Paper
The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
Authors
Biplab Pal, Santanu Bhattacharya
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.
Metadata
Related papers
Vibe Coding XR: Accelerating AI + XR Prototyping with XR Blocks and Gemini
Ruofei Du, Benjamin Hersh, David Li, Nels Numan, Xun Qian, Yanhe Chen, Zhongy... • 2026-03-25
Comparing Developer and LLM Biases in Code Evaluation
Aditya Mittal, Ryan Shar, Zichu Wu, Shyam Agarwal, Tongshuang Wu, Chris Donah... • 2026-03-25
Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
Saahil Mathur, Ryan David Rittner, Vedant Ajit Thakur, Daniel Stuart Schiff, ... • 2026-03-25
MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
Zhuo Li, Yupeng Zhang, Pengyu Cheng, Jiajun Song, Mengyu Zhou, Hao Li, Shujie... • 2026-03-25
Anti-I2V: Safeguarding your photos from malicious image-to-video generation
Duc Vu, Anh Nguyen, Chi Tran, Anh Tran • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.24582v1</id>\n <title>The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence</title>\n <updated>2026-03-25T17:56:11Z</updated>\n <link href='https://arxiv.org/abs/2603.24582v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.24582v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>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.\n 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.\n 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.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n <published>2026-03-25T17:56:11Z</published>\n <arxiv:comment>22 pages, 5 figures, submitted to Engineering Applications of Artificial Intelligence</arxiv:comment>\n <arxiv:primary_category term='cs.AI'/>\n <author>\n <name>Biplab Pal</name>\n </author>\n <author>\n <name>Santanu Bhattacharya</name>\n </author>\n </entry>"
}