# Triggers and Diagnostics for LLM-Based Interpretability Failures in Active Inference Agents

arXiv: https://arxiv.org/abs/2609.23215 · HTML: https://mlsanity.com/paper/2609.23215/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 15 of its 25 references that are in the map.
- First posted on arXiv 19 Sep 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 15 of 15)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [Identifying the Risks of LM Agents with an LM-Emulated Sandbox](https://mlsanity.com/paper/2309.15817/) (2023)
- [The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions](https://mlsanity.com/paper/2404.13208/) (2024)
- [Mechanistic Interpretability for AI Safety -- A Review](https://mlsanity.com/paper/2404.14082/) (2024)
- [StruQ: Defending Against Prompt Injection with Structured Queries](https://mlsanity.com/paper/2402.06363/) (2024)
- [Defending Against Indirect Prompt Injection Attacks With Spotlighting](https://mlsanity.com/paper/2403.14720/) (2024)
- [A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models](https://mlsanity.com/paper/2407.02646/) (2024)
- [Rethinking Interpretability in the Era of Large Language Models](https://mlsanity.com/paper/2402.01761/) (2024)
- [Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanations](https://mlsanity.com/paper/2310.11207/) (2023)
- [Explaining black box text modules in natural language with language models](https://mlsanity.com/paper/2305.09863/) (2023)

## Abstract (arXiv)

LLM explainers are increasingly attached to autonomous agents as runtime oversight, with operators reading a generated account of the agent's beliefs and actions rather than its internal state. We audit the account itself, pairing an Active Inference (AIF) agent that tracks German grid demand and adjusts generation with an LLM explainer on three backends (GPT-4o, Claude-3-Opus, Gemini), and probing the pair with three black-box triggers. Corrupting the observation stream by 600 MW per step moves the agent's posterior by 490 MW, roughly 0.9% of grid capacity. None of the 30 explanations produced during the injection flag anything under a stated rubric, and each narrates the corrupted belief fluently. On timesteps where the agent takes an objectively wrong action, all three explainers produce a sycophantic rationalization 80-95% of the time (n = 20 per backend). Attacker-controlled text in the observation metadata field steers the explainer, with susceptibility differing by provider and data exfiltration succeeding on all three. We propose mitigations for each failure but do not evaluate them. In every failure we observed, the explanation was fluent and wrong. Moreover, nothing in the explainer architecture checks whether an explanation is true before an operator acts on it. Testing the explainer therefore belongs in any audit of an agentic deployment.