[Feature Request]: Implement SAFE Agent for fact-checking

[rokosbasilisk]

https://github.com/google-deepmind/long-form-factuality/tree/main
https://arxiv.org/pdf/2403.18802.pdf
SAFE is a method to split longform answers and check factuality, ConverseableAgent can be extented to implement this.

[rokosbasilisk]

I am currently working on this, if this is not in-line with autogen's priorities the issue can be closed.

[WaelKarkoub]

@rokosbasilisk can it be implemented as a capability?

[Josephrp]

my impression is that you shoulld build what you like then contribute it upstream as you see fit, a good start is a notebook demo , for a capability , it could be interesting but a lot more work than a simpler demonstration.

[gagb]

@rokosbasilisk thank you! Let us know if there are any updates.

[rysweet]

if still interested please feel free to contribute in autogen 0.4.5 or later