I'm doing some work now that involves taking natural language input, and then using an LLM to classify the input by FIPA performative, as well as part-of-speech-tagging to support downstream processing. It's early days, but hoping something interesting falls out of this.
Interesting, I do wonder about FIPA performative acts. On the one hand they have a clear function in terms of tagging steps in the protocols, and the protocols have a very clear function in terms of co-ordination and resource management. On the other hand this doesn't seem to have been the driver for the development of the performative act library - rather they developed them from the perspective of "let's classify the intent of all messages".
I did a paper for AAMAS 20 years ago where I reviewed the use of performative acts by real developers. No one in my project would co-author it with me (bad sign) and it got rejected (doh) but I do believe that it was useful and it's a shame that it didn't get into the literature. Anyway, the punch line was that when devs actually tried to use FIPA they just used the performative acts in the protocols that they implemented, and those protocols were almost always Fipa-Request and Fipa-Query.
Zeus has a FIPA transport as well as its native transport, it's got reasoning engines that it uses to act as approximately a BDI agent. The problem is that its STRIPS style planner can't reason so much... and also the RETE engine has sharp limits around rule chaining explosions and so on. The other big problem is that I haven't actually run it successfully for about 10 years due to Java versioning challenges (it works on 1.4 very well... however...)
did a paper for AAMAS 20 years ago where I reviewed the use of performative acts by real developers. No one in my project would co-author it with me (bad sign) and it got rejected (doh) but I do believe that it was useful and it's a shame that it didn't get into the literature.
Oh man. Bummer. I don't suppose you have a copy available online anywhere? I'd still love to give that a look if it's available.
Zeus has a FIPA transport as well as its native transport, it's got reasoning engines that it uses to act as approximately a BDI agent. The problem is that its STRIPS style planner can't reason so much...
Oh very cool. Zeus was somehow not on my radar. I'll have to give that a look. Currently I use Jason for BDI, but it doesn't have built in inference or planning. Which may be good or bad depending on your point of view. But that's where I'm going with the stuff I'm doing... looking at how to combine a BDI loop, various inference/reasoning techniques, planning, etc.
The interesting thing is, we know how to do those things in isolation reasonably well. It's combining them in a way that makes a cohesive whole that seems to be the big challenge. :-)
One thing we did with Zeus which remained proprietary was to build a graphplan planner to replace the STRIPS planner. This was better, but unfortunately it only shifted right by one step - very quickly we found that there were planning issues in the agent loop that were intractable.
I think that SAT planners could help further, and I think that LLM's can play a role by suggesting subplans as well. We know that for closed domains like games RL based planners like Alphago can be spectacular, but for the kind of open ___domain reasoning that Agents have to do I don't think that there is a solution yet.
https://jade-project.gitlab.io/
Or if you prefer Github, I mirror the repo here:
https://github.com/mindcrime-forks/jade-agents
I'm doing some work now that involves taking natural language input, and then using an LLM to classify the input by FIPA performative, as well as part-of-speech-tagging to support downstream processing. It's early days, but hoping something interesting falls out of this.