Integrating Diverse Knowledge Sources for Online One-shot Learning of Novel Tasks

by CICWebsiteAdmin | Feb 6, 2023 | News, Publications

We have written a paper, now on arXiv (https://arxiv.org/abs/2208.09554), that describes how we are integrating large-language models into Interactive Task Learning (ITL), where agents can learn new tasks thru interactive instruction. The paper outlines the role of...

Understanding how agents can prompt language models for learning novel tasks

by CICWebsiteAdmin | Nov 29, 2022 | News, Publications

Kirk, J., Wray, R. E., Lindes, P., & Laird, J. E. (2022, November). Improving Language Model Prompting in Support of Semi-autonomous Task Learning. Proceedings of the 2022 Advances in Cognitive Systems Conference. Advances in Cognitive Systems, Washington,...

Introduction to Soar

by CICWebmaster | Jul 8, 2022 | Publications

Laird, J. E. (2022) Introduction to...

Incorporating Abstract Behavioral Constraints in the Performance of Agent Tasks

by CICWebmaster | Jul 6, 2022 | Publications

Wray, R. E., & Laird, J. E. (2021, July). Incorporating Abstract Behavioral Constraints in the Performance of Agent Tasks. Proceedings of the International Conference on Artificial Intelligence. International Conference on Artificial Intelligence, Las Vegas,...

Language Models as a Knowledge Source for Cognitive Agents

by CICWebmaster | Jul 6, 2022 | Publications

Wray, R. E., Kirk, J. R., & Laird, J. E. (2021). Language Models as a Knowledge Source for Cognitive Agents. Proceedings of the Ninth Annual Conference on Advances in Cognitive Systems. Ninth Annual Conference on Advances in Cognitive Systems, Virtual....