The Agentic Leash: Extracting Causal Feedback Fuzzy Cognitive Maps with LLMs

2025-12-31

arXiv.org

AI Summary

This work proposes an automated approach leveraging large language model (LLM) agents to extract fuzzy cognitive maps (FCMs) with causal feedback structures from raw textual data, thereby modeling the dynamic causal relationships inherent in complex systems. Through a three-stage structured prompting pipeline, the LLM agent sequentially identifies key concepts, constructs nodes, and infers fuzzy causal edges to generate dynamically convergent FCMs that stabilize at attractor states. The study introduces an innovative “agent-tethering” mechanism that establishes bidirectional coupling between the LLM and the FCM: the equilibrium state of the FCM guides subsequent text extraction, while newly extracted text dynamically updates the FCM structure, endowing the system with limited autonomy. Validation on texts by Kissinger et al. concerning the future of AI demonstrates that the generated FCMs yield limit cycles consistent with manually constructed counterparts, and that hybrid multi-LLM strategies not only preserve dominant dynamics but also reveal emergent equilibria that better approximate true causal relationships.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

We design a large-language-model (LLM) agent that extracts causal feedback fuzzy cognitive maps (FCMs) from raw text. The causal learning or extraction process is agentic both because of the LLM's semi-autonomy and because ultimately the FCM dynamical system's equilibria drive the LLM agents to fetch and process causal text. The fetched text can in principle modify the adaptive FCM causal structure and so modify the source of its quasi-autonomy--its equilibrium limit cycles and fixed-point attractors. This bidirectional process endows the evolving FCM dynamical system with a degree of autonomy while still staying on its agentic leash. We show in particular that a sequence of three finely tuned system instructions guide an LLM agent as it systematically extracts key nouns and noun phrases from text, as it extracts FCM concept nodes from among those nouns and noun phrases, and then as it extracts or infers partial or fuzzy causal edges between those FCM nodes. We test this FCM generation on a recent essay about the promise of AI from the late diplomat and political theorist Henry Kissinger and his colleagues. This three-step process produced FCM dynamical systems that converged to the same equilibrium limit cycles as did the human-generated FCMs even though the human-generated FCM differed in the number of nodes and edges. A final FCM mixed generated FCMs from separate Gemini and ChatGPT LLM agents. The mixed FCM absorbed the equilibria of its dominant mixture component but also created new equilibria of its own to better approximate the underlying causal dynamical system.

Problem

• causal feedback
• fuzzy cognitive maps
• LLM agents
• causal extraction
• dynamical systems

Innovation

• Agentic LLM
• Fuzzy Cognitive Maps
• Causal Feedback Extraction
• Dynamic Equilibrium
• Autonomous Text-to-FCM