# Generic-to-Specific Reasoning and Learning for Scalable Ad Hoc Teamwork

arXiv: https://arxiv.org/abs/2508.04163 · HTML: https://mlsanity.com/paper/2508.04163/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 30 references that are in the map.
- First posted on arXiv 6 Aug 2025.

## Builds on (most cited first, 8 of 8)

- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [VirtualHome: Simulating Household Activities via Programs](https://mlsanity.com/paper/1806.07011/) (2018)
- [Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning](https://mlsanity.com/paper/2305.14909/) (2023)
- [Are Emergent Abilities in Large Language Models just In-Context Learning?](https://mlsanity.com/paper/2309.01809/) (2023)
- [Towards Open Ad Hoc Teamwork Using Graph-based Policy Learning](https://mlsanity.com/paper/2006.10412/) (2020)
- [Cooperation on the Fly: Exploring Language Agents for Ad Hoc Teamwork in the Avalon Game](https://mlsanity.com/paper/2312.17515/) (2023)
- [Expected Value of Communication for Planning in Ad Hoc Teamwork](https://mlsanity.com/paper/2103.01171/) (2021)
- [Knowledge-based Reasoning and Learning under Partial Observability in Ad Hoc Teamwork](https://mlsanity.com/paper/2306.00790/) (2023)

## Abstract (arXiv)

AI agents deployed in assistive roles often have to collaborate with other agents (humans, AI systems) without prior coordination. Methods considered state of the art for such ad hoc teamwork often pursue a data-driven approach that needs a large labeled dataset of prior observations, lacks transparency, and makes it difficult to rapidly revise existing knowledge in response to changes. As the number of agents increases, the complexity of decision-making makes it difficult to collaborate effectively. This paper advocates leveraging the complementary strengths of knowledge-based and data-driven methods for reasoning and learning for ad hoc teamwork. For any given goal, our architecture enables each ad hoc agent to determine its actions through non-monotonic logical reasoning with: (a) prior commonsense domain-specific knowledge; (b) models learned and revised rapidly to predict the behavior of other agents; and (c) anticipated abstract future goals based on generic knowledge of similar situations in an existing foundation model. We experimentally evaluate our architecture's capabilities in VirtualHome, a realistic physics-based 3D simulation environment.