This is neat - potentially - but the authors should include some benchmarks where this added complexity increases system performance. Otherwise it could be a solution in search of a problem.
Yes, I want to run benchmarks, but I haven’t found a suitable benchmark library yet, and I’m still not great with Python.
Anda AI App has integrated KIP, but based on its performance, it hasn’t met expectations yet. Current LLMs like GPT-5 and Gemini 2.5 Pro still can’t effectively power KIP.
I guess what could be interesting is that you can explore building a knowledge graph with this tool sans LLM…where you are the agent…
Absolutely. But I'm more interested in the knowledge graph an LLM would build. Actually, I haven't seen GPT-5 or Gemini 2.5 generate complex KIP—we need stronger LLMs!