38 citations · 70 across the 9 of their papers we have counts for
9 papers
Applying Cognitive Design Patterns to General LLM Agents
Robert E. Wray, James R. Kirk, John E. Laird
One goal of AI (and AGI) is to identify and understand specific mechanisms and representations sufficient for general intelligence. Often, this work manifests in research focused o…
Acquiring Grounded Representations of Words with Situated Interactive Instruction
Shiwali Mohan, Aaron H. Mininger, James R. Kirk +1
We present an approach for acquiring grounded representations of words from mixed-initiative, situated interactions with a human instructor. The work focuses on the acquisition of…
Eliciting Problem Specifications via Large Language Models
Robert E. Wray, James R. Kirk, John E. Laird
Cognitive systems generally require a human to translate a problem definition into some specification that the cognitive system can use to attempt to solve the problem or perform t…
Exploiting Language Models as a Source of Knowledge for Cognitive Agents
James R. Kirk, Robert E. Wray, John E. Laird
Large language models (LLMs) provide capabilities far beyond sentence completion, including question answering, summarization, and natural-language inference. While many of these c…
Improving Knowledge Extraction from LLMs for Task Learning through Agent Analysis
James R. Kirk, Robert E. Wray, Peter Lindes +1
Large language models (LLMs) offer significant promise as a knowledge source for task learning. Prompt engineering has been shown to be effective for eliciting knowledge from an LL…
Improving Language Model Prompting in Support of Semi-autonomous Task Learning
James R. Kirk, Robert E. Wray, Peter Lindes +1
Language models (LLMs) offer potential as a source of knowledge for agents that need to acquire new task competencies within a performance environment. We describe efforts toward a…
Integrating Diverse Knowledge Sources for Online One-shot Learning of Novel Tasks
James R. Kirk, Robert E. Wray, Peter Lindes +1
Autonomous agents are able to draw on a wide variety of potential sources of task knowledge; however current approaches invariably focus on only one or two. Here we investigate the…
Language Models as a Knowledge Source for Cognitive Agents
Robert E. Wray, III, James R. Kirk +1
Language models (LMs) are sentence-completion engines trained on massive corpora. LMs have emerged as a significant breakthrough in natural-language processing, providing capabilit…
A Computational Model for Situated Task Learning with Interactive Instruction
Shiwali Mohan, James Kirk, John Laird
Learning novel tasks is a complex cognitive activity requiring the learner to acquire diverse declarative and procedural knowledge. Prior ACT-R models of acquiring task knowledge f…