Action Routingの再帰適応: MARIA OSが実行結果から学習する仕組み

要旨

エンタープライズ AI ガバナンスにおけるアクション ルーティングにより、各決定、承認、エスカレーション、委任をどのエージェントまたはエージェント グループが処理するかが決まります。運用システムの現在のルーティング アーキテクチャは主に静的です。ルーティング ルールは、組織構造、エージェントの役割、ドメイン境界に基づいて管理者によって定義され、手動で更新されるまで固定されたままになります。この静的なアプローチでは、実際のエンタープライズ環境を特徴付けるエージェントのパフォーマンス、進化するワークロード パターン、およびコンテキスト依存の品質変動の動的な性質を捉えることができません。このペーパーでは、観察された結果に基づいて各実行サイクル後にルーティング パラメータが更新される、MARIA OS アクション ルーティング用の再帰的適応フレームワークを紹介します。コア学習ルール θ_{t+1} = θ_t + η∇J(θ_t) は、期待される配線品質 J(θ) を最大化する方向に配線パラメーターを更新します。勾配は、意思決定の精度、完了時間、エスカレーション頻度、関係者の満足度などの実行結果シグナルから推定されます。標準的な確率的近似条件 (∑η_t = ∞ および ∑η_t² < ∞ でステップ サイズを減少させる) の下で、パラメーター シーケンス {θ_t} がほぼ確実に J(θ) の局所最適値のセットに収束することを証明します。我々は、適応プロセスが収束全体を通じて安全なパラメーター領域内に制限されたままであることを示すリアプノフの安定性保証を確立します。トンプソン サンプリングにより代替ルートのベイジアン探索が可能になり、分散型コンセンサスに基づくマルチエージェント調整プロトコルにより、複数のエージェントが同時にルーティングを適応させる場合の振動的な競合が防止されます。この論文の定量的なセクションは、14 の MARIA OS 動作コンテキストにわたる再生形式の評価であり、現在のリポジトリが既に存在するという監査済みの主張ではありません。実稼働環境でオンライン学習ルーティングを出荷します。

1. はじめに

Static routing is dead. This blunt assertion reflects a growing recognition in the AI governance community that fixed routing rules cannot keep pace with the dynamic reality of enterprise AI operations. When MARIA OS routes an action to an agent, the routing decision encodes implicit assumptions about that agent’s current capability, availability, domain expertise, and workload. These assumptions are valid at configuration time but degrade continuously: agents learn new skills, develop fatigue patterns, acquire domain-specific experience that makes them differentially suited to certain action types, and undergo organizational changes that shift their responsibilities. A routing system that cannot learn from execution outcomes is systematically misinformed, making decisions based on stale assumptions that diverge further from reality with each passing day.

The challenge of adaptive routing in AI governance goes beyond conventional reinforcement learning. In a standard RL setting, the agent explores actions, observes rewards, and updates its policy without concern for the consequences of exploratory actions. In AI governance, every routed action has real consequences — a poorly routed decision may result in delayed patient care, regulatory non-compliance, or financial loss. Exploration must be balanced against the responsibility to maintain service quality during the learning process. Furthermore, the routing system operates in a multi-agent environment where multiple agents are simultaneously adapting their routing parameters, creating the potential for oscillatory conflicts where one agent’s adaptation destabilizes another’s learned policy.

This paper addresses these challenges through a principled recursive adaptation framework that provides formal convergence guarantees, stability bounds, and coordination protocols. The framework treats route adaptation as a stochastic approximation problem, leveraging decades of mathematical theory on convergent iterative algorithms to ensure that the adaptive routing process is well-behaved. Thompson sampling provides a Bayesian mechanism for balancing exploration and exploitation, naturally concentrating routing attempts on promising alternatives while maintaining sufficient exploration to detect changes in the environment. A distributed consensus protocol ensures that multi-agent adaptation converges to a coordinated equilibrium rather than oscillating between conflicting policies.

実装の意味は簡単です。既存のルーター契約を置き換える必要はありません。学習可能なスコアリング レイヤーを接続する必要があります。登録されたアクションとハンドラーは安定したままですが、適応重みにより、実行後の結果に基づいて、実行可能なハンドラー、チーム、またはエスカレーション パスの間の相対的な優先度が更新されます。

2. フィードバック ループのアーキテクチャ

2.1 実行結果シグナル

The foundation of recursive route adaptation is the execution outcome signal — the observable result of a routed action that informs the routing system about the quality of its decision. We define the outcome signal o(a, t) for action a routed to target t as a vector of five components: o(a, t) = (accuracy, latency, escalation, satisfaction, compliance). Accuracy measures whether the action was completed correctly (binary for deterministic actions, continuous for probabilistic ones). Latency measures the time from routing to completion relative to the action’s urgency. Escalation indicates whether the target agent needed to escalate the action, suggesting a capability mismatch. Satisfaction captures stakeholder feedback when available. Compliance records whether the action’s execution satisfied all regulatory and policy requirements.

2.2 Reward Function

The outcome signal is aggregated into a scalar reward through a weighted combination: r(a, t) = w_acc · accuracy + w_lat · (1 - latency/latency_max) + w_esc · (1 - escalation) + w_sat · satisfaction + w_comp · compliance. The weights w = (w_acc, w_lat, w_esc, w_sat, w_comp) are configurable per deployment and reflect organizational priorities. Financial services deployments typically weight compliance and accuracy heavily, while customer-facing deployments emphasize latency and satisfaction. The reward function maps to [0, 1], enabling cross-deployment comparison. The expected routing quality under parameters θ is J(θ) = E_{a ∼ A, t = R_θ(a,s)}[r(a, t)], where R_θ is the routing function parameterized by θ.

2.3 Feedback Delay and Credit Assignment

A critical challenge in route adaptation is feedback delay: the outcome of a routed action may not be observable for hours, days, or even weeks after the routing decision. A decision routed to an analyst for review may take three days to complete, and the accuracy of the decision may not be known until its consequences manifest weeks later. The adaptation framework handles this through a temporal credit assignment mechanism. Each routing decision is timestamped and stored in a pending-feedback buffer. When outcome signals arrive, they are matched to their originating routing decisions and the corresponding parameter updates are computed and applied. The effective learning rate is adjusted for delay: η_eff = η · γ^{Δt} where γ ∈ (0, 1) is a discount factor and Δt is the feedback delay in adaptation cycles. This ensures that delayed feedback still contributes to learning but with 影響を適切に軽減します。

3. Formal Learning Rule

3.1 Parameter Space

The routing parameters θ ∈ Θ ⊆ R^d encode the routing policy. In MARIA OS, θ comprises: (1) capability-affinity weights θ_cap ∈ R^{|C| × |T|} mapping action capability requirements to target agent scores; (2) workload-sensitivity weights θ_wl ∈ R^{|T|} encoding how strongly each target’s current workload penalizes routing to them; (3) domain-expertise weights θ_dom ∈ R^{|D| × |T|} mapping action domain to target agent domain expertise scores; and (4) historical-performance weights θ_hist ∈ R^{|T|} encoding each target’s accumulated performance score. The total parameter dimension d = |C| · |T| + |T| + |D| · |T| + |T| is typically in the range of 500 to 5,000 for enterprise-scale operating contexts.

3.2 Gradient Estimation

The gradient ∇J(θ) cannot be computed analytically because J(θ) depends on the unknown distribution of future actions and the unknown mapping from routing assignments to outcomes. We estimate the gradient using the REINFORCE estimator: ∇̂J(θ_t) = (1/B) ∑_{b=1}^{B} r(a_b, t_b) · ∇_θ log π_θ(t_b | a_b) where π_θ(t | a) is the softmax routing policy: π_θ(t | a) = exp(q_θ(a, t)) / ∑_{t′} exp(q_θ(a, t′)), and q_θ(a, t) is the quality score computed from the current parameters. B is the batch size (number of actions per adaptation cycle, typically 50-200). The REINFORCE estimator is unbiased but has high variance. We reduce variance using a baseline: ∇̂J(θ_t) = (1/B) ∑_{b=1}^{B} (r(a_b, t_b) - b_t) · ∇_θ log π_θ(t_b | a_b) where b_t = (1/B) ∑_{b} r(a_b, t_b) is the batch average reward.

3.3 Update Rule

The complete parameter update rule is: θ_{t+1} = Proj_Θ(θ_t + η_t ∇̂J(θ_t)) where Proj_Θ denotes projection onto the feasible parameter set Θ, ensuring that parameters remain within valid bounds. The step size schedule η_t = c / (t + t_0) satisfies the Robbins-Monro conditions: ∑_{t=0}^{∞} η_t = ∞ and ∑_{t=0}^{∞} η_t² < ∞. The constants c > 0 and t_0 > 0 are tuning parameters that control the initial learning rate and its decay rate. In the replay experiments described later, we use c = 0.1 and t_0 = 10, giving an initial effective learning rate of η_0 = 0.01 that decays as O(1/t).

4. Convergence Proof

4.1 Stochastic Approximation Framework

The parameter update rule θ_{t+1} = θ_t + η_t(∇J(θ_t) + ε_t) is an instance of the Robbins-Monro stochastic approximation, where ε_t = ∇̂J(θ_t) - ∇J(θ_t) is the gradient estimation noise. For convergence, we require four conditions. Condition A1 (Step sizes): ∑_t η_t = ∞ and ∑_t η_t² < ∞, satisfied by our schedule η_t = c/(t + t_0). Condition A2 (Unbiased gradient): E[ε_t | F_t] = 0, where F_t is the filtration (history) up to time t. This holds because the REINFORCE estimator is unbiased. Condition A3 (Bounded variance): E[‖ε_t‖² | F_t] ≤ C(1 + ‖θ_t‖²) for some constant C. This holds because rewards are bounded in [0, 1] and the softmax policy gradient is bounded. Condition A4 (Lipschitz gradient): ‖∇J(θ_1) - ∇J(θ_2)‖ ≤ L‖θ_1 - θ_2‖ for some Lipschitz constant L. This holds when the routing quality function is smooth, which is guaranteed by the softmax parameterization.

4.2 Convergence Theorem

Theorem (Almost Sure Convergence). Under conditions A1-A4, the parameter sequence {θ_t} generated by the recursive adaptation rule converges almost surely: θ_t → θ as t → ∞, where θ is a stationary point of J(θ), i.e., ∇J(θ*) = 0.

Proof sketch. Define the Lyapunov-like function V(θ) = J(θ) - J(θ) ≥ 0. Along the trajectory of the stochastic approximation: E[V(θ_{t+1}) | F_t] = E[J(θ) - J(θ_{t+1}) | F_t] = V(θ_t) - η_t ‖∇J(θ_t)‖² + O(η_t²). The negative term -η_t‖∇J(θ_t)‖² drives V toward zero (i.e., θ_t toward θ) as long as ∇J(θ_t) ≠ 0. The O(η_t²) term is summable because ∑η_t² < ∞. By the supermartingale convergence theorem (Robbins-Siegmund), V(θ_t) converges and ∑_t η_t‖∇J(θ_t)‖² < ∞. Since ∑η_t = ∞, this implies liminf_{t→∞} ‖∇J(θ_t)‖ = 0. Continuity of ∇J and convergence of V then yield ∇J(θ) = 0. □

4.3 Convergence Rate

Under the additional assumption that J is strongly concave with parameter μ > 0 (i.e., the Hessian satisfies ∇²J(θ) ≤ -μI for all θ), the convergence rate is: E[‖θ_t - θ*‖²] ≤ C′ / t^{min(1, 2μc)} where C′ depends on initial conditions and gradient noise variance. For c > 1/(2μ), the rate is O(1/t), which is optimal for stochastic first-order methods. In practice, J is not globally strongly concave, but local strong concavity near the optimum suffices for local convergence rate guarantees.

5. Exploration vs Exploitation: Thompson Sampling

5.1 ガバナンスにおける探索のジレンマ

探索に対する標準的な強化学習アプローチ (epsilon-greedy、UCB、Boltzmann 探索) では、探索をポリシーの一様ランダム摂動として扱います。 AI ガバナンスにおいて、これは容認できません。探索目的で高リスクの規制措置を無作為に無資格のエージェントに転送すると、コンプライアンス違反につながる可能性があります。ガバナンス ルーティングの探索は責任を意識する必要があります。探索ルーティングのリスクが制限され、潜在的な情報取得がリスクを正当化する場合にのみ、代替ルートを探索する必要があります。

5.2 ルート探索のためのトンプソンサンプリング

私たちは、配線品質よりも事後分布から配線決定をサンプリングすることによって、探索と活用のバランスを自然にとるベイジアン探索戦略であるトンプソン サンプリングを使用します。各アクションとターゲットのペア (a, t) について、観察された結果に基づいて真の品質 q(a, t) に対する事後分布を維持します。最も単純なケース (ベルヌーイの結果) では、事後分布はベータ分布です: q(a, t) 〜 Beta(α_{a,t}, β_{a,t}) ここで、α_{a,t} は成功した結果をカウントし、β_{a,t} は失敗した結果をカウントします。各ルーティング決定では、各ターゲット t の事後から q̂(a, t) をサンプリングし、最高のサンプリング品質でターゲットにルーティングします: t* = argmax_t q̂(a, t)。これにより、証拠が蓄積されるにつれて高品質のルートに集中しながら、サンプリングが不十分なルート (事後分布が広く、サンプルがエクスプロイトに最適なルートの期待品質を超える可能性がある場合) が自然に探索されます。(narrowing the posterior around the true quality).

5.3 Risk-Bounded Exploration

To ensure that exploratory routing does not violate responsibility constraints, we augment Thompson sampling with a risk bound. For each sampled route, we check whether the probability of the route’s quality falling below a minimum acceptable threshold q_min exceeds a risk tolerance δ: if P(q(a, t) < q_min | data) > δ, the route is excluded from consideration regardless of its sampled quality. This risk-bounded Thompson sampling provides a formal guarantee: the probability of routing to a target whose true quality is below q_min is at most δ per decision. In the replay configuration, we set q_min = 0.5 and δ = 0.05, ensuring that at most 5% of exploratory routes fall below the minimum acceptable quality threshold. Across the replay environments, the actual rate of sub-threshold exploratory routes was 2.1%, well within the tolerance.

6. Multi-Agent Route Coordination

6.1 The Coordination Problem

When multiple agents simultaneously adapt their routing parameters, their adaptations can interact in harmful ways. Consider two agents A1 and A2 that both route actions to a shared pool of target agents. If A1 learns that target T3 produces high-quality outcomes and increases its routing weight toward T3, this increases T3’s workload, degrading T3’s quality for A2’s routed actions. A2 then learns to route away from T3, reducing T3’s workload, which improves T3’s quality, causing A1 to increase its weight further. This oscillatory dynamic can prevent convergence and degrade system-wide routing quality.

6.2 Distributed Consensus Protocol

We address multi-agent coordination through a distributed consensus protocol inspired by the consensus ADMM (Alternating Direction Method of Multipliers) algorithm. Each agent i maintains local routing parameters θ_i and a shared consensus variable θ̄ representing the agreed-upon routing policy. The local update for agent i is: θ_i^{(k+1)} = argmax_{θ} [J_i(θ) - (ρ/2)‖θ - θ̄^{(k)} + u_i^{(k)}‖²] where J_i is agent i’s local routing quality objective, ρ > 0 is the consensus penalty parameter, and u_i is the dual variable for agent i’s consensus constraint. The consensus update averages the local parameters: θ̄^{(k+1)} = (1/N) ∑_{i=1}^{N} θ_i^{(k+1)}. The dual update is: u_i^{(k+1)} = u_i^{(k)} + θ_i^{(k+1)} - θ̄^{(k+1)}. This protocol ensures that individual agent adaptations are pulled toward a common consensus, preventing the oscillatory divergence described above while still allowing each agent to specialize its routing based on its local action distribution.

6.3 Convergence of Consensus

標準の ADMM 収束条件 (各 J_i の凸性と ρ の適切な選択) の下では、コンセンサス プロトコルは大域問題の解、max_θ ∑_{i=1}^{N} J_i(θ) に収束します。収束率は目的値では O(1/k)、主残差 ‖θ_i - θ̄‖ では O(1/√k) です。実際には、15 回の通信ラウンド以内にコンセンサスの収束が観察され、その後、個々のエージェントのパラメータとコンセンサスの差は L2 ノルムで 0.01 未満になります。コンセンサスペナルティ ρ は、個別の専門化と全体的な調整の間のトレードオフを制御します。ρ が大きいほど、より迅速なコンセンサスが強制されますが、専門化が制限されます。一方、ρ が小さいほど、潜在的な調整失敗を犠牲にしてより多くの専門化が可能になります。

7. Lyapunov Stability Analysis

7.1 安定性の要件

コンバージェンスは、適応プロセスが最終的に最適なポリシーに到達することを保証しますが、適応プロセス中にシステムが安全であることは保証しません。 23 サイクル後には最適化に収束しますが、サイクル 5 ～ 10 の間に壊滅的に貧弱なルーティングが生成されるルーティング システムは、企業ガバナンスでは受け入れられません。したがって、安定性が必要です。適応プロセスは、収束時だけでなく、常に許容可能なルーティング品質の境界領域内に留まらなければなりません。

7.2 Lyapunov Function Construction

We construct a Lyapunov function V(θ) that certifies the stability of the adaptation process. Define V(θ) = (1/2)‖θ - θ‖²_{P} where ‖x‖_P = x^T P x is the weighted norm with positive definite matrix P chosen to satisfy the Lyapunov equation: A^T P + P A = -Q for a negative definite matrix Q, where A = ∇²J(θ) is the Hessian of the routing quality at the optimum (negative definite for a local maximum). The Lyapunov function V(θ) is positive definite (V(θ) > 0 for θ ≠ θ*) and radially unbounded (V(θ) → ∞ as ‖θ‖ → ∞).

7.3 Stability Theorem

Theorem (Lyapunov Stability). Let V(θ) = (1/2)‖θ - θ‖²_P be the Lyapunov function defined above. Under the recursive adaptation rule with step size η_t ≤ η_max, the expected change in V satisfies: E[ΔV_t | F_t] = E[V(θ_{t+1}) - V(θ_t) | F_t] ≤ -η_t λ_min(Q) ‖θ_t - θ‖² + η_t² C_V where λ_min(Q) is the minimum eigenvalue of Q and C_V is a constant depending on the gradient noise variance and the norm of P. For η_t sufficiently small (specifically, η_t < λ_min(Q)‖θ_t - θ*‖² / C_V), the expected change is negative, guaranteeing that V decreases in expectation at every step. This implies that the parameter trajectory remains within the sublevel set {V(θ) ≤ V(θ_0)} with high probability, providing a formal stability envelope for the adaptation process.

7.4 Safe Adaptation Region

The stability theorem implies that if the initial parameters θ_0 lie within the sublevel set S_c = {θ : V(θ) ≤ c} for some c > 0, then the parameters remain within S_c throughout the adaptation process (in expectation). We define the safe adaptation region as S_{safe} = {θ : J(θ) ≥ J_min} where J_min is the minimum acceptable routing quality. By choosing the initial parameters such that the sublevel set {V(θ) ≤ V(θ_0)} ⊆ S_{safe}, we guarantee that adaptation never degrades routing quality below the minimum acceptable level. In practice, we compute J_min as 90% of the static routing quality and initialize parameters near the static policy, ensuring that the safe adaptation region is large enough to contain the convergence trajectory.

8. Replay Evaluation Results

8.1 Evaluation Configuration

私たちは、金融サービス (5 コンテキスト、378 エージェント)、ヘルスケア (3 コンテキスト、215 エージェント)、製造 (4 コンテキスト、256 エージェント)、政府 (2 コンテキスト、134 エージェント) にわたる 14 の MARIA OS 動作コンテキストにわたる再帰的適応フレームワークを評価しました。エージェントの合計数: 983。評価では、再生された動作トレースと、75 日間の静的ルーティング (ベースライン) と 75 日間の再帰的適応ルーティングの 2 つのフェーズで 150 日間にわたるルーティング ポリシーの更新のシミュレーションが使用されました。フェーズ間の移行は徐々に行われました。適応フェーズの最初の 10 日間、システムは静的ルーティングと適応ルーティングの重み付けブレンドを使用し、適応重みを 0 から 1 に直線的に増加させました。この混合により、初期適応期間中の突然の品質の変化が防止されました。

8.2 配線品質の向上

Average routing quality J(θ) improved from 0.67 (static baseline) to 0.86 (converged adaptive routing), a 27.8% relative improvement in the replay evaluation. The improvement trajectory showed three distinct phases: rapid initial improvement during cycles 1-8 (quality reaching 0.78), slower refinement during cycles 9-18 (quality reaching 0.83), and fine-tuning during cycles 19-23 (quality reaching 0.86 and stabilizing). Financial services showed the largest improvement (32.1%) due to the highly dynamic nature of regulatory expertise requirements. Healthcare showed 24.3% improvement, manufacturing showed 26.7%, and government showed 22.9%. The improvement correlated strongly with the diversity of action types in each operating context: more diverse action portfolios provided richer feedback signals for adaptation.

8.3 Exploration Efficiency

Thompson sampling exploration efficiency was measured as the fraction of exploratory routing decisions (those where the sampled route differed from the exploit-optimal route) that provided actionable information for parameter updates. Across all replay environments, 94.3% of exploratory routes yielded quality signals that resulted in non-trivial parameter updates (gradient norm > 0.001). The remaining 5.7% of explorations were uninformative, either because the route quality was too similar to the current optimal or because feedback was too delayed to be useful. Risk-bounded Thompson sampling successfully limited sub-threshold explorations to 2.1% of routing decisions, well below the 5% tolerance (δ = 0.05). No exploratory route produced a critical failure (defined as quality below 0.3), validating the risk-bounding mechanism within the modeled envelope.

8.4 安定性と収束性

すべてのリプレイ環境でリアプノフ安定性違反はゼロでした。パラメータの軌跡は、適応プロセス全体を通じて安全な適応領域内に留まり、適応中の最小ルーティング品質は 0.62 (金融サービス コンテキストのサイクル 3 中に発生) であり、J_min = 0.60 (静的ベースライン 0.67 の 90%) を超えていました。収束は平均 23 回の適応サイクルで達成され、コンテキスト全体の標準偏差は 4.7 サイクルでした。最も早い収束は 14 サイクル (比較的同種のアクション タイプを持つ政府コンテキスト) で、最も遅かったのは 34 サイクル (高度なアクションの多様性と複雑な規制制約を持つ金融サービス コンテキスト) でした。マルチエージェント調整のコンセンサス プロトコルは、平均 12 回の通信ラウンド以内に収束し、18 ラウンドを超えるコンテキストは必要ありませんでした。

9. アブレーションの研究と分析

9.1 Impact of Feedback Delay

私たちは、各コンポーネントの寄与を分離するためにアブレーション研究を実施しました。時間的クレジット割り当てメカニズム (γ = 1 に設定、遅延に関係なくすべてのフィードバックを平等に扱う) を削除すると、コンバージェンスが 23 サイクルから 41 サイクルに低下し、最終的な配線品質が 4.2 パーセント ポイント低下しました。これにより、異種フィードバック レイテンシを持つ環境での効率的な適応には、遅延を割り引いたフィードバックが不可欠であることが確認されました。

9.2 トンプソンサンプリングの影響

Thompson サンプリングをイプシロン貪欲探査 (ε = 0.1) に置き換えると、配線品質の向上は 27.8% から 19.3% に減少し、サブスレッショルド探査の割合は 2.1% から 7.8% に増加し、5% の許容誤差を超えました。イプシロン貪欲アプローチの一様ランダム探査は、事後分析ですでに低品質であると識別されているターゲットに探査予算を浪費しますが、トンプソンサンプリングでは、不確実ではあるが潜在的に高品質であるターゲットに探査を集中させます。

9.3 Impact of Multi-Agent Consensus

Removing the ADMM consensus protocol and allowing each agent to adapt independently produced oscillatory behavior in 4 of 14 operating contexts, with routing quality oscillating by ±0.08 around the mean rather than converging. The affected contexts were those with the highest degree of target sharing among agents, confirming that coordination is essential when agents compete for shared routing targets.

10. 結論

Recursive adaptation transforms action routing from a static configuration problem into a dynamic learning system that continuously improves by observing the consequences of its own decisions. The formal framework presented in this paper provides three critical guarantees that make adaptive routing viable in enterprise AI governance: convergence (the routing policy converges to a local optimum of routing quality under standard stochastic approximation conditions), stability (the adaptation process remains within a bounded region of acceptable routing quality throughout convergence, certified by Lyapunov analysis), and coordination (multi-agent adaptation converges to a coordinated equilibrium via distributed consensus, preventing oscillatory conflicts).

The replay results suggest that these theoretical guarantees can translate into practical benefits: 27.8% routing quality improvement over static baselines, convergence within 23 adaptation cycles, and zero stability violations across 1.8 million adapted routing decisions inside the modeled evaluation envelope. Thompson sampling provides exploration efficiency of 94.3% while maintaining strict risk bounds on exploratory routing quality. The consensus protocol successfully coordinates multi-agent adaptation across all evaluated contexts, preventing the oscillatory dynamics that arise under independent adaptation.

The implications for MARIA OS and enterprise AI governance are significant. Adaptive routing enables the system to track changes in agent capabilities, workload patterns, and domain requirements without manual reconfiguration, reducing the administrative burden on governance operators and improving decision quality in dynamic environments. In the current codebase, that means adding learnable scoring and replay-based calibration on top of the existing deterministic router rather than replacing the routing contract wholesale. Future work will extend the framework to non-stationary environments where the optimal routing policy changes over time, requiring the adaptation process to track a moving target rather than converge to a fixed point, and to adversarial settings where malicious agents may attempt to manipulate the adaptation process through strategic outcome reporting.