concept

planning

Facts (20)

Sources

A Comprehensive Review of Neuro-symbolic AI for Robustness ... link.springer.com Springer Dec 9, 2025 3 facts

procedureNeuro-symbolic programming allows users to write high-level programs that utilize neural networks as subroutines for perception tasks, enabling the resulting system to perform probabilistic inference or planning.

claimRobots can use probabilistic programs to model uncertainty in their environment while using neural networks to analyze sensor data, allowing the system to perform Bayesian updating and planning that is verifiable at the program level.

referenceModular architectures in neuro-symbolic AI retain clear separability between neural and symbolic subsystems, where neural modules output probabilistic facts or distributions that are consumed by symbolic solvers for logical inference or planning.

The Synergy of Symbolic and Connectionist AI in LLM-Empowered ... arxiv.org arXiv Jul 11, 2024 3 facts

claimLLM-enhanced autonomous agents utilize deep neural networks for processing while employing symbolic AI principles to guide task decomposition and planning by breaking tasks into discrete, logical steps.

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.

The Synergy of Symbolic and Connectionist AI in LLM ... arxiv.org arXiv 2 facts

claimLarge Language Models are trained on large-scale transformers comprising billions of learnable parameters to support abilities including perception, reasoning, planning, and action.

claimLLM-empowered Autonomous Agents demonstrate advanced reasoning, planning, and decision-making abilities.

The Profound Interplay Between Sleep and Cognitive Function creyos.com Mackenzie Godard · Creyos Aug 14, 2025 1 fact

referenceSleep deprivation significantly impacts executive functions such as planning, judgment, and impulse control, which can lead to risky decision-making and impaired problem-solving abilities, according to Salfi et al. (2020) and Wild et al. (2018).

Neuro-symbolic AI - Wikipedia en.wikipedia.org Wikipedia 1 fact

referenceDaniel Kahneman's book "Thinking, Fast and Slow" describes human cognition as encompassing two components: System 1, which is fast, reflexive, intuitive, and unconscious, and System 2, which is slower, step-by-step, and explicit. System 1 is used for pattern recognition, while System 2 handles planning, deduction, and deliberative thinking.

Unlocking the Potential of Generative AI through Neuro-Symbolic ... arxiv.org arXiv Feb 16, 2025 1 fact

claimSymbolic AI systems function on explicit rules and structured representations, enabling them to perform reasoning tasks such as mathematical proofs, planning, and expert systems.

Global workspace theory - Wikipedia en.wikipedia.org Wikipedia 1 fact

claimGlobal Workspace Theory facilitates top-down control of attention, working memory, planning, and problem-solving through information sharing.

LLM-empowered knowledge graph construction: A survey - arXiv arxiv.org arXiv Oct 23, 2025 1 fact

claimKnowledge graphs are increasingly used as a cognitive middle layer between raw input and LLM reasoning, providing a structured scaffold for querying, planning, and decision-making to enable more interpretable and grounded generation.

Papers - Dr Vaishak Belle vaishakbelle.github.io 1 fact

referenceThe paper 'Counterfactual Explanations as Plans' by V. Belle was published in the ICLP proceedings in 2023.

The construction and refined extraction techniques of knowledge ... nature.com Nature Feb 10, 2026 1 fact

referenceThe task branch module defines input-output structures for five core tasks: planning, threat evaluation, equipment configuration, command parsing, and domain-specific question answering.

Landmark experiment sheds new light on the origins of consciousness alleninstitute.org Liz Dueweke · Allen Institute 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.

Building Better Agentic Systems with Neuro-Symbolic AI cutter.com Cutter Consortium Dec 10, 2025 1 fact

claimLarge language models (LLMs) struggle with tasks that require strict logic, long-term planning, or adherence to hard rules such as laws, legal codes, or physics.

Attention and Consciousness in Psychology | PDF - Scribd scribd.com Scribd 1 fact

claimConscious attention serves three primary purposes: monitoring the environment, linking past and present experiences, and planning future actions.

KG-RAG: Bridging the Gap Between Knowledge and Creativity - arXiv arxiv.org arXiv May 20, 2024 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 Frontiers Aug 26, 2024 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.