Relations (1)

related 0.20 — supporting 2 facts

LLM-based agents are directly derived from Large Language Models, as they leverage the emergent abilities and flexible knowledge embedded within these models to perform reasoning and generate human-like responses as described in [1] and [2].

Facts (2)

Sources
The Synergy of Symbolic and Connectionist AI in LLM ... arxiv.org arXiv 1 fact
claimLLM-based agents are better able to handle ambiguity and generate human-like responses compared to symbolic AI because the knowledge embedded in LLMs is more flexible.
The Synergy of Symbolic and Connectionist AI in LLM-Empowered ... arxiv.org arXiv 1 fact
claimLLM-empowered agents (LAAs) demonstrate unique advantages over Knowledge Graphs (KGs) by analogizing human reasoning with agentic workflows and various prompting techniques, scaling effectively on large datasets, adapting to in-context samples, and leveraging the emergent abilities of Large Language Models.