Operationalizing Reconstructive Authority: Runtime Construction, Dependency Resolution, and Execution Gating in Autonomous Agent Systems

Computer Science > Artificial Intelligence [Submitted on 24 Apr 2026] Operationalizing Reconstructive Authority: Runtime Construction, Dependency Resolution, and Execution Gating in Autonomous Agent Systems Marcelo Fernandez - TraslaIA Autonomous agent systems fail not only due to incorrect decisions, but due to executing decisions whose authority no longer holds at runtime. Prior work defined Reconstructive Authority (RAM) as a condition for valid execution: actions are permitted only if authority can be constructed from current state. This paper addresses enforcement at runtime: how to enforce this condition in a running system. We introduce a runtime execution model in which authority is evaluated at action time and execution is conditioned on its constructibility. This extends the execution state space beyond admit/deny with a third state, halt, representing cases where authority is undefined due to incomplete or uncertain observability. We define a concrete execution protocol including dynamic dependency resolution, authority reconstruction, and explicit decision semantics. We further introduce a Recovery Loop that integrates drift detection (IML) with execution control (ACP), allowing the system to suspend execution, acquire missing information, and re-attempt authority reconstruction. We show that this model guarantees safety -- no action is executed without constructible authority -- and conditional liveness: execution resumes when authority-defining variables become observable. This work operationalizes reconstructive authority as a runtime enforcement mechanism, providing the execution semantics required to apply RAM in real systems. Comments: Agent Governance Series, Paper P6. Companion papers on arXiv: P0 (2604.17511), P1 (2603.18829), P2 (2604.17517). P3/4 and P5 submitted concurrently (pending arXiv IDs). Zenodo: https://doi.org/10.5281/zenodo.19699460 Subjects: Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Multiagent Systems (cs.MA); Software Engineering (cs.SE); Systems and Control (eess.SY) Cite as: arXiv:2605.23935 [cs.AI]   (or arXiv:2605.23935v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2605.23935 Focus to learn more Related DOI: https://doi.org/10.5281/zenodo.19699460 Focus to learn more Submission history From: Marcelo Fernandez [view email] [v1] Fri, 24 Apr 2026 13:32:09 UTC (21 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-05 Change to browse by: cs cs.CY cs.MA cs.SE cs.SY eess eess.SY References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)