Overview

About the workshop

LLM agents increasingly collaborate and utilize external tools to address complex user requests. This emerging paradigm demands vast volumes of data for training, testing, reasoning, memory, and execution to ensure accurate and timely responses and actions. Despite the clear benefits, there remains a pressing need for a more rigorous characterization of software engineering constructs to effectively support LLM agents—particularly in areas such as orchestration, data management, knowledge augmentation, and planning. This workshop explores novel solutions to these challenges from the joint perspectives of software engineering and big data.

Aims

The goal of this workshop is to discuss original, high-quality software engineering challenges and applied solutions for agentic AI and its synergy with big data, including frameworks, data science pipelines, integrations, and representations.

Topics
Topics of interest include, but are not limited to:
  • Agentic big data frameworks and systems.
  • Requirements engineering for agentic systems.
  • Design and architecture of agentic systems.
  • Development processes and data management in agentic systems.
  • Applications and tools in the context of agentic systems.
  • Human-in-the-loop in agentic systems.
  • Prompt engineering for big data analysis in agentic systems.
  • Structured and unstructured data manipulation in agentic recommender systems.
  • Reproducibility and traceability of agentic systems development.
  • Agentic AI initiatives on data science.
  • Code generation assisted by software agents.
  • Testing and maintenance of agentic systems.
  • Verification and validation in agentic systems.
  • Domain-specific case studies in software engineering for agentic systems.
  • Self-adaptation and other self-* properties in the context of agentic AI.

Submissions

Call For Papers
We invite original research papers on Software Engineering for Agentic AI.
  • Short papers (3-4 pages, including references)
  • Regular papers (about 8 pages, including references)
Important dates
  • Submission deadline: November 3, 2025 November 10, 2025.
  • Notification of paper acceptance to authors: November 17, 2025
  • Camera-ready of accepted papers: November 23, 2025
  • Workshop / conference dates: December 8-11, 2025
Instructions

Use the submission system: https://wi-lab.com/cyberchair/2025/bigdata25/index.php

This workshop is online. Meeting link: Zoom

Schedule
Time (Macau) Title Authors
8:00 am - 8:20 am A Large-Scale Study on the Development and Issues of Multi-Agent AI Systems Daniel Liu, Krishna Upadhyay, Vinaik Chhetri, Abu Bakar Siddique, and Umar Farooq
8:20 am - 8:40 am Plan-Execute-Generate-Judge: A Self Verifying Multi Agent LLM Framework for Complex NoSQL Querying Alex Kaplunovich
8:40 am - 9:00 am An Accountability-Based Architectural Tactic for Agent Cooperation in LLM-Based Multi-Agent Systems Marco Becattini, Roberto Verdecchia, and Enrico Vicario

Contact

Organizers
  • Ivens: iportugal@uwaterloo.ca
  • Ulisses Telemaco: utelemac@uwaterloo.ca
  • Tales Paiva: tmellopaiva@uwaterloo.ca
  • Giuliano Lorenzoni: giuliano.lorenzoni@uwaterloo.ca
  • Paulo Alencar: palencar@uwaterloo.ca
  • Donald Cowan: dcowan@uwaterloo.ca