AI RESEARCH
How Much LLM Does a Self-Revising Agent Actually Need?
arXiv CS.CL
•
ArXi:2604.07236v1 Announce Type: cross Recent LLM-based agents often place world modeling, planning, and reflection inside a single language model loop. This can produce capable behavior, but it makes a basic scientific question difficult to answer: which part of the agent's competence actually comes from the LLM, and which part comes from explicit structure around it? We study this question not by claiming a general answer, but by making it empirically tractable.