# Implicitly Aligning Humans and Autonomous Agents through Shared Task Abstractions

arXiv: https://arxiv.org/abs/2505.04579 · HTML: https://mlsanity.com/paper/2505.04579/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 44 references that are in the map.
- First posted on arXiv 7 May 2025.

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

- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [On the Utility of Learning about Humans for Human-AI Coordination](https://mlsanity.com/paper/1910.05789/) (2019)
- [FeUdal Networks for Hierarchical Reinforcement Learning](https://mlsanity.com/paper/1703.01161/) (2017)
- ["Other-Play" for Zero-Shot Coordination](https://mlsanity.com/paper/2003.02979/) (2020)
- [Open Problems in Cooperative AI](https://mlsanity.com/paper/2012.08630/) (2020)
- [Collaborating with Humans without Human Data](https://mlsanity.com/paper/2110.08176/) (2021)
- [RODE: Learning Roles to Decompose Multi-Agent Tasks](https://mlsanity.com/paper/2010.01523/) (2020)
- [Off-Belief Learning](https://mlsanity.com/paper/2103.04000/) (2021)
- [Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordination](https://mlsanity.com/paper/2112.11701/) (2021)
- [A Survey of Ad Hoc Teamwork Research](https://mlsanity.com/paper/2202.10450/) (2022)
- [Feudal Multi-Agent Hierarchies for Cooperative Reinforcement Learning](https://mlsanity.com/paper/1901.08492/) (2019)
- [K-level Reasoning for Zero-Shot Coordination in Hanabi](https://mlsanity.com/paper/2207.07166/) (2022)
- [Too many cooks: Bayesian inference for coordinating multi-agent collaboration](https://mlsanity.com/paper/2003.11778/) (2020)
- [PECAN: Leveraging Policy Ensemble for Context-Aware Zero-Shot Human-AI Coordination](https://mlsanity.com/paper/2301.06387/) (2023)
- [Learning to Cooperate with Humans using Generative Agents](https://mlsanity.com/paper/2411.13934/) (2024)
- [Any-Play: An Intrinsic Augmentation for Zero-Shot Coordination](https://mlsanity.com/paper/2201.12436/) (2022)
- [Quantifying the effects of environment and population diversity in multi-agent reinforcement learning](https://mlsanity.com/paper/2102.08370/) (2021)
- [Diverse Conventions for Human-AI Collaboration](https://mlsanity.com/paper/2310.15414/) (2023)
- [A Hierarchical Approach to Population Training for Human-AI Collaboration](https://mlsanity.com/paper/2305.16708/) (2023)
- [How to be Helpful? Supportive Behaviors and Personalization for Human-Robot Collaboration](https://mlsanity.com/paper/1710.11194/) (2017)
- [Resonating Minds -- Emergent Collaboration Through Hierarchical Active Inference](https://mlsanity.com/paper/2112.01210/) (2021)

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

- [Towards Zero-Shot Coordination between Teams of Agents: The N-XPlay Framework](https://mlsanity.com/paper/2506.17560/) (2025)
- [Evaluating XAI Support From A Hierarchical Reinforcement Learning Policy in Human-Agent Collaboration](https://mlsanity.com/paper/2608.06381/) (2026)

## Abstract (arXiv)

In collaborative tasks, autonomous agents fall short of humans in their capability to quickly adapt to new and unfamiliar teammates. We posit that a limiting factor for zero-shot coordination is the lack of shared task abstractions, a mechanism humans rely on to implicitly align with teammates. To address this gap, we introduce HA2: Hierarchical Ad Hoc Agents, a framework leveraging hierarchical reinforcement learning to mimic the structured approach humans use in collaboration. We evaluate HA2 in the Overcooked environment, demonstrating statistically significant improvement over existing baselines when paired with both unseen agents and humans, providing better resilience to environmental shifts, and outperforming all state-of-the-art methods.