Title
From Generation to Action: The Evolution, Core Architecture, and Challenges of AI Agents

Abstract
While generative AI revolutionized content creation, it remained fundamentally reactive—responding to prompts but unable to pursue goals autonomously. Agentic AI emerged to bridge this gap—not through traditional workflow automation's predetermined processes, but through autonomous reasoning that enables AI to pursue goals independently. Unlike workflow automation which executes fixed sequences, Agentic AI can break down ambiguous objectives, make dynamic decisions, use tools adaptively, and collaborate across systems—representing a shift from scripted automation to intelligent agency. However, despite widespread prediction of Agentic AI and the proliferation of frameworks and protocols, enterprise adoption has lagged expectations. This gap stems from a fundamental tension: while agentic capabilities promise autonomous execution, the non-deterministic nature of LLMs creates reliability challenges that compound in multi-step workflows. This talk examines why implementations fail, maps the current landscape of challenges from non-deterministic behavior to cost control, and invites researchers to engage with these open problems—advancing our collective understanding of what production-ready AI agents truly require.

Biodata
Dr. Chia-Hui Chang is a full Professor at National Central University, Taiwan. Her research interests focus on the technologies and applications of artificial intelligence, including natural language understanding, information integration, Web intelligence and machine learning. Dr. Chang has published over 130 papers in refereed conferences (e.g. WWW, PAKDD, ICWSM, etc.) and journals (e.g. TKDE, and IEEE Intelligent Systems), and was elected as one of Stanford's Top 2% Scientists (Career Impact) since 2021. She has served as the convenor of the Intelligent Computing Department of the National Science and Technology Council in Taiwan since 2024. Dr. Chang is actively involved in organizing major conferences in her field, including serving as local chair for AACL 2022/ACML 2010, General Chair for ROCLING 2021 and TAAI 2020, area co-chair for ACL 2017 and NAACL 2018, and PC member for ICDE, CIKM, PAKDD, AAAI, and ICTIR, among others. She served as the President of the Taiwan Association for Artificial Intelligence (TAAI) from 2019 to 2020 and as the President of the Association for Computational Linguistics and Chinese Language Processing (ACLCLP) from 2020 to 2021.