# Partner Capability Estimation for Task-Agnostic Adaptation in Ad-Hoc Teamwork

arXiv: https://arxiv.org/abs/2607.27177 · HTML: https://mlsanity.com/paper/2607.27177/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 64 references that are in the map.
- First posted on arXiv 29 Jul 2026.

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

- [On the Utility of Learning about Humans for Human-AI Coordination](https://mlsanity.com/paper/1910.05789/) (2019)
- ["Other-Play" for Zero-Shot Coordination](https://mlsanity.com/paper/2003.02979/) (2020)
- [Deep Reinforcement Learning from Self-Play in Imperfect-Information Games](https://mlsanity.com/paper/1603.01121/) (2016)
- [Collaborating with Humans without Human Data](https://mlsanity.com/paper/2110.08176/) (2021)
- [Modeling Others using Oneself in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1802.09640/) (2018)
- [A Survey of Ad Hoc Teamwork Research](https://mlsanity.com/paper/2202.10450/) (2022)
- [Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased](https://mlsanity.com/paper/2302.01605/) (2023)
- [Efficient Model Learning for Human-Robot Collaborative Tasks](https://mlsanity.com/paper/1405.6341/) (2014)
- [On the Critical Role of Conventions in Adaptive Human-AI Collaboration](https://mlsanity.com/paper/2104.02871/) (2021)
- [PECAN: Leveraging Policy Ensemble for Context-Aware Zero-Shot Human-AI Coordination](https://mlsanity.com/paper/2301.06387/) (2023)
- [Reasoning about Hypothetical Agent Behaviours and their Parameters](https://mlsanity.com/paper/1906.11064/) (2019)
- [Belief and Truth in Hypothesised Behaviours](https://mlsanity.com/paper/1507.07688/) (2015)
- [Diverse Conventions for Human-AI Collaboration](https://mlsanity.com/paper/2310.15414/) (2023)
- [Coordination with Humans via Strategy Matching](https://mlsanity.com/paper/2210.15099/) (2022)
- [Adaptive Coordination in Social Embodied Rearrangement](https://mlsanity.com/paper/2306.00087/) (2023)
- [AssistanceZero: Scalably Solving Assistance Games](https://mlsanity.com/paper/2504.07091/) (2025)
- [Robust Task Scheduling for Heterogeneous Robot Teams under Capability Uncertainty](https://mlsanity.com/paper/2106.12111/) (2021)
- [Adaptive Task Allocation for Heterogeneous Multi-Robot Teams with Evolving and Unknown Robot Capabilities](https://mlsanity.com/paper/2003.03344/) (2020)
- [Decentralized MCTS via Learned Teammate Models](https://mlsanity.com/paper/2003.08727/) (2020)
- [Learning Human Preferences Over Robot Behavior as Soft Planning Constraints](https://mlsanity.com/paper/2403.19795/) (2024)
- [Intuitive and Efficient Human-robot Collaboration via Real-time Approximate Bayesian Inference](https://mlsanity.com/paper/2205.08657/) (2022)
- [Diverse, Top-k, and Top-Quality Planning Over Simulators](https://mlsanity.com/paper/2308.13147/) (2023)

## Built on by (most cited first, 1 of 1)

- [Watch, Infer, Coordinate: Inferring Robot Partner Constraints for Zero-Shot Coordination](https://mlsanity.com/paper/2610.02170/) (2026)

## Abstract (arXiv)

Effective collaboration with novel and diverse partners is a crucial skill for autonomous agents. Most current ad-hoc teamwork (AHT) approaches assume that agents will collaborate on a single, fixed task and that the partner's capabilities, their ability to successfully execute the desired action, are already known. In reality, a partner's true capabilities are often hidden, and human collaborators may act sub-optimally on tasks with multiple valid strategies. To address these limitations, we extend ad-hoc teamwork into a multi-task setting by re-framing it as a problem of joint planning with decentralised execution under hidden partner capabilities. We introduce CE-CM (Capability Estimation via Contextual Models), an approximate Bayesian method that infers task-invariant capability vectors. By using simulation-based sampling, the agent estimates capabilities and induces a contextual Multi-agent Markov Decision Processes for planning. This approach requires no population pre-training and refines its beliefs online from just a few tasks. To account for human unpredictability, we propose CE-CM-Div, an extension that evaluates capability hypotheses against diverse planner rollouts rather than a single optimal trajectory. Simulated experiments demonstrate that CE-CM rapidly recovers hidden capabilities, reduces infeasible action assignments, and adapts to changes over time. Furthermore, in an offline human study of 225 trajectories from 15 participants, CE-CM-Div substantially improved capability estimates over the baseline CE-CM method. Our results suggest capability-based modelling is a promising interpretable, task-agnostic representation in the studied settings, demonstrating that accounting for behavioural diversity is essential for robust human-AI teaming.