[dead]
Survey Study on AI Agent Architectures (2024)
41–50 of 121 posts
Re: Survey Study on AI Agent Architectures (2024)
#42[dead]
Re: Survey Study on AI Agent Architectures (2024)
#43[dead]
Re: Survey Study on AI Agent Architectures (2024)
#44[dead]
Re: Survey Study on AI Agent Architectures (2024)
#45[dead]
Re: Survey Study on AI Agent Architectures (2024)
#46[dead]
Re: Survey Study on AI Agent Architectures (2024)
#47Not mentioned in the paper, but I have been experimenting with behavior trees for LLM agents, and have had a lot of success: https://richardkelley.io/dendron/tutorial_intro/
How is a behavior tree different from a decision tree? Is there a subtle difference I am missing? https://en.wikipedia.org/wiki/Decision_tree
The other reply linked to a good explanation. I would only add that I also wrote a paper on Dendron, and Figure 17 shows how to transform a decision tree node into a behavior tree, so that you can implement any decision tree as a behavior tree:
Re: Survey Study on AI Agent Architectures (2024)
#48[flagged]
Re: Survey Study on AI Agent Architectures (2024)
#49[dead]
Re: Survey Study on AI Agent Architectures (2024)
#50I'll just draw folks attention to the long running AAMAS conference series.
Of course, it's quite academic in nature, but it may be that some useful approaches could be picked up from this resource for LLM driven approaches.