Towards Selection as Power: Bounding Decision Authority in Autonomous Agents

• URL: http://arxiv.org/abs/2602.14606v1
• Date: Mon, 16 Feb 2026 10:10:47 GMT
• Title: Towards Selection as Power: Bounding Decision Authority in Autonomous Agents
• Authors: Jose Manuel de la Chica Rodriguez, Juan Manuel Vera Díaz,
• Abstract summary: We propose a governance architecture that separates cognition, selection, and action into distinct domains and models autonomy as a vector of sovereignty.<n>We evaluate the system across multiple regulated financial scenarios under adversarial stress targeting variance manipulation, threshold gaming, framing skew, ordering effects, and entropy probing.<n>Results show that mechanical selection governance is implementable, auditable, and prevents deterministic outcome capture while preserving reasoning capacity.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Autonomous agentic systems are increasingly deployed in regulated, high-stakes domains where decisions may be irreversible and institutionally constrained. Existing safety approaches emphasize alignment, interpretability, or action-level filtering. We argue that these mechanisms are necessary but insufficient because they do not directly govern selection power: the authority to determine which options are generated, surfaced, and framed for decision. We propose a governance architecture that separates cognition, selection, and action into distinct domains and models autonomy as a vector of sovereignty. Cognitive autonomy remains unconstrained, while selection and action autonomy are bounded through mechanically enforced primitives operating outside the agent's optimization space. The architecture integrates external candidate generation (CEFL), a governed reducer, commit-reveal entropy isolation, rationale validation, and fail-loud circuit breakers. We evaluate the system across multiple regulated financial scenarios under adversarial stress targeting variance manipulation, threshold gaming, framing skew, ordering effects, and entropy probing. Metrics quantify selection concentration, narrative diversity, governance activation cost, and failure visibility. Results show that mechanical selection governance is implementable, auditable, and prevents deterministic outcome capture while preserving reasoning capacity. Although probabilistic concentration remains, the architecture measurably bounds selection authority relative to conventional scalar pipelines. This work reframes governance as bounded causal power rather than internal intent alignment, offering a foundation for deploying autonomous agents where silent failure is unacceptable.

Related papers

• Selection as Power: Constrained Reinforcement for Bounded Decision Authority [0.0]
  We introduce incentivized selection governance, where reinforcement updates are applied to scoring and reducer parameters under externally enforced sovereignty constraints.<n>We show that learning dynamics can coexist with structural diversity when sovereignty constraints are enforced at every update step.<n>These results demonstrate that learning dynamics can coexist with structural diversity when sovereignty constraints are enforced at every update step.
  arXiv  Detail & Related papers  (2026-03-02T16:02:34Z)
• Agentic AI for Cybersecurity: A Meta-Cognitive Architecture for Governable Autonomy [0.0]
  This paper argues that cybersecurity orchestration should be reconceptualized as an agentic, multi-agent cognitive system.<n>We introduce a conceptual framework in which heterogeneous AI agents responsible for detection, hypothesis formation, contextual interpretation, explanation, and governance are coordinated through an explicit meta-cognitive judgement function.<n>Our contribution is to make this cognitive structure architecturally explicit and governable by embedding meta-cognitive judgement as a first-class system function.
  arXiv  Detail & Related papers  (2026-02-12T12:52:49Z)
• Budgeting Discretion: Theory and Evidence on Street-Level Decision-Making [10.816276884713611]
  We propose a principled model of how discretion should be rationed over time under real operational constraints.<n>We show that overrides follow a dynamic threshold rule: use discretion only when the opportunity exceeds a time and budget-dependent cutoff.<n>These results suggest that discretion can be both procedurally constrained and welfare-improving when treated as an explicitly budgeted resource.
  arXiv  Detail & Related papers  (2026-02-10T18:02:14Z)
• Agentic Uncertainty Quantification [76.94013626702183]
  We propose a unified Dual-Process Agentic UQ (AUQ) framework that transforms verbalized uncertainty into active, bi-directional control signals.<n>Our architecture comprises two complementary mechanisms: System 1 (Uncertainty-Aware Memory, UAM), which implicitly propagates verbalized confidence and semantic explanations to prevent blind decision-making; and System 2 (Uncertainty-Aware Reflection, UAR), which utilizes these explanations as rational cues to trigger targeted inference-time resolution only when necessary.
  arXiv  Detail & Related papers  (2026-01-22T07:16:26Z)
• The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution [63.61358761489141]
  Large Language Model (LLM)-based agents are widely used in real-world applications such as customer service, web navigation, and software engineering.<n>We propose a novel framework for textbfgeneral agentic attribution, designed to identify the internal factors driving agent actions regardless of the task outcome.<n>We validate our framework across a diverse suite of agentic scenarios, including standard tool use and subtle reliability risks like memory-induced bias.
  arXiv  Detail & Related papers  (2026-01-21T15:22:21Z)
• Admissibility Alignment [0.0]
  We present MAP-AI, a new control-plane system architecture for aligned decision-making under uncertainty.<n>It enforces alignment through Monte Carlo estimation of outcome distributions and admissibility-controlled policy selection.<n>We show how alignment evaluation can be integrated into decision-making itself, yielding an admissibility-controlled action selection mechanism.
  arXiv  Detail & Related papers  (2026-01-05T05:58:19Z)
• Assured Autonomy: How Operations Research Powers and Orchestrates Generative AI Systems [18.881800772626427]
  We argue generative models can be fragile in operational domains unless paired with mechanisms that provide feasibility, robustness to distribution shift, and stress testing.<n>We develop a conceptual framework for assured autonomy grounded in operations research.<n>These elements define a research agenda for assured autonomy in safety-critical, reliability-sensitive operational domains.
  arXiv  Detail & Related papers  (2025-12-30T04:24:06Z)
• Making LLMs Reliable When It Matters Most: A Five-Layer Architecture for High-Stakes Decisions [51.56484100374058]
  Current large language models (LLMs) excel in verifiable domains where outputs can be checked before action but prove less reliable for high-stakes strategic decisions with uncertain outcomes.<n>This gap, driven by mutually cognitive biases in both humans and artificial intelligence (AI) systems, threatens the defensibility of valuations and sustainability of investments in the sector.<n>This report describes a framework emerging from systematic qualitative assessment across 7 frontier-grade LLMs and 3 market-facing venture vignettes under time pressure.
  arXiv  Detail & Related papers  (2025-11-10T22:24:21Z)
• Collaborative Trustworthiness for Good Decision Making in Autonomous Systems [0.26999000177990923]
  We propose a general collaborative approach for increasing the level of trustworthiness in the environment of operation.<n>In the presence of conflicting information, aggregation becomes a major issue for trustworthy decision making based on collaborative data sharing.<n>We use Binary Decision Diagrams (BDDs) as formal models for beliefs aggregation and propagation, and formulate reduction rules to reduce the size of the BDDs.
  arXiv  Detail & Related papers  (2025-07-15T09:37:28Z)
• Toward a Theory of Agents as Tool-Use Decision-Makers [89.26889709510242]
  We argue that true autonomy requires agents to be grounded in a coherent epistemic framework that governs what they know, what they need to know, and how to acquire that knowledge efficiently.<n>We propose a unified theory that treats internal reasoning and external actions as equivalent epistemic tools, enabling agents to systematically coordinate introspection and interaction.<n>This perspective shifts the design of agents from mere action executors to knowledge-driven intelligence systems, offering a principled path toward building foundation agents capable of adaptive, efficient, and goal-directed behavior.
  arXiv  Detail & Related papers  (2025-06-01T07:52:16Z)
• The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence [57.57786477441956]
  Prior work suggests that a single refusal direction in the model's activation space determines whether an LLM refuses a request.<n>We propose a novel gradient-based approach to representation engineering and use it to identify refusal directions.<n>We show that refusal mechanisms in LLMs are governed by complex spatial structures and identify functionally independent directions.
  arXiv  Detail & Related papers  (2025-02-24T18:52:59Z)
• Conformal Decision Theory: Safe Autonomous Decisions from Imperfect Predictions [80.34972679938483]
  We introduce Conformal Decision Theory, a framework for producing safe autonomous decisions despite imperfect machine learning predictions. Decisions produced by our algorithms are safe in the sense that they come with provable statistical guarantees of having low risk. Experiments demonstrate the utility of our approach in robot motion planning around humans, automated stock trading, and robot manufacturing.
  arXiv  Detail & Related papers  (2023-10-09T17:59:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.