[HN Gopher] Survey Study on AI Agent Architectures (2024)
___________________________________________________________________
Survey Study on AI Agent Architectures (2024)
Author : jslampe
Score : 50 points
Date : 2024-04-22 15:47 UTC (7 hours ago)
(HTM) web link (arxiv.org)
(TXT) w3m dump (arxiv.org)
| rck wrote:
| Not 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/
| muratsu wrote:
| This looks very interesting, thanks for sharing.
| billmalarky wrote:
| Hi Richard I just reached out to you on LI. I'd love to get a
| chance to chat with you about your experience with this. Thank
| you for sharing this is fascinating.
| gnat wrote:
| That's a very well-written tutorial! I wish more software came
| with something so friendly and informative. Thanks.
| temporarely wrote:
| 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
| sdesol wrote:
| This talks about the distinction
|
| https://gamedev.stackexchange.com/questions/51693/difference.
| ..
| temporarely wrote:
| thanks.
| rck wrote:
| 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:
|
| https://arxiv.org/abs/2404.07439
| temporarely wrote:
| Thanks! Noted the cite to this paper (below) as well in
| your paper in case others are interested:
|
| _Behavior Trees in Robotics and AI: An Introduction_ ,
| Michele Colledanchise, Petter Ogren, 2017
|
| http://arxiv.org/abs/1709.00084
|
| _1.1 A Short History and Motivation of BTs
|
| BTs were developed in the computer game industry, as a tool
| to increase modularity in the control structures of Non-
| Player Characters (NPCs) . In this billion-dollar industry,
| modularity is a key property that enables reuse of code,
| incremental design of functionality, and efficient testing.
|
| In games, the control structures of NPCs were often
| formulated in terms of Finite State Machines (FSMs).
| However, just as Petri Nets provide an alternative to FSMs
| that supports design of concurrent systems, BTs provide an
| alternative view of FSMs that supports design of modular
| systems. Following the development in the industry, BTs
| have now also started to receive attention in academia.
|
| At Carnegie Mellon University, BTs have been used
| extensively to do robotic manipulation. The fact that
| modularity is the key reason for using BTs is clear from
| the following quote from [2]: "The main advantage is that
| individual behaviors can easily be reused in the context of
| another higher-level behavior, without needing to specify
| how they relate to subsequent behaviors".
|
| BTs have also been used to enable non-experts to do robot
| programming of pick and place operations, due to their
| "modular, adaptable representation of a robotic task" and
| allowed "end-users to visually create programs with the
| same amount of complexity and power as traditionally-
| written programs" [56]. Furthermore, BTs have been proposed
| as a key component in brain surgery robotics due to their
| "flex- ibility, reusability, and simple syntax"._
| abrichr wrote:
| Not mentioned: learning from demonstration. This is the approach
| we are taking at https://github.com/OpenAdaptAI/OpenAdapt.
| sgt101 wrote:
| I'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.
|
| https://aamas2023.soton.ac.uk/
| jrussino wrote:
| In addition, here are a few other conferences that may be of
| interest to people in this thread:
|
| - AAAI: https://aaai.org/conference/aaai/
|
| - ICAPS: https://icaps24.icaps-conference.org/
|
| - IJCAI: https://www.ijcai.org/
| 2genders28501 wrote:
| Are you lonely? Do u want an AI girlfriend?
| https://discord.gg/elyza HmgfRIzviKPDqRZRr
| 2genders37515 wrote:
| hi are u lonely want ai gf?? https://discord.gg/elyza
| zvAUbNxLzAjpghFhb
| SEXMCNIGGA38087 wrote:
| hi are u lonely want ai gf?? https://discord.gg/elyza -- FOLLOW
| THE HOMIE https://twitter.com/hashimthearab lTSkqmHfDoBuAbGFM
| 2genders18584 wrote:
| hi are u lonely want ai gf?? https://discord.gg/candyai
| JpYPtXtXteuEGyQoW
| 2genders42041 wrote:
| Are you lonely? Do u want an AI girlfriend?
| https://discord.gg/elyza -- FOLLOW THE HOMIE
| https://twitter.com/hashimthearab OoybHTYjKEeDvjICw
| 2genders30123 wrote:
| hi are u lonely want ai gf?? https://discord.gg/candyai
| OImcfmLGYzxoFhWTa
| 2genders44146 wrote:
| hi are u lonely want ai gf?? https://discord.gg/candyai
| TvWAqIxiAUOktvTMb
| 2genders2513 wrote:
| hi are u lonely want ai gf?? https://discord.gg/candyai
| ZieQofMjdHFYawgLO
| 2genders3548 wrote:
| hi are u lonely want ai gf?? https://discord.gg/elyza
| vZOhfQCMFCAjZiiXh
| 2genders13032 wrote:
| hi are u lonely want ai gf?? https://discord.gg/elyza
| qxtsqVWsDajdZZCSJ
| 2genders38930 wrote:
| hi are u lonely want ai gf?? https://discord.gg/elyza
| fWUIOLKwIsdvuOCqY
___________________________________________________________________
(page generated 2024-04-22 23:00 UTC)