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

arXiv: https://arxiv.org/abs/2601.00097 · HTML: https://mlsanity.com/paper/2601.00097/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 6 of its 17 references that are in the map.
- First posted on arXiv 31 Dec 2025.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 6 of 6)

- [GPT-NER: Named Entity Recognition via Large Language Models](https://mlsanity.com/paper/2304.10428/) (2023)
- [A Bayesian machine scientist to aid in the solution of challenging scientific problems](https://mlsanity.com/paper/2004.12157/) (2020)
- [Explaining the Unique Nature of Individual Gait Patterns with Deep Learning](https://mlsanity.com/paper/1808.04308/) (2018)
- [Causal Reasoning in Software Quality Assurance: A Systematic Review](https://mlsanity.com/paper/2408.17183/) (2024)
- [Causal Autoencoder-like Generation of Feedback Fuzzy Cognitive Maps with an LLM Agent](https://mlsanity.com/paper/2509.25593/) (2025)
- [Soft Measures for Extracting Causal Collective Intelligence](https://mlsanity.com/paper/2409.18911/) (2024)

## Built on by (most cited first, 2 of 2)

- [Agentic Chunking and Bayesian De-chunking of AI Generated Fuzzy Cognitive Maps: A Model of the Thucydides Trap](https://mlsanity.com/paper/2605.17903/) (2026)
- [LLM for the development of FCM](https://mlsanity.com/paper/2607.04983/) (2026)

## Abstract (arXiv)

We design a large-language-model (LLM) agent system 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 the system still stays on its agentic leash. We show in particular that a sequence of three system-instruction sets 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.