Agent Architecture: Capability Gap Detection, Tool Synthesis, and Autonomous Evolution Under Governance Constraints
Agents that recognize their own limitations and autonomously build the tools they need — within the safety boundaries of an operating system
Traditional AI agents are bounded by the tools humans provide. When an agent encounters a task outside its toolset, it halts and waits. This paper introduces the Self-Extending Agent Architecture (SEAA), where agents detect their own capability gaps, synthesize new tools through code generation, validate those tools in sandboxed environments, and register them into the OS runtime — all under human-governed safety constraints. We formalize the agent state model X_t = (C, T, M, R), derive the self-extension equation X_{t+1} = E_t ∘ G_t ∘ J_t(X_t), prove Capability Monotonicity under validation gates, and demonstrate the architecture within MARIA OS's hierarchical coordinate system.
自己拡張型Agentアーキテクチャ — 能力不足を自ら認識し、ツールを自律生成するOS設計
Agentが自身の限界を検知し、コード生成でツールを合成し、サンドボックスで検証し、OSランタイムに登録する — すべてガバナンス制約の下で
従来のAIエージェントは、人間が提供したツールセットに束縛される。未対応タスクに遭遇すると停止し、人間の介入を待つ。本論文では、Self-Extending Agent Architecture（SEAA）を提案する。エージェントが自律的に能力ギャップを検出し、構造化コード生成でツールを合成し、サンドボックス環境で検証し、OSランタイムに登録するフレームワークである。エージェント状態モデル X_t = (C, T, M, R) を形式化し、自己拡張方程式 X_{t+1} = E_t ∘ G_t ∘ J_t(X_t) を導出し、検証ゲート下での能力単調性定理を証明する。MARIA OSの階層座標系における具体的な実装を示す。
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.
Evolution as Safe Mutation Governance
DNA repair, mutation rate control, and developmental constraints reveal evolution as a governed improvement process
Evolution is commonly misunderstood as purely random mutation plus natural selection. In reality, DNA repair mechanisms, mutation rate regulation, developmental constraints, and epigenetic inheritance make it a sophisticated governed mutation system. This article reframes evolution as a design pattern for safe agent self-improvement.