# Neural Reasoning About Agents' Goals, Preferences, and Actions

arXiv: https://arxiv.org/abs/2312.07122 · HTML: https://mlsanity.com/paper/2312.07122/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 22 of its 48 references that are in the map.
- First posted on arXiv 12 Dec 2023.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)](https://mlsanity.com/paper/1511.07289/) (2015)
- [CLEVRER: CoLlision Events for Video REpresentation and Reasoning](https://mlsanity.com/paper/1910.01442/) (2019)
- [Abductive Commonsense Reasoning](https://mlsanity.com/paper/1908.05739/) (2019)
- [Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoning](https://mlsanity.com/paper/1909.00277/) (2019)
- [Video Transformer Network](https://mlsanity.com/paper/2102.00719/) (2021)
- [Machine Theory of Mind](https://mlsanity.com/paper/1802.07740/) (2018)
- [IntPhys: A Framework and Benchmark for Visual Intuitive Physics Reasoning](https://mlsanity.com/paper/1803.07616/) (2018)
- [CRAFT: A Benchmark for Causal Reasoning About Forces and inTeractions](https://mlsanity.com/paper/2012.04293/) (2020)
- [AGENT: A Benchmark for Core Psychological Reasoning](https://mlsanity.com/paper/2102.12321/) (2021)
- [Baby Intuitions Benchmark (BIB): Discerning the goals, preferences, and actions of others](https://mlsanity.com/paper/2102.11938/) (2021)
- [Probing Physics Knowledge Using Tools from Developmental Psychology](https://mlsanity.com/paper/1804.01128/) (2018)
- [Solving the Baby Intuitions Benchmark with a Hierarchically Bayesian Theory of Mind](https://mlsanity.com/paper/2208.02914/) (2022)
- [A Benchmark for Modeling Violation-of-Expectation in Physical Reasoning Across Event Categories](https://mlsanity.com/paper/2111.08826/) (2021)
- [Grid-to-Graph: Flexible Spatial Relational Inductive Biases for Reinforcement Learning](https://mlsanity.com/paper/2102.04220/) (2021)

## Built on by (most cited first, 8 of 8)

- [The Overcooked Generalisation Challenge: Evaluating Cooperation with Novel Partners in Unknown Environments Using Unsupervised Environment Design](https://mlsanity.com/paper/2406.17949/) (2024)
- [Limits of Theory of Mind Modelling in Dialogue-Based Collaborative Plan Acquisition](https://mlsanity.com/paper/2405.12621/) (2024)
- [Brittle Minds, Fixable Activations: Understanding Belief Representations in Language Models](https://mlsanity.com/paper/2406.17513/) (2024)
- [Explicit Modelling of Theory of Mind for Belief Prediction in Nonverbal Social Interactions](https://mlsanity.com/paper/2407.06762/) (2024)
- [ToM-SSI: Evaluating Theory of Mind in Situated Social Interactions](https://mlsanity.com/paper/2509.05066/) (2025)
- [The Yokai Learning Environment: Tracking Beliefs Over Space and Time](https://mlsanity.com/paper/2508.12480/) (2025)
- [Concepts Learned Visually by Infants Can Contribute to Visual Learning and Understanding in AI Models](https://mlsanity.com/paper/2503.03361/) (2025)
- [MindZero: Learning Online Mental Reasoning With Zero Annotations](https://mlsanity.com/paper/2606.00240/) (2026)

## Abstract (arXiv)

We propose the Intuitive Reasoning Network (IRENE) - a novel neural model for intuitive psychological reasoning about agents' goals, preferences, and actions that can generalise previous experiences to new situations. IRENE combines a graph neural network for learning agent and world state representations with a transformer to encode the task context. When evaluated on the challenging Baby Intuitions Benchmark, IRENE achieves new state-of-the-art performance on three out of its five tasks - with up to 48.9% improvement. In contrast to existing methods, IRENE is able to bind preferences to specific agents, to better distinguish between rational and irrational agents, and to better understand the role of blocking obstacles. We also investigate, for the first time, the influence of the training tasks on test performance. Our analyses demonstrate the effectiveness of IRENE in combining prior knowledge gained during training for unseen evaluation tasks.