MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning

2022/05/01 by Ehud Karpas, Karpas, Ehud, Omri Abend +31 · 23 citations
Computer Science · #Natural Language Processing Techniques #Topic Modeling #AI-based Problem Solving and Planning

paper · pdf · doi:10.48550/arxiv.2205.00445

Abstract

Huge language models (LMs) have ushered in a new era for AI, serving as a gateway to natural-language-based knowledge tasks. Although an essential element of modern AI, LMs are also inherently limited in a number of ways. We discuss these limitations and how they can be avoided by adopting a systems approach. Conceptualizing the challenge as one that involves knowledge and reasoning in addition to linguistic processing, we define a flexible architecture with multiple neural models, complemented by discrete knowledge and reasoning modules. We describe this neuro-symbolic architecture, dubbed the Modular Reasoning, Knowledge and Language (MRKL, pronounced "miracle") system, some of the technical challenges in implementing it, and Jurassic-X, AI21 Labs' MRKL system implementation.

Cited by

• VeraGrid-Agent: Tool-Augmented LLMs for Distribution Optimal Power Flow at the Grid Edge
• From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World
• An Empirical Study on the Security Vulnerabilities of GPTs
• Learning to Debug: LLM-Organized Knowledge Trees for Solving RTL Assertion Failures
• Systematic Reconstruction of Disease Networks from Longitudinal Blood Data for Causal Discovery and Intervention Analysis
• Procedural Knowledge Improves Agentic LLM Workflows
• Can Current Agents Close the Discovery-to-Application Gap? A Case Study in Minecraft
• Evidence-Bound Autonomous Research (EviBound): A Governance Framework for Eliminating False Claims
• Adaptive Minds: Empowering Agents with LoRA-as-Tools
• NetMCP: Network-Aware Model Context Protocol Platform for LLM Capability Extension
• A Survey on Evaluation of Large Language Models
• A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis
• A survey on neural-symbolic learning systems
• Adaptive Tool Generation with Models as Tools and Reinforcement Learning
• Expanding the Action Space of LLMs to Reason Beyond Language
• AutoMaAS: Self-Evolving Multi-Agent Architecture Search for Large Language Models
• From Static to Dynamic: Adaptive Monte Carlo Search for Mathematical Process Supervision
• PARL-MT: Learning to Call Functions in Multi-Turn Conversation with Progress Awareness
• Automatic Red Teaming LLM-based Agents with Model Context Protocol Tools
• Can neural networks do arithmetic? A survey on the elementary numerical skills of state-of-the-art deep learning models
• UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning
• Secure Multi-LLM Agentic AI and Agentification for Edge General Intelligence by Zero-Trust: A Survey
• M3LLM: Model Context Protocol-aided Mixture of Vision Experts For Multimodal LLMs in Networks

Related

• Emergence of Machine Language: Towards Symbolic Intelligence with Neural Networks
• Modular Machine Learning: An Indispensable Path towards New-Generation Large Language Models
• Converging Paradigms: The Synergy of Symbolic and Connectionist AI in LLM-Empowered Autonomous Agents
• Neuro-Symbolic Artificial Intelligence: Towards Improving the Reasoning Abilities of Large Language Models
• Proceedings of the First International Workshop on Next-Generation Language Models for Knowledge Representation and Reasoning (NeLaMKRR 2024)