Knowledge Tree
Relations (1)
related 3.00 — strongly supporting 7 facts
Reasoning and planning are consistently grouped as core cognitive abilities of AI agents and Large Language Models, as evidenced by their joint mention in agent architectures [1], agent capabilities {fact:1, fact:2, fact:4}, and specialized evaluation benchmarks [2]. Furthermore, both concepts are identified as key functions of the prefrontal cortex in biological contexts [3].
Facts (7)
Sources
The Synergy of Symbolic and Connectionist AI in LLM ... arxiv.org 2 facts
The Synergy of Symbolic and Connectionist AI in LLM-Empowered ... arxiv.org 2 facts
referenceThe architecture of an LAA consists of a neural sub-system (LLM) acting as a core controller, which orchestrates a symbolic sub-system and external tools, including components for planning, reasoning, memory, and tool-use.
claimLarge Language Models (LLMs) are trained on large-scale transformers comprising billions of learnable parameters to support agent abilities such as perception, reasoning, planning, and action.
Landmark experiment sheds new light on the origins of consciousness alleninstitute.org 1 fact
claimThe study suggests that while the prefrontal cortex is important for reasoning and planning, it may not be the primary hub for all visual specifics of conscious experience.
KG-RAG: Bridging the Gap Between Knowledge and Creativity - arXiv arxiv.org 1 fact
claimThe brain of an AI agent serves as the decision-making core responsible for reasoning, planning, and storing the agent’s knowledge and memories.
Combining large language models with enterprise knowledge graphs frontiersin.org 1 fact
referenceThe paper 'Planbench: an extensible benchmark for evaluating large language models on planning and reasoning about change' by Valmeekam et al. (2024) presents a benchmark designed to evaluate the planning and reasoning capabilities of large language models.