mlsanityData to 14 Oct 2026

Enabling Rapid Shared Human-AI Mental Model Alignment via the After-Action Review

arXiv 2503.19607 ↗First posted 25 Mar 2025cs.HC cs.AIcited by 1

On the map: LLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment

Abstract (arXiv)

In this work, we present two novel contributions toward improving research in human-machine teaming (HMT): 1) a Minecraft testbed to accelerate testing and deployment of collaborative AI agents and 2) a tool to allow users to revisit and analyze behaviors within an HMT episode to facilitate shared mental model development. Our browser-based Minecraft testbed allows for rapid testing of collaborative agents in a continuous-space, real-time, partially-observable environment with real humans without cumbersome setup typical to human-AI interaction user studies. As Minecraft has an extensive player base and a rich ecosystem of pre-built AI agents, we hope this contribution can help to facilitate research quickly in the design of new collaborative agents and in understanding different human factors within HMT. Our mental model alignment tool facilitates user-led post-mission analysis by including video displays of first-person perspectives of the team members (i.e., the human and AI) that can be replayed, and a chat interface that leverages GPT-4 to provide answers to various queries regarding the AI's experiences and model details.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 13 of its 38 references that are in the map. First posted on arXiv 25 Mar 2025.

Builds on

13 of 38 references.

References · 13

  1. 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 708
  2. 2019On the Utility of Learning about Humans for Human-AI Coordinationcited by 349
  3. 2019Emergent Tool Use From Multi-Agent Autocurriculacited by 313
  4. 2017StarCraft II: A New Challenge for Reinforcement Learningcited by 274
  5. 2019Google Research Football: A Novel Reinforcement Learning Environmentcited by 260
  6. 2019The Hanabi Challenge: A New Frontier for AI Researchcited by 197
  7. 2023Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanationscited by 90
  8. 2021Evaluation of Human-AI Teams for Learned and Rule-Based Agents in Hanabicited by 40
  9. 2019Improving Policies via Search in Cooperative Partially Observable Gamescited by 33
  10. 2022The Utility of Explainable AI in Ad Hoc Human-Machine Teamingcited by 30
  11. 2019CraftAssist: A Framework for Dialogue-enabled Interactive Agentscited by 28
  12. 2023Effective Human-AI Teams via Learned Natural Language Rules and Onboardingcited by 20
1 more
  1. 2023Using Large Language Models for Interpreting Autonomous Robots Behaviorscited by 4

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025X-Ego: Acquiring Team-Level Tactical Situational Awareness via Cross-Egocentric Contrastive Video Representation Learningcited by 3

Similar, not cited

Close in wording, no citation either way

  1. 2024TeamCraft: A Benchmark for Multi-Modal Multi-Agent Systems in Minecraft
  2. 2025Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning
  3. 2026Humans' ALMANAC: A Human Collaboration Dataset of Action-Level Mental Model Annotations for Agent Collaboration
  4. 2026Evaluating Generative Models as Interactive Emergent Representations of Human-Like Collaborative Behavior
  5. 2025CrafterDojo: A Suite of Foundation Models for Building Open-Ended Embodied Agents in Crafter
  6. 2024MindForge: Empowering Embodied Agents with Theory of Mind for Lifelong Cultural Learning
  7. 2024Mutual Theory of Mind in Human-AI Collaboration: An Empirical Study with LLM-driven AI Agents in a Real-time Shared Workspace Task
  8. 2022MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge