Knowledge and Reasoning
For AI to be useful, it needs to understand what’s being asked of it, and to know how to respond. At IBM Research, we’re working on systems to help AI better reason with the tasks it’s presented, such as understanding context and analogies, comprehension, and planning through scenarios.
Our work
How close are we to real AI reasoning?
Q & APeter HessAI, you have a lot of explaining to do
ReleaseDinesh Garg, Parag Singla, Dinesh Khandelwal, Shourya Aggarwal, Divyanshu Mandowara, and Vishwajeet Agrawal5 minute readIBM, MIT and Harvard release “Common Sense AI” dataset at ICML 2021
ReleaseDan Gutfreund, Abhishek Bhandwaldar, and Chuang Gan6 minute readIBM’s new AI outperforms competition in table entry search with question-answering
ReleaseAlfio Gliozzo, Michael Glass, and Mustafa Canim7 minute readGetting AI to reason: using neuro-symbolic AI for knowledge-based question answering
ResearchSalim Roukos, Alexander Gray, and Pavan Kapanipathi7 minute readDualTKB: A Dual Learning Bridge between Text and Knowledge Base
ResearchPierre Dognin6 minute read
Publications
A Generalist Hanabi Agent
- Arjun Sudhakar
- Hadi Nekoei
- et al.
- 2025
- ICLR 2025
Comparative Study of Open-source LLMs for text classification and knowledge extraction in the Material Discovery Domain
- Viviane T. Silva
- Anaximandro Souza
- et al.
- 2025
- ACS Spring 2025
Foundation models for materials discovery – current state and future directions
- Edward Pyzer-knapp
- Matteo Manica
- et al.
- 2025
- npj Computational Materials
Neural Reasoning Networks: Efficient interpretable neural networks with automatic textual explanations
- Steve Carrow
- Kyle Harper Erwin
- et al.
- 2025
- AAAI 2025
ULKB Logic: A HOL-based Framework for Reasoning over Knowledge Graphs
- 2025
- Science of Computer Programming
The WHY in Business Processes: Discovery of Causal Execution Dependencies
- 2025
- Künstl Intell