The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence

• URL: http://arxiv.org/abs/2603.24582v1
• Date: Wed, 25 Mar 2026 17:56:11 GMT
• Title: The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
• Abstract summary: We show that a large workflow can appear well supported at the state level while retaining substantial blind mass over next-step decisions.<n>The framework is demonstrated on a large-scale enterprise procurement workflow.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Agentic artificial intelligence (AI) in organizations is a sequential decision problem constrained by reliability and oversight cost. When deterministic workflows are replaced by stochastic policies over actions and tool calls, the key question is not whether a next step appears plausible, but whether the resulting trajectory remains statistically supported, locally unambiguous, and economically governable. We develop a measure-theoretic Markov framework for this setting. The core quantities are state blind-spot mass B_n(tau), state-action blind mass B^SA_{pi,n}(tau), an entropy-based human-in-the-loop escalation gate, and an expected oversight-cost identity over the workflow visitation measure. We instantiate the framework on the Business Process Intelligence Challenge 2019 purchase-to-pay log (251,734 cases, 1,595,923 events, 42 distinct workflow actions) and construct a log-driven simulated agent from a chronological 80/20 split of the same process. The main empirical finding is that a large workflow can appear well supported at the state level while retaining substantial blind mass over next-step decisions: refining the operational state to include case context, economic magnitude, and actor class expands the state space from 42 to 668 and raises state-action blind mass from 0.0165 at tau=50 to 0.1253 at tau=1000. On the held-out split, m(s) = max_a pi-hat(a|s) tracks realized autonomous step accuracy within 3.4 percentage points on average. The same quantities that delimit statistically credible autonomy also determine expected oversight burden. The framework is demonstrated on a large-scale enterprise procurement workflow and is designed for direct application to engineering processes for which operational event logs are available.

Related papers

• A Data-Driven Framework for Identifying and Prioritizing RPA Opportunities in Healthcare Processes [0.808778527821476]
  An estimated 30-50% of Robotic Process Automation initiatives underperform in U.S. hospitals.<n>We propose a four- module, data-driven framework unifying these decisions.<n>The framework is a conceptual synthesis of the literature rather than an instrument calibrated on primary hospital data.
  arXiv  Detail & Related papers  (2026-09-08T17:55:28Z)
• ScaleSense: Cost-Intelligent Scaling Framework via Learned Resource Estimation in Alibaba AnalyticDB [59.708423132520515]
  Cloud-native serverless data warehouses achieve fine-grained elasticity by decoupling storage from compute.<n>Yet determining the optimal resource allocation for highly heterogeneous ad-hoc queries remains a formidable industrial challenge.<n>We propose ScaleSense, a proactive, query-level resource scaling framework.
  arXiv  Detail & Related papers  (2026-08-08T06:10:35Z)
• Civilizational Metamaterials: Engineering Coordination Under Capability Gradients and Structural Turbulence [0.0]
  We argue that governance must transition from a normative discipline to an engineering discipline.<n>We develop a formal framework, inspired by the physics of metamaterials, to make this transition quantitative and testable.
  arXiv  Detail & Related papers  (2026-05-29T18:10:00Z)
• ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox [61.862814740220806]
  $textbfComplexMCP$ is a benchmark designed to evaluate agents in rigorous conditions.<n>Built on the Model Context Protocol (MCP), $textbfComplexMCP$ provides over 300 meticulously tested tools.
  arXiv  Detail & Related papers  (2026-05-11T16:20:51Z)
• Compiled AI: Deterministic Code Generation for LLM-Based Workflow Automation [3.225273674498579]
  We study compiled AI, a paradigm in which large language models generate executable code artifacts during a compilation phase, after which execute deterministically without further model invocation.<n>Our contribution is a systems-oriented study of its application to high-stakes runtime enterprise.
  arXiv  Detail & Related papers  (2026-04-06T20:25:20Z)
• Dynamic analysis enhances issue resolution [53.50448142467294]
  DAIRA (Dynamic Analysis-enhanced Issue Resolution Agent) is an automated repair framework that embeds dynamic analysis into the agent's reasoning cycle.<n> Driven by a Test Tracing-Driven methodology, DAIRA utilizes lightweight monitors to extract critical runtime data.<n>When powered by Gemini 3 Flash Preview, DAIRA establishes a new state-of-the-art (SOTA) performance, achieving a 79.4% resolution rate on the SWE-bench Verified dataset.
  arXiv  Detail & Related papers  (2026-03-23T14:48:54Z)
• AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents [50.481033105867205]
  We introduce AgentProcessBench, the first benchmark dedicated to evaluating step-level effectiveness in realistic, tool-augmented trajectories.<n>The benchmark comprises 1,000 diverse trajectories and 8,509 human-labeled step annotations with 89.1% inter-annotator agreement.<n>It features a ternary labeling scheme to capture exploration and an error propagation rule to reduce labeling ambiguity.
  arXiv  Detail & Related papers  (2026-03-15T16:13:58Z)
• When AI Levels the Playing Field: Skill Homogenization, Asset Concentration, and Two Regimes of Inequality [0.7016842616745783]
  Generative AI compresses within-task skill differences while shifting economic value toward concentrated complementary assets.<n>We formalize this tension in a task-based model with endogenous education, employer screening, and heterogeneous firms.<n>The model yields two regimes whose boundary depends on AI's technology structure.
  arXiv  Detail & Related papers  (2026-03-05T12:41:08Z)
• ProAct: Agentic Lookahead in Interactive Environments [56.50613398808361]
  ProAct is a framework that enables agents to internalize accurate lookahead reasoning through a two-stage training paradigm.<n>We introduce Grounded LookAhead Distillation (GLAD), where the agent undergoes supervised fine-tuning on trajectories derived from environment-based search.<n>We also propose the Monte-Carlo Critic (MC-Critic), a plug-and-play auxiliary value estimator designed to enhance policy-gradient algorithms.
  arXiv  Detail & Related papers  (2026-02-05T05:45:16Z)
• Managing the Stochastic: Foundations of Learning in Neuro-Symbolic Systems for Software Engineering [0.27195102129094995]
  Current approaches to AI coding agents blur the lines between the Large Language Model and the agent itself.<n>This paper proposes setting the control boundary such that the LLM is treated as a component of the environment environment.
  arXiv  Detail & Related papers  (2025-12-18T15:28:21Z)
• Towards a Science of Scaling Agent Systems [79.64446272302287]
  We formalize a definition for agent evaluation and characterize scaling laws as the interplay between agent quantity, coordination structure, modelic, and task properties.<n>We derive a predictive model using coordination metrics, that cross-validated R2=0, enabling prediction on unseen task domains.<n>We identify three effects: (1) a tool-coordination trade-off: under fixed computational budgets, tool-heavy tasks suffer disproportionately from multi-agent overhead, and (2) a capability saturation: coordination yields diminishing or negative returns once single-agent baselines exceed 45%.
  arXiv  Detail & Related papers  (2025-12-09T06:52:21Z)
• The 4/$δ$ Bound: Designing Predictable LLM-Verifier Systems for Formal Method Guarantee [5.345468714252351]
  This work bridges the gap by developing an LLM-Verifier Convergence Theorem.<n>We model the interaction between the LLM and the verifier as a discrete-time Markov Chain.<n>We stress-tested this prediction in an extensive empirical campaign comprising more than 90,000 trials.
  arXiv  Detail & Related papers  (2025-11-30T22:19:09Z)
• AgentGuard: Runtime Verification of AI Agents [1.14219428942199]
  AgentGuard is a framework for runtime verification of Agentic AI systems.<n>It provides continuous, quantitative assurance through a new paradigm called Dynamic Probabilistic Assurance.
  arXiv  Detail & Related papers  (2025-09-28T13:08:50Z)
• OmniEAR: Benchmarking Agent Reasoning in Embodied Tasks [52.87238755666243]
  We present OmniEAR, a framework for evaluating how language models reason about physical interactions, tool usage, and multi-agent coordination in embodied tasks.<n>We model continuous physical properties and complex spatial relationships across 1,500 scenarios spanning household and industrial domains.<n>Our systematic evaluation reveals severe performance degradation when models must reason from constraints.
  arXiv  Detail & Related papers  (2025-08-07T17:54:15Z)
• Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute [61.00662702026523]
  We propose a unified Test-Time Compute scaling framework that leverages increased inference-time instead of larger models.<n>Our framework incorporates two complementary strategies: internal TTC and external TTC.<n>We demonstrate our textbf32B model achieves a 46% issue resolution rate, surpassing significantly larger models such as DeepSeek R1 671B and OpenAI o1.
  arXiv  Detail & Related papers  (2025-03-31T07:31:32Z)

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.