2026-05-26原文

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

This paper introduces a runtime execution model that enforces Reconstructive Authority (RAM) in autonomous agent systems: actions are permitted only if authority can be constructed from the current state. It extends the admit/deny state space with a third state, halt, for cases where authority is undefined due to incomplete or uncertain observability. A concrete execution protocol is defined including dynamic dependency resolution, authority reconstruction, and explicit decision semantics. A Recovery Loop integrates drift detection (IML) with execution control (ACP) to suspend execution, acquire missing information, and retry authority reconstruction. The model guarantees safety (no action without constructible authority) and conditional liveness (execution resumes when authority-defining variables become observable).

Article intelligence

EngineersIntermediate

Key points

Autonomous agent systems fail not only due to incorrect decisions, but due to executing decisions whose authority no longer holds at runtime.
The model introduces a third state 'halt' to handle cases where authority is undefined due to uncertain observability.
A Recovery Loop combines drift detection and execution control to pause and retry authority reconstruction when missing information.
Formal proof shows the protocol ensures safety and conditional liveness.

Why it matters

This matters because autonomous agent systems fail not only due to incorrect decisions, but due to executing decisions whose authority no longer holds at runtime.

Technical impact

May affect model selection, inference cost, product capability, and evaluation benchmarks.

[2605.23935] Operationalizing Reconstructive Authority: Runtime Construction, Dependency Resolution, and Execution Gating in Autonomous Agent Systems

[Submitted on 24 Apr 2026]

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

View a PDF of the paper titled Operationalizing Reconstructive Authority: Runtime Construction, Dependency Resolution, and Execution Gating in Autonomous Agent Systems, by Marcelo Fernandez - TraslaIA

View PDF HTML (experimental)

Abstract: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

arXiv-issued DOI via DataCite

Related DOI:

https://doi.org/10.5281/zenodo.19699460

DOI(s) linking to related resources

Submission history

From: Marcelo Fernandez [view email] [v1] Fri, 24 Apr 2026 13:32:09 UTC (21 KB)

Full-text links:

Access Paper:

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.AI

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

Data provided by:

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

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)