Adaptive Workflow Intelligence: A Cognitive Architecture for Context-Driven Enterprise Automation

Sreedevi Pandiyath Viswambaran

cs.AIMar 18, 2026

Adaptive Workflow Intelligence: A Cognitive Architecture for Context-Driven Enterprise Automation

Authors: Sreedevi Pandiyath Viswambaran

Organizations: Georgia Institute of Technology

Abstract

Enterprise systems increasingly rely on automated workflows, yet many AI-driven solutions remain brittle under non-stationary conditions, evolving policies, and delayed operational feedback. While reinforcement learning and large language model (LLM) agents offer partial adaptability, they do not by themselves provide persistent reflection mechanisms or straightforward integration with policy-constrained enterprise operations. This paper introduces Adaptive Workflow Intelligence (AWI), a cognitive architecture for context-driven enterprise agents organized around a four-layer Perception-Cognition-Action-Reflection (PCAR) loop. AWI treats reflection as a mechanism for continuous policy refinement and combines hybrid reasoning with reflective memory and feedback-driven adaptation to support decision making under environmental drift and operational constraints. We evaluate AWI in a simulated enterprise decision workflow characterized by delayed outcomes and a controlled regime shift. In a drift-and-delay stress test, guardrail-constrained adaptive approaches recover more rapidly than static automation while maintaining policy compliance. Within this setting, AWI's reflective components modestly reduce behavioral oscillation and feedback variance, illustrating the stability-agility trade-off introduced by reflective policy adaptation.

Figures & tables

Figure 1: Adaptive Workflow Intelligence (AWI) — PCAR Loop

Method	PCR $\uparrow$	Audit $\uparrow$	Switch $\downarrow$	VarR $\downarrow$	Recov $\downarrow$
Static Policy	1.000 $\pm$ 0.000	0.866 $\pm$ 0.006	0.108 $\pm$ 0.004	0.043 $\pm$ 0.005	15.60 $\pm$ 19.42
BanditOnly	1.000 $\pm$ 0.000	0.866 $\pm$ 0.006	0.038 $\pm$ 0.049	0.018 $\pm$ 0.013	4.20 $\pm$ 4.31
AWI_Full	1.000 $\pm$ 0.000	0.866 $\pm$ 0.006	0.031 $\pm$ 0.052	0.017 $\pm$ 0.012	4.40 $\pm$ 4.23
AWI_NoReflection	1.000 $\pm$ 0.000	0.866 $\pm$ 0.006	0.038 $\pm$ 0.049	0.018 $\pm$ 0.013	4.20 $\pm$ 4.31
AWI_NoGuardrails	0.972 $\pm$ 0.056	0.866 $\pm$ 0.006	0.015 $\pm$ 0.030	0.104 $\pm$ 0.186	15.40 $\pm$ 21.29
AWI_FrozenPolicy	1.000 $\pm$ 0.000	0.866 $\pm$ 0.006	0.000 $\pm$ 0.000	0.010 $\pm$ 0.003	1.80 $\pm$ 2.18

TABLE I: Minimal evaluation under drift and delayed outcomes. Results are reported as mean

\pm

95% confidence interval over 5 random seeds.

Cognitive Architectures for AI Agents

Cognitive architectures for AI agents organize perception, memory, goals, reasoning, and action into systems for persistent, adaptive behavior.

See all 86 papers

The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
Mar 25, 2026Biplab Pal, Santanu BhattacharyaAI Agent Reliability AI Agent Auditing
CARDS (Center for Real-Time Distributed Sensing and Autonomy), University of Maryland Baltimore County, Baltimore, MD, USA · Massachusetts Institute of Technology, Cambridge, MA, USA
Adaptive Multimodal Agents-Based Framework for Automatic Workflow Execution
May 27, 2026Susanna Cifani, Mario Luca Bernardi, Marta CimitileMulti-Agent Orchestration Multi-Agent Collaboration
Sapienza University of Rome Rome, Italy · Department of Engineering University of Sannio Benevento, Italy · Faculty of Jurisprudence Unitelma Sapienza University Rome, Italy
Safe and Policy-Compliant Multi-Agent Orchestration for Enterprise AI
Apr 19, 2026Vinil Pasupuleti, Shyalendar Reddy Allala, Siva Rama Krishna Varma Bayyavarapu +1Multi-Agent System Optimization Multi-Agent Coordination
International Business Machines · International Business Machines (IBM) · South Carolina, United States +6

Mar 25, 2026J/K move · Enter open · S save

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

Biplab Pal, Santanu Bhattacharya

CARDS (Center for Real-Time Distributed Sensing and Autonomy), University of Maryland Baltimore County, Baltimore, MD, USA · Massachusetts Institute of Technology, Cambridge, MA, USA

AI Agent Reliability AI Agent Auditing Human-in-the-Loop AI Markov Models

Open paper AskPDF arXiv

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.

Abstract

Cognitive Architectures for AI Agents

Explore similar work

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

Adaptive Multimodal Agents-Based Framework for Automatic Workflow Execution

Safe and Policy-Compliant Multi-Agent Orchestration for Enterprise AI