Language model cognitive architecture

Applied to On Devin by DivineMango 1mo ago

Language model cognitive architectures (LMCAs) are also called language model agents or scaffold agents. AutoGPT is the best-known example. It and other LMAs use a large language model and other components to create a goal-directed, agentic system. They use a large language model as a sort of "cognitive engine" performing much of the cognitive work, and incorporate other components to make the composite system goal-directed, and to fill in gaps in and extend the LLMs cognitive abilities.

Applied to On AutoGPT by Seth Herd 5mo ago

Language model cognitive architectures (LMCAs) are also called language model agents. AutoGPT is the best-known example. It and other LMAs use a large language model and other components to create a goal-directed, agentic system. They use a large language model as a sort of "cognitive engine" performing much of the cognitive work, and incorporate other components to make the composite system goal-directed, and to fill in gaps in and extend the LLMs cognitive abilities.

The term language model agent better captures the inherent agency of such a system, while "language model cognitive architecture" better captures the extensive additions to the LLM, and the resulting change in function and capabilities.

LMCAs are arguably a likely candidate for the first agentic, self-aware and self-improving AGIs.

Created by Seth Herd at 5mo