# Automated Meta Prompt Engineering for Alignment with the Theory of Mind

arXiv: https://arxiv.org/abs/2505.09024 · HTML: https://mlsanity.com/paper/2505.09024/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 48 references that are in the map.
- First posted on arXiv 13 May 2025.

## Builds on (most cited first, 30 of 30)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents](https://mlsanity.com/paper/2310.11667/) (2023)
- [Machine Theory of Mind](https://mlsanity.com/paper/1802.07740/) (2018)
- [Chain-of-Thought Reasoning Without Prompting](https://mlsanity.com/paper/2402.10200/) (2024)
- [An Introduction to Deep Reinforcement Learning](https://mlsanity.com/paper/1811.12560/) (2018)
- [Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge](https://mlsanity.com/paper/2407.19594/) (2024)
- [Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future](https://mlsanity.com/paper/2309.15402/) (2023)
- [More Agents Is All You Need](https://mlsanity.com/paper/2402.05120/) (2024)
- [The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey](https://mlsanity.com/paper/2404.11584/) (2024)
- [Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding](https://mlsanity.com/paper/2401.12954/) (2024)
- [Combining Deep Reinforcement Learning and Search for Imperfect-Information Games](https://mlsanity.com/paper/2007.13544/) (2020)
- [Counterfactual Invariance to Spurious Correlations: Why and How to Pass Stress Tests](https://mlsanity.com/paper/2106.00545/) (2021)
- [Large Language Models are Diverse Role-Players for Summarization Evaluation](https://mlsanity.com/paper/2303.15078/) (2023)
- [Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMs](https://mlsanity.com/paper/2404.15676/) (2024)
- [How to Prompt? Opportunities and Challenges of Zero- and Few-Shot Learning for Human-AI Interaction in Creative Applications of Generative Models](https://mlsanity.com/paper/2209.01390/) (2022)
- [Harnessing the Power of Large Language Models for Empathetic Response Generation: Empirical Investigations and Improvements](https://mlsanity.com/paper/2310.05140/) (2023)
- [InterIntent: Investigating Social Intelligence of LLMs via Intention Understanding in an Interactive Game Context](https://mlsanity.com/paper/2406.12203/) (2024)
- [Reinforcement Learning in the Era of LLMs: What is Essential? What is needed? An RL Perspective on RLHF, Prompting, and Beyond](https://mlsanity.com/paper/2310.06147/) (2023)
- [Unveiling Theory of Mind in Large Language Models: A Parallel to Single Neurons in the Human Brain](https://mlsanity.com/paper/2309.01660/) (2023)
- [Effective Structured Prompting by Meta-Learning and Representative Verbalizer](https://mlsanity.com/paper/2306.00618/) (2023)
- [Advancing the Search Frontier with AI Agents](https://mlsanity.com/paper/2311.01235/) (2023)
- [Adopting AI: How Familiarity Breeds Both Trust and Contempt](https://mlsanity.com/paper/2305.01405/) (2023)
- [On Meta-Prompting](https://mlsanity.com/paper/2312.06562/) (2023)
- [Large Scale Generative AI Text Applied to Sports and Music](https://mlsanity.com/paper/2402.15514/) (2024)
- [Spontaneous Theory of Mind for Artificial Intelligence](https://mlsanity.com/paper/2402.13272/) (2024)

## Abstract (arXiv)

We introduce a method of meta-prompting that jointly produces fluent text for complex tasks while optimizing the similarity of neural states between a human's mental expectation and a Large Language Model's (LLM) neural processing. A technique of agentic reinforcement learning is applied, in which an LLM as a Judge (LLMaaJ) teaches another LLM, through in-context learning, how to produce content by interpreting the intended and unintended generated text traits. To measure human mental beliefs around content production, users modify long form AI-generated text articles before publication at the US Open 2024 tennis Grand Slam. Now, an LLMaaJ can solve the Theory of Mind (ToM) alignment problem by anticipating and including human edits within the creation of text from an LLM. Throughout experimentation and by interpreting the results of a live production system, the expectations of human content reviewers had 100% of alignment with AI 53.8% of the time with an average iteration count of 4.38. The geometric interpretation of content traits such as factualness, novelty, repetitiveness, and relevancy over a Hilbert vector space combines spatial volume (all trait importance) with vertices alignment (individual trait relevance) enabled the LLMaaJ to optimize on Human ToM. This resulted in an increase in content quality by extending the coverage of tennis action. Our work that was deployed at the US Open 2024 has been used across other live events within sports and entertainment.