Large Language Model (LLM) agents hold promise for a flexible and scalable alternative to traditional business process automation, but struggle to reliably follow complex company policies. In this study we introduce a deterministic, transparent, and modular framework for enforcing business policy adherence in agentic workflows. Our method operates in two phases: (1) an offline buildtime stage that compiles policy documents into verifiable guard code associated with tool use, and (2) a runtime integration where these guards ensure compliance before each agent action. We demonstrate our approach on the challenging 𝜏 -bench Airlines domain, showing encouraging preliminary results in policy enforcement, and further outline key challenges for real-world deployments.

AI agents and business automation tools interacting with external web services require standardized, machine-readable information about their APIs in the form of API specifications. However, the information about APIs available online is often presented as unstructured, free-form HTML documentation, requiring external users to spend significant time manually converting it into a structured format. To address this, we introduce OASBuilder, a novel framework that transforms long and diverse API documentation pages into consistent, machine-readable API specifications. This is achieved through a carefully crafted pipeline that integrates large language models and rule-based algorithms which are guided by domain knowledge of the structure of documentation webpages. Our experiments demonstrate that OASBuilder generalizes well across hundreds of APIs, and produces valid OpenAPI specifications that encapsulate most of the information from the original documentation. OASBuilder has been successfully implemented in an enterprise environment, saving thousands of hours of manual effort and making hundreds of complex enterprise APIs accessible as tools for LLMs.

In the digital era, the widespread use of APIs is evident. However, scalable utilization of APIs poses a challenge due to structure divergence observed in online API documentation. This underscores the need for automatic tools to facilitate API consumption. A viable approach involves the conversion of documentation into an API Specification format. While previous attempts have been made using rule-based methods, these approaches encountered difficulties in generalizing across diverse documentation. In this paper we introduce SpeCrawler, a comprehensive system that utilizes large language models (LLMs) to generate OpenAPI Specifications from diverse API documentation through a carefully crafted pipeline. By creating a standardized format for numerous APIs, SpeCrawler aids in streamlining integration processes within API orchestrating systems and facilitating the incorporation of tools into LLMs. The paper explores SpeCrawler's methodology, supported by empirical evidence and case studies, demonstrating its efficacy through LLM capabilities.

We consider two complementary tasks for consuming optimization results of a given multiobjective problem by decision-makers. The underpinning in both exploratory tasks is analyzing Pareto landscapes, and we propose in both cases discrete graph-based reductions. Firstly, we introduce interactive navigation from a given suboptimal reference solution to Pareto efficient solution-points. The proposed traversal mechanism is based upon landscape improvement-transitions from the reference towards Pareto-dominating solutions in a baby-steps fashion – accepting relatively small variations in the design-space. The Efficient Frontier and the archive of Pareto suboptimal points are to be obtained by population-based multiobjective solvers, such as Evolutionary Multiobjective Algorithms. Secondly, we propose a framework for automatically recommending a preferable subset of points belonging to the Frontier that accounts for the decision-maker’s tendencies. We devise a line of action that activates one of two approaches: either recommending the top offensive team – the gain-prone subset of points, or the top defensive team – the loss-averse subset of points. We describe the entire recommendation process and formulate mixed-integer linear programs for solving its combinatorial graph-based problems.

Simulation performance may be evaluated according to multiple quality measures that are in competition and their simultaneous consideration poses a conflict. In the current study we propose a practical framework for investigating such simulation performance criteria, exploring the inherent conflicts amongst them and identifying the best available tradeoffs, based upon multiobjective Pareto optimization. This approach necessitates the rigorous derivation of performance criteria to serve as objective functions and undergo vector optimization. We demonstrate the effectiveness of our proposed approach by applying it to a specific Artificial Neural Networks (ANN) simulation, with multiple stochastic quality measures. We formulate performance criteria of this use-case, pose an optimization problem, and solve it by means of a simulation-based Pareto approach. Upon attainment of the underlying Pareto Frontier, we analyze it and prescribe preference-dependent configurations for the optimal simulation training.

Decision makers often need to take into account multiple conflicting objectives when selecting a solution for their problem. This can result in a potentially large number of candidate solutions to be considered. Visualizing a Pareto Frontier, the optimal set of solutions to a multi-objective problem, is considered a difficult task when the problem at hand spans more than three objective functions. We introduce a novel visual-interactive approach to facilitate coping with multi-objective problems. We propose a characterization of the Pareto Frontier data and the tasks decision makers face as they reach their decisions. Following a comprehensive analysis of the design alternatives, we show how a semantically-enhanced Self-Organizing Map, can be utilized to meet the identified tasks. We argue that our newly proposed design provides both consistent orientation of the 2D mapping as well as an appropriate visual representation of individual solutions. We then demonstrate its applicability with two real-world multi-objective case studies. We conclude with a preliminary empirical evaluation and a qualitative usefulness assessment.

When choosing a solution, decision makers are often required to account for multiple conflicting objectives. This is a situation that can result in a potentially huge number of candidate solutions. Despite the wide selection of multivariate visualizations that can potentially help decide between various candidates, no designated means exist to assess the effectiveness of these visualizations under different circumstances. As a first contribution in this work, we developed a method to evaluate different types of multivariate visualization. The method focuses on the visualization’s ability to facilitate a better understanding of inter-objective trade-offs as a proxy to more sensible decision making. We used the method to evaluate two existing visualization aids: Parallel-Coordinates and an adaptation of Self Organizing Maps (SOM). Both visualizations were compared with tabular data presentation. Our results show that the first visualization is more effective than a plain tabular visualization for the purpose of multi-objective decision making.

Business analysts, business architects, and solution consultants use a variety of practices and methods in their quest to understand business. The resulting work products often end up being transitioned into the formal world of software requirement definitions or as recommendations for all kinds of business activities. We describe an empirical study about the nature of these methods, diagrams, and home grown conceptual models as reflected in real practice at IBM. We identify the models as artifacts of “enterprise conceptual modeling”. We study important features of these models, suggest practical classifications and characterizations, and distinguish them from drawings. Specifically we look into context, type, methods and complexity to determine enterprise conceptual models usage. Our survey shows that the “enterprise conceptual modeling” arena presents a variety of descriptive models, each used by a relatively small group of colleagues. Together they form a spectrum that extends from “drawings” on one end to “standards” on the other.

A serious tool gap exists at the start of the software lifecy-cle, before requirements formulation. Pre-requirements analysts gather information, organize it to gain insight, en-vision possible futures, and present insights and recom-mendations to stakeholders. They typically use office tools, which give great freedom, but no help with consistency management, change propagation, or information migration to downstream tools. Despite these downsides, office tools are still favored over modeling tools, which are constrain-ing and difficult to use. We introduce the notion of flexible modeling tools, which blend the advantages of office and modeling tools. We propose a conceptual architecture for such tools, and outline research challenges to be met in realizing them. We briefly describe the Business Insight Toolkit, a prototype tool embodying this architecture.