authority allocation and arbitration

This work addresses the absence of a unified conceptual framework for describing the autonomy of AI agents and the allocation of decision-making authority in contemporary CI/CD pipelines. It introduces the notion of “authority transfer” to systematically delineate the boundaries of agent autonomy, distinguishing between decision rights in the data plane and the control plane, and identifies governance of the control plane as a critical research direction. Through architectural abstraction, pattern identification, and governance mechanism design—supported by prototype implementation and analysis of industrial platforms—the study reveals three prevalent patterns: constrained autonomy, externally dominated governance, and delayed evaluation. These findings establish a theoretical foundation and outline a research agenda for developing safe, controllable, and highly autonomous CI/CD systems.

This work addresses a critical gap in current AI systems, which often conflate technical capability with operational authority, resulting in inadequate governance of authorized autonomy. The paper proposes a structured governance framework that systematically distinguishes between an AI system’s Autonomous Capability Level (ACL) and its Authorized Autonomy Level (AAL). By integrating risk exposure, action reversibility, and accountability, the framework introduces a dynamic authorization mechanism that decouples capability from permission. Validated in enterprise-grade data engineering agents, the approach enables high-capability systems to be safely constrained to lower authorization levels aligned with organizational risk tolerance. Through layered autonomy modeling and risk-aware decision protocols, the framework ensures that AI autonomy remains both effective and responsibly governed.

How to rigorously define the autonomy level of AI agents while balancing innovation potential and risk mitigation? This paper proposes the first systematic, quantifiable five-level autonomy framework, explicitly treating autonomy as a design dimension orthogonal to capability and environment, and delineating control boundaries based on user roles (from operator to observer). It introduces the novel concept of an “AI Autonomy Certificate” to enable tiered governance for both single and multi-agent systems, and establishes a new evaluation paradigm centered on human–agent interaction modalities. Integrating human–agent modeling, hierarchical design principles, governance architecture, and behavioral norms, the framework yields a calibrated, verifiable, and implementable methodology for autonomy assessment. It provides a technical pathway for developing safe, controllable AI agents and delivers an auditable certification basis for regulatory oversight.

Control authority allocation and transfer in shared autonomous systems lack theoretical foundations. Method: This paper proposes a game-theoretic dynamic takeover mechanism, modeling human–machine collaboration as a stochastic dynamic game with uncertain human intent. It uniquely embeds control authority directly into system dynamics and formulates a Nash equilibrium strategy framework. To resolve the tension between solvability and intent flexibility under partially misaligned objectives, we introduce a novel dual-matrix potential game reformulation. Efficient cooperative strategies are generated via closed-form linear-quadratic recursion, saddle-point value function computation, and potential game transformation. Results: Evaluated on vehicle trajectory tracking, the approach demonstrates adaptive takeover capability across straight and curved road segments. Quantitative analysis reveals an inherent trade-off between human adaptability and automation efficiency.

Existing requirements engineering approaches fail to explicitly define the scope of delegated decision-making, authorization hierarchies, oversight mechanisms, and control-relinquishment protocols in AI agent systems, often leaving critical requirements implicit in prompts or runtime policies. This work proposes the first requirements engineering framework tailored for autonomous agents, introducing the novel concept of “delegation autonomy boundaries” and modeling authority as a hierarchical structure. The framework specifies delegation behavior across six dimensions—purpose, authority, information, coordination, assurance, and evolution—through two complementary artifacts: Agent Justification Records (AJRs) and Agent Delegation Policies (ADPs). Empirical validation in hospital discharge coordination and automated code review scenarios demonstrates the framework’s effectiveness in enabling clear definition and management of delegation boundaries for both safety-critical and routine tasks.

This work addresses the challenge of implementing continuous, effective, and self-enforcing participatory governance over deployed AI agents to prevent behavioral drift from human interests. It proposes a mechanism-design-based governance framework that uniquely leverages computational resources as a core governance instrument. By introducing a dedicated governance currency and market mechanisms, the framework enables empirically verified human stakeholders to express preferences through sequential games. These preferences are aggregated via a dual-threshold rule into a binary authorization signal, which is then mapped to signed computational permits bounded by a safety cap, thereby enabling hardware-level self-execution of decisions. The framework formally characterizes the class of governable agents, identifies “agent manipulation of voters” as a critical vulnerability, and establishes a new paradigm for “safe AI.”

This work addresses the challenge of dynamically, efficiently, and governably allocating tasks between humans and machines beyond static binary divisions. It proposes the HAAS framework, which integrates a rule-driven expert system with a contextual multi-armed bandit learner, leveraging a five-dimensional cognitive model and a five-level autonomy spectrum to enable adaptive task allocation in software engineering and manufacturing domains. Innovatively treating governance as a tunable design parameter, the study finds that strong governance simultaneously enhances performance and mitigates fatigue in manufacturing, whereas moderate governance becomes increasingly advantageous with accumulated experience. The research also uncovers a workload buffering effect and establishes a cross-domain, reproducible benchmark platform, offering organizations an auditable and comparable environment for simulating human–machine collaboration strategies.

This study addresses the challenge of deploying agentic AI in regulated environments, where existing approaches lack a systematic design framework that jointly accounts for autonomy and agency, often failing to balance compliance, auditability, and error correction. The work introduces the first unified model of these two dimensions, defining a two-dimensional hierarchical design space with five operational levels each. It proposes six architectural strategies—checkpoints, escalation mechanisms, multi-agent delegation, tool provisioning, tool sandboxing, and write staging—to enable flexible system configuration under real-world regulatory constraints. Validated through public-sector case studies, the framework establishes a shared terminology and actionable design guidelines, facilitating interpretable, controllable, and compliant AI deployment amid evolving model capabilities and tool fidelity.

This work addresses the limitations of existing human-in-the-loop (HITL) mechanisms in intelligent agent workflows, which are often tightly coupled with application logic, resulting in poor reusability, weak consistency, and limited scalability. To overcome these challenges, the paper proposes a decoupled HITL system architecture that abstracts human oversight into an independent component. By introducing explicit interfaces and a structured execution model, the approach cleanly separates human–machine interaction from business logic. Furthermore, it introduces a novel four-dimensional framework—comprising intervention conditions, role resolution, interaction semantics, and communication channels—to enable context-aware, controllable human intervention. This design achieves, for the first time, protocol-level reusability of HITL mechanisms, supporting consistent and scalable autonomy governance in multi-agent environments and laying a foundational infrastructure for system-level human–agent collaboration.

This work addresses the challenge of effectively translating social preferences into resource allocation objectives within multi-agent control systems to fulfill ethical and socially responsible missions. By aggregating individual preferences into a welfare-oriented control objective, the study unifies this approach across three major control paradigms: online feedback optimization, Markov decision process control, and model predictive control. It presents the first systematic framework that embeds social welfare principles directly into the control design pipeline, integrating preference aggregation with formal verification mechanisms to yield a certifiably compliant control architecture. This framework offers a novel pathway for automated resource allocation systems that simultaneously ensures fairness, efficiency, and interpretability.