I am a neurosymbolic AI researcher specializing in cognitive architectures and expert systems, with an interest in combining symbolic reasoning with machine learning to improve the accuracy, explainability, and adaptability of AI in physical and digital environments.
My research develops human-centered AI for decision-making, analytics, and intelligent operations. I investigate symbolic reasoning in cognitive architectures and their integration with neural models to build personalized cyber-physical AI systems. My work spans large language models for predictive maintenance, autonomous agents for product prototyping, and robotics for automated operations.
Currently, I am a tenure-track Assistant Professor of AI and Information Sciences and Technology at School of Business Administration, Penn State Harrisburg. I obtained my Ph.D. in Informatics from the College of Information Sciences and Technology at Penn State University Park, advised by Frank Ritter. Before that, I received an M.Sc. in Instructional Technology and Learning Sciences from Utah State University, where I studied agent-based modeling and connected learning with Hillary Swanson, Uri Wilensky, and Bruce Sherin.
Recent news
Aug 2026: Poster Decode the Mind of the Machine, with Aritra Bandyopadhyay, Alessandro Oltramari, Jonathan Francis, and Frank Ritter, was accepted for presentation at ACM HCOMP 2026 (extended abstract available soon) & Invited as a reviewer for Journal of Cognitive Engineering and Decision Making.
May–Aug 2026: Obtained Ph.D. in Informatics at Penn State and started tenure-track Assistant Professor of AI and Information Sciences and Technology at Penn State Harrisburg, with a faculty co-hire in the Institute for Computational and Data Sciences (ICDS), and an Affiliate Assistant Professor of AI and IST in the College of Information Sciences and Technology at Penn State.
Selected publications
- CogDriver: The Longest-Running Autonomous Driving Cognitive Model Exhibits Human Factors.
Christian Wasta, Siyu Wu, Frank E. Ritter.
AHFE 2025, Cognitive Computing and Internet of Things
🏆 Best student paper
paper - VSM-ACTR 2: A Human-Like Decision Making Model with Metacognition for Manufacturing Solutions.
Siyu Wu, Alessandro Oltramari, Frank E. Ritter.
Journal of Computational and Mathematical Organization Theory 2025
paper - Cognitive LLMs: Toward Human-Like Artificial Intelligence by Integrating Cognitive Architectures and Large Language Models for Manufacturing Decision-making.
Siyu Wu, Alessandro Oltramari, Jonathan Francis, C. Lee Giles, Frank E. Ritter.
Journal of Neurosymbolic AI 2025
paper - LLM-ACTR: from Cognitive Models to LLMs in Manufacturing Solutions.
Siyu Wu, Alessandro Oltramari, Jonathan Francis, C. Lee Giles, Frank E. Ritter.
AAAI-MAKE 2025 Oral
paper | slides - Neurosymbolic Cognitive Methods for Enhancing Foundation Model-based Reasoning.
Kaushik Roy, Siyu Wu, Alessandro Oltramari.
Handbook on Neurosymbolic AI and Knowledge Graphs 2025
book chapter - VSM-ACT-R: Toward Using Cognitive Architecture For Manufacturing Solutions.
Siyu Wu, Alessandro Oltramari, Frank Ritter.
SBP-BRIMS 2024 Oral
🏆 Best student paper
paper | repo - Comparing LLMs for Prompt-Enhanced ACT-R and Soar Model Development: A Case Study in Cognitive Simulation
Siyu Wu, Rodrigo F. Souza, Frank Ritter, Walter Lima Jr.
AAAI Symposia 2023 Oral
paper | repo | slides - Long Road Ahead: Lessons Learned from the (soon to be) Longest Running Cognitive Model
Siyu Wu, Amir Bagherzadeh, Frank Ritter, Farnaz Tehranchi.
ICCM 2023 Oral
paper | repo | slides | simulation
Selected awards & fellowships
- Future Leader in Responsible Data Science & AI, UMichigan Institute for Data Science, 2024.
- Merit based scholarship, SBP‑BRiMS, Carnegie Mellon University, 2023 -2025.
- Robert Graham Endowed Fellowship for outstanding graduate students, PSU, 2023.
- Graduate Enhancement Award for academic excellence, Utah State University, 2022.
Work
- 2025 ML/AI intern at Bell labs, Nokia advised by Dan Kushnir.
- 2024 Neurosymbolic AI intern at Bosch Center for AI advised by Alessandro Oltramari, collaborated with Cory Henson, and Jonathan Francis .
performance review | slides - 2021 Instrutional Tech intern at Brex.
portfolio
Patents
-
System and Method for a Cognitive Architecture Utilized in Manufacturing.
Siyu Wu, and Alessandro Oltramari
Pending, Bosch LLC, 2024. -
HARP: Human-like Robot Adaptation through Remediation and Memory Driven Planning.
Dan Kushnir, and Siyu Wu
Unissued patent application , Bell labs, Nokia, 2025.
Selected talks
- HARP: Human‑like robot adaptation through remediation and memory driven planning, Statistics and Data Science Lab, Bell Labs Solutions Research, Aug 2025.
- From Cognitive Models to LLMs in Decision-making, 2025 Soar Workshop, Center for Integrated Cognition, UMichigan.
- 2024 Annual Ethical AI symposium, Michigan institute for data & AI in society, UMichigan.
Talk sketch| In proceedings - LLAMA-ACT-R, a Neuro-Symbolic Architecture (ACT-R) for LLM Decision Making, 2024 Soar Workshop, Center for Integrated Cognition, UMichigan.
slides
Grants
- Cognitive Multi‑Agent Decision Support: Investigating users’ understanding of decision support in the context of neurosymbolic integration using cognitive architectures, Co-PI, Social Science Research Institute (SSRI) seed grant, PSU.
Teaching
- IST557 Data Mining, TA, Fall 2025 & Fall 2024, fundamental for MS and PhD in AI & DS tracks
- IST510 Computational Informatics, TA, Spring 2025, fundamental for Informatics PhD
(Last updated: Apr 2026)