5 papers · 1 filter
SAAG: Structured Agent Assessment and Grounding
Ritvik Garimella, Vedant Khandelwal, Anvi Kohli +1
Exact-match evaluation of agent-calling obscures qualitatively different failure modes: a model may select the right function yet hallucinate argument values, or satisfy a schema w…
A Neurosymbolic Fast and Slow Architecture for Graph Coloring
Vedant Khandelwal, Vishal Pallagani, Biplav Srivastava +1
Constraint Satisfaction Problems (CSPs) present significant challenges to artificial intelligence due to their intricate constraints and the necessity for precise solutions. Existi…
Language Models Coupled with Metacognition Can Outperform Reasoning Models
Vedant Khandelwal, Francesca Rossi, Keerthiram Murugesan +4
Large language models (LLMs) excel in speed and adaptability across various reasoning tasks, but they often struggle when strict logic or constraint enforcement is required. In con…
PDDLFuse: A Tool for Generating Diverse Planning Domains
Vedant Khandelwal, Amit Sheth, Forest Agostinelli
Various real-world challenges require planning algorithms that can adapt to a broad range of domains. Traditionally, the creation of planning domains has relied heavily on human im…
A Domain-Agnostic Neurosymbolic Approach for Big Social Data Analysis: Evaluating Mental Health Sentiment on Social Media during COVID-19
Vedant Khandelwal, Manas Gaur, Ugur Kursuncu +2
Monitoring public sentiment via social media is potentially helpful during health crises such as the COVID-19 pandemic. However, traditional frequency-based, data-driven neural net…