# Causal Autoencoder-like Generation of Feedback Fuzzy Cognitive Maps with an LLM Agent

arXiv: https://arxiv.org/abs/2509.25593 · HTML: https://mlsanity.com/paper/2509.25593/

## Key facts

- Cited by 3 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 7 of its 23 references that are in the map.
- First posted on arXiv 29 Sep 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, 7 of 7)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Understanding disentangling in β-VAE](https://mlsanity.com/paper/1804.03599/) (2018)
- [Lossy Image Compression with Compressive Autoencoders](https://mlsanity.com/paper/1703.00395/) (2017)
- [GPT-NER: Named Entity Recognition via Large Language Models](https://mlsanity.com/paper/2304.10428/) (2023)
- [Generalized Denoising Auto-Encoders as Generative Models](https://mlsanity.com/paper/1305.6663/) (2013)
- [Relational Autoencoder for Feature Extraction](https://mlsanity.com/paper/1802.03145/) (2018)
- [Discriminative Autoencoder for Feature Extraction: Application to Character Recognition](https://mlsanity.com/paper/1912.12131/) (2019)

## Built on by (most cited first, 3 of 3)

- [The Agentic Leash: Extracting Causal Feedback Fuzzy Cognitive Maps with LLMs](https://mlsanity.com/paper/2601.00097/) (2025)
- [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)
- [Converting Sequenced Fuzzy Cognitive Maps to Causal Virtual Worlds with Large Video Generators](https://mlsanity.com/paper/2609.14985/) (2026)

## Abstract (arXiv)

A large language model (LLM) can map a feedback causal fuzzy cognitive map (FCM) into text and then reconstruct the FCM from the text. This explainable AI system approximates an identity map from the FCM to itself and resembles the operation of an autoencoder (AE). Both the encoder and the decoder explain their decisions in contrast to black-box AEs. Humans can read and interpret the encoded text in contrast to the hidden variables and synaptic webs in AEs. The LLM agent approximates the identity map through a sequence of system instructions that does not compare the output to the input. The reconstruction is lossy because it removes weak causal edges or rules while it preserves strong causal edges. The encoder preserves the strong causal edges even when it trades off some details about the FCM to make the text sound more natural.