Selected Publications

More than 40 peer-reviewed publications across AI, NLP, cognitive science, and robotics venues, organized around one question: can AI reasoning be trusted — and how do we establish it? Below is a selection; the complete record — including workshop papers, preprints, and earlier work — is on Google Scholar.

2026

Where Norms and References Collide: Evaluating LLMs on Normative Reasoning
Mitchell Abrams, Kaveh Eskandari Miandoab, Felix Gervits, Vasanth Sarathy, and Matthias Scheutz
AAAI · oral
IntelliProof: An Argumentation Network-based Conversational Helper for Organized Reflection
Kaveh Eskandari Miandoab, Katharine Kowalyshyn, Kabir Pamnani, Anesu Gavhera, Vasanth Sarathy, and Matthias Scheutz
AAAI (demo track)
CogSLLaM: Cognitive Security for Large Language Models
Janine Mator, Chelsea Johnson, Vasanth Sarathy, Erin Roper, Antonio Piazza, Ethan Irby, and Kimberly Ferguson-Walter
AAAI-SS — AAAI Symposium Series (symposium) · oral
State-Wise Constrained Policy Shaping: Runtime Behavior Steering for Safe Reinforcement Learning
Thomas Howell, Phi Bui, Robert McPherson, and Vasanth Sarathy
AAAI-W — AAAI Workshop on AI Governance (AIGOV) (workshop) · oral

2025

Tools in the Loop: Quantifying Uncertainty of LLM Question Answering Systems That Use Tools
Panagiotis Lymperopoulos and Vasanth Sarathy
AAMAS (extended abstract)
On Evaluating LLM Integration into Robotic Architectures
Vasanth Sarathy, Marlow Fawn, Matthew McWilliams, Matthias Scheutz, and Bradley Oosterveld
TIST — ACM Transactions on Intelligent Systems and Technology (journal)

2024

"Let's Argue Both Sides": Argument Generation Can Force Small Models to Utilize Previously Inaccessible Reasoning Capabilities
Kaveh Eskandari Miandoab and Vasanth Sarathy
EMNLP-W — EMNLP Workshop on Customizable NLP (workshop)
Large Language Models Know What To Say But Not When To Speak
Muhammad Umair, Vasanth Sarathy, and Jan P. de Ruiter
EMNLP — Findings of EMNLP
Towards Human-Robot Co-Creative Collaboration Through Interactive Task Dialogue
Helen Long, Jingwen Feng, Emma Bethel, Vasanth Sarathy, Elaine Short, and Matthias Scheutz
ICSR · oral
Using Puzzle Video Games to Study Cognitive Processes in Human Insight and Creative Problem-Solving
Vasanth Sarathy, Nicholas Rabb, Daniel Kasenberg, and Matthias Scheutz
CogSci
Recognizing Value Resonance with Resonance-Tuned RoBERTa
Noam Benkler, Scott Friedman, Pavan Kantharaju, Matthew McLure, Drisana Mosaphir, Vasanth Sarathy, and Sonja Schmer-Galunder
COLING — LREC-COLING
Analogical Reasoning Within a Conceptual Hyperspace
Howard Goldowsky and Vasanth Sarathy
IJCAI-W — IJCAI Workshop on Analogical Abstraction (workshop) · oral
LgTS: Dynamic Task Sampling Using LLM-Generated Sub-Goals for Reinforcement Learning Agents
Yash Shukla, Wenchang Gao, Vasanth Sarathy, Alvaro Velasquez, Robert Wright, and Jivko Sinapov
AAMAS · oral

2023

Fostering Online Civil Sanctuaries with Theory-Informed Automated Content Moderation
Vasanth Sarathy, Sonja Schmer-Galunder, Dan Thomsen, Laurel Bobrow, and Richard Freedman
IC2S2
Mapping a Plurality of Explanations with NLP: A Case Study of Mothers and Health Workers in India
Scott Friedman, Sonja Schmer-Galunder, Vasanth Sarathy, Ruta Wheelock, Matthew McLure, Drisana Mosaphir, Robert P. Goldman, Noam Benkler, Pavan Kantharaju, Micah Goldwater, and Cristine Legare
CogSci · oral

2022

Cultural Value Resonance in Folktales: A Transformer-Based Analysis with the World Value Corpus
Noam Benkler, Scott Friedman, Sonja Schmer-Galunder, Drisana Mosaphir, Vasanth Sarathy, Pavan Kantharaju, Matthew McLure, and Robert P. Goldman
SBP-BRiMS · oral
A Neuro-Symbolic Cognitive System for Intuitive Argumentation
Vasanth Sarathy, Mark Burstein, Scott Friedman, Robert Bobrow, and Ugur Kuter
ACS — Advances in Cognitive Systems (ACS) · oral
Portals and Spaces: An Egocentric Knowledge Representation for Reasoning about Actions
Christopher Geib, Jeffrey Rye, and Vasanth Sarathy
ACS — Advances in Cognitive Systems (ACS)
BIPLEX: Creative Problem-Solving by Planning for Experimentation
Vasanth Sarathy and Matthias Scheutz
ICCC · oral
RAPid-Learn: A Framework for Learning to Recover for Handling Novelties in Open-World Environments
Shivam Goel, Yash Shukla, Vasanth Sarathy, Matthias Scheutz, and Jivko Sinapov
ICDL — IEEE ICDL · oral

2021

From Unstructured Text to Causal Knowledge Graphs: A Transformer-Based Approach
Scott Friedman, Ian Magnusson, Vasanth Sarathy, and Sonja Schmer-Galunder
ACS — Advances in Cognitive Systems (ACS) · oral
SPOTTER: Extending Symbolic Planning Operators Through Targeted Reinforcement Learning
Vasanth Sarathy, Daniel Kasenberg, Shivam Goel, Jivko Sinapov, and Matthias Scheutz
AAMAS · oral
A Novelty-Centric Agent Architecture for Changing Worlds
Faizan Muhammad, Vasanth Sarathy, Gyan Tatiya, Shivam Goel, Saurav Gyawali, Mateo Guaman, Jivko Sinapov, and Matthias Scheutz
AAMAS · oral

2020

Reasoning Requirements for Indirect Speech Act Interpretation
Vasanth Sarathy, Alexander Tsuetaki, Antonio Roque, and Matthias Scheutz
COLING
Developing a Corpus of Indirect Speech Act Schemas
Antonio Roque, Alexander Tsuetaki, Vasanth Sarathy, and Matthias Scheutz
LREC · oral

2019

When Exceptions Are the Norm: Exploring the Role of Consent in HRI
Vasanth Sarathy, Thomas Arnold, and Matthias Scheutz
THRI — ACM Transactions on Human-Robot Interaction (THRI) (journal)
An Overview of the DIARC Cognitive Architecture
Matthias Scheutz, Thomas Williams, Evan Krause, Bradley Oosterveld, Vasanth Sarathy, and Tyler Frasca
Springer — Cognitive Architectures, Springer (book chapter)
On Resolving Ambiguous Anaphoric Expressions in Imperative Discourse
Vasanth Sarathy and Matthias Scheutz
AAAI · oral
Towards the Engineering of Virtuous Machines
Naveen Sundar Govindarajulu, Selmer Bringsjord, Rikhiya Ghosh, and Vasanth Sarathy
AIES · spotlight
Learning Context-Sensitive Norms under Uncertainty
Vasanth Sarathy
AIES

2018

MacGyver Problems: AI Challenges for Testing Resourcefulness and Creativity
Vasanth Sarathy and Matthias Scheutz
ACS — Advances in Cognitive Systems (journal)
Real World Problem-Solving
Vasanth Sarathy
Frontiers — Frontiers in Human Neuroscience (journal)
A Logic-Based Computational Framework for Inferring Cognitive Affordances
Vasanth Sarathy and Matthias Scheutz
TCDS — IEEE Transactions on Cognitive and Developmental Systems (journal)
Quasi-Dilemmas for Artificial Moral Agents
Daniel Kasenberg, Vasanth Sarathy, Thomas Arnold, Matthias Scheutz, and Thomas Williams
ICRES · oral
Knowledge Acquisition in the Cockpit Using One-Shot Learning
Evana Gizzi, Lisa Le Vie, Matthias Scheutz, Vasanth Sarathy, and Jivko Sinapov
NAECON — IEEE NAECON
Learning Cognitive Affordances for Objects from Natural Language Instruction
Vasanth Sarathy, Bradley Oosterveld, Evan Krause, and Matthias Scheutz
ACS — Advances in Cognitive Systems (ACS) · oral

2017

Learning Behavioral Norms in Uncertain and Changing Contexts
Vasanth Sarathy, Matthias Scheutz, and Bertram Malle
CogInfoCom — IEEE CogInfoCom · oral
Mental Representations and Computational Modeling of Context-Specific Human Norm Systems
Vasanth Sarathy, Matthias Scheutz, Joseph Austerweil, Yoed Kenett, Mowafak Allaham, and Bertram Malle
CogSci · Outstanding Student Paper · oral

2016

Beyond Grasping: Perceiving Affordances Across Various Stages of Cognitive Development
Vasanth Sarathy and Matthias Scheutz
ICDL — IEEE ICDL-EpiRob · oral
Cognitive Affordance Representations in Uncertain Logic
Vasanth Sarathy and Matthias Scheutz
KR · spotlight

Patent

Natural Language Processing for Bias Identification
Vasanth Sarathy, Scott Friedman, and Sara Friedman
U.S. Patent 12,493,751 B2, issued December 2025