Enterprise Representation Simplification (ERS): Reducing Representational Complexity for Enterprise AI

Terry Dorsey; Kevin Huggins

cs.AISep 30, 2026

Enterprise Representation Simplification (ERS): Reducing Representational Complexity for Enterprise AI

Authors: Terry Dorsey, Kevin Huggins

Organizations: Denodo Corporation Palo Alto, California 94301 · Harrisburg University Harrisburg, Pennsylvania 17101

Abstract

Enterprise information is represented through artifacts shaped by applications, projects, technologies, organizational boundaries, and local requirements. These structures accumulate over time, creating representational complexity that must be maintained by the enterprise and interpreted by information consumers and AI systems. This paper introduces Enterprise Representation Simplification (ERS) as reducing unnecessary representational complexity while preserving required information within a defined scope, and Enterprise Representation Complexity (ERC), a representation-neutral model for comparing complexity across representation states. ERC characterizes representational extent through four dimensions: Representation Objects, Interactions, Behaviors, and Supporting Sources. Objects, Interactions, and Behaviors form dependent categories, while Supporting Sources characterize representation exposure. ERC is defined at representation and task levels, enabling comparison and distinguishing architectural simplification from retrieval optimization. The paper develops two consequences of ERS. First, representational structures create lifecycle obligations for maintenance, governance, dependencies, change, enhancement, and operation. An economic model distinguishes recurring global representation cost, recurring task-level cost, and one-time transformation cost, enabling evaluation over a defined time horizon. Second, reductions in task-level ERC reduce the representational extent an AI system must identify, relate, and interpret. Text-to-SQL research provides evidence that reduced schema and reasoning complexity can improve reasoning accuracy. ERC is not a universal complexity, performance, or cost metric. It provides measurable architectural variables for comparing representational alternatives, transformation effects, economic outcomes, and AI reasoning performance.

Figures & tables

Measure	Current $R_{0}$	Simplified $R_{S}$
ERC	$(18,14,6,1)$	$(3,2,1,1)$
Consumer dependencies	75	28
One-time transformation	—	$150K
Global recurring obligations	$70K/year	$25K/year
Representation-dependent cost / attempt	$0.10	$0.08
Illustrative task accuracy	75.0%	79.2%

Table 1: System Metrics and Financial Comparison between

R_{0}

and

R_{S}

Measure	Enhanced $R_{E}$	Enhanced $R_{SE}$
Projected ERC	$(24,20,9,4)$	$(3,2,1,1)$
Consumer dependencies	110	28
Representation Change Surface	12	0
Phase 2 transformation cost	$120K	$80K
Global recurring obligations	$100K/year	$275K/year
Representation-dependent cost / attempt	$0.18	$0.08

Table 2: Phase 2 values

Figure 1: Illustrative recurring-cost comparison at 3.0 million annual task attempts

Figure 2: Illustrative task cost per attempt and Expected Cost per Successful Task (ECST).

Explore similar work

Jul 27, 2026cs.AI

ERUnderstand: Evaluating Vision-Language Models on Structured ER Diagrams

Entity-Relationship Diagrams (ERDs) are central to conceptual database design, yet they are typically available only as rendered images rather than machine-readable schemas, limiting AI-assisted database engineering. We introduce ERUnderstand, the first large-scale benchmark for structured understanding of ER diagrams, comprising 2,960 diagrams collected from curated educational sources, real-world schemas, and synthetically generated examples spanning diverse domains, notations, complexity levels, and Extended Entity-Relationship (EER) constructs. Each diagram is paired with a standardized machine-readable representation for fine-grained evaluation of schema elements. Evaluating state-of-the-art Vision-Language Models (VLMs), we find that while common ERD elements are recovered reliably (F1 > 0.74), performance drops sharply on weak entities (as low as 0.28 F1), multivalued attributes (0.14 F1), and N-ary relationships (0.07 F1). Reasoning-augmented models improve overall performance by 15-25% but remain sensitive to linguistic priors and increasing diagram complexity. ERUnderstand provides a standardized benchmark for evaluating multimodal understanding of conceptual database schemas. The benchmark, dataset, evaluation toolkit, and generation code are publicly available at https://github.com/salinaria/ERUnderstand.

Ali Ansari, Yasmin Mohammadi, Farnoush Nili +3

Temple University · Department of Computer and Information Sciences · Philadelphia, PA, USA

Diagrams Schema Diagnostic Benchmark Table Reasoning Datasets Entities Data Lakes+1

Ask PDF

Sep 23, 2026cs.CL

Realize What Matters: Principled Context Representation for Large-Scale Reasoning

Solving complex tasks in domains such as science, medicine, law, and finance often requires assembling interdependent information scattered across vast, heterogeneous sources far beyond model context limits. Existing approaches tackle this challenge by organizing information into more manageable representations over which models can reason, such as graphs, textual memories, and retrieval collections. These representations dictate what downstream reasoning is possible and, ultimately, whether it succeeds; yet their design and construction remain largely ad hoc. In this work, drawing on the cognitive theory of relevance realization, we propose concrete principles for designing AI systems that construct effective representations of very large contexts. We analyze existing approaches and show how their successes and failures map onto their alignment with these principles, and introduce R3Con, a harness designed to operationalize the principles more systematically. We evaluate R3Con against nine state-of-the-art baselines on two recent benchmarks of reasoning over large document corpora. On these benchmarks, R3Con substantially outperforms the strongest baseline, by

20

and

8.4

percentage points. It also enables smaller models to outperform much larger ones: R3Con with 4B and 9B models outperforms all evaluated 35B baselines, while R3Con with a 35B-A3B model outperforms Claude Code with Claude-Sonnet-5 at

3.7\times

lower cost. Our results show that context representations following our principled approach can reduce reliance on model scale, pointing toward a future of AI systems with frontier-level performance powered by smaller models. Our code is available at https://github.com/michaeltheologitis/r3con

Michael Theologitis, Dean Light, Shuyue Stella Li +3

University of Washington

Contextual Reasoning Relevance Model Context Protocol

Ask PDF

Jul 14, 2026cs.AI

Do AI Agents Know When a Task Is Simple? Toward Complexity-Aware Reasoning and Execution

Large language model (LLM) agents increasingly automate multi-step engineering and informatics workflows, yet they rarely ask how much effort a task actually requires. They often follow a maximum-context-first strategy--re-reading files and dependencies they have already seen--turning a one-line edit into a small code-base audit. We argue the missing capability is task-aware execution-scope estimation: judging a task's difficulty, the information it truly needs, and the shortest reliable path before committing budget. We formalize minimum-sufficient execution and the Agent Cognitive Redundancy Ratio (ACRR), and propose E3 (Estimate, Execute, Expand): the agent estimates an initial operating point, executes a minimum viable path, and expands scope only when verification fails. On MSE-Bench--a deterministic benchmark of 121 edits in a capability-controlled simulator--E3 matches the strongest baseline's 100% success while cutting cost by 85%, tokens by 91%, and inspected files by 92%, and further beats a strong adaptive retrieval baseline by 16%; the gains survive held-out instruction wording and essentially every cost weighting. A companion real-model harness (LLM-Case) corroborates the effect on a live gpt-4o agent editing a real open-source library, with every candidate patch graded by actually running the project's real pytest suite against a measured oracle: the over-reading is milder but real, and E3 is the leanest and fastest policy at comparable task success--its one shortfall a provider rate-limit, not a wrong edit. We frame this as a controlled probe of execution redundancy, not a measurement of any deployed agent, and position task-aware execution as a step toward engineering-grounded AI (EGAI)--agents whose effort is anchored in the engineering reality of the task. We release the framework and benchmark.

Junjie Yin, Xinyu Feng

University of Tennessee, Knoxville, TN 37996, USA · Microsoft, Redmond, WA 98052, USA

Smooth Execution Artificial Intelligence Agents Simple

Ask PDF