Paper Overview
Field: ML Authors: Peter Tisnikar, Maja Swieczkowska, Benteng Ma, Gerard Canal, Matteo Leonetti arXiv: 2607.27177
Summary
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, the authors 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.
Key Contributions
- CE-CM (Capability Estimation via Contextual Models): an approximate Bayesian method that infers task-invariant capability vectors. Using simulation-based sampling, the agent estimates capabilities and induces a contextual multi-agent Markov decision process for planning.
- No population pretraining: beliefs are refined online across only a few tasks.
- CE-CM-Div: to handle human unpredictability, this extension evaluates capability hypotheses against diverse planner rollouts rather than a single optimal trajectory.
- In simulation, CE-CM rapidly recovers hidden capabilities, reduces infeasible action assignments, and adapts to time-varying capabilities.
- In an offline human study with 225 trajectories from 15 participants, CE-CM-Div significantly outperforms the baseline CE-M method.
Results
Conclusion
Capability-based modeling is a promising interpretable, task-agnostic representation for the studied scenarios, and accounting for behavioural diversity is essential for robust human-AI teaming.
--- *Auto-collected on 2026-07-31*