arXiv:2508. 06336v2 Announce Type: replace-cross Abstract: We introduce Unsupervised Partner Design (UPD), a population-free multi-agent reinforcement learning method for robust ad-hoc teamwork.
arXiv:2602. 17737v2 Announce Type: replace-cross Abstract: Mutual adaptation is a central challenge in human-AI teaming, as humans naturally adjust their strategies in response to an AI agent's behavior.
The paper introduces ROTATE, a regret-driven open‑ended training framework that jointly improves an Ad Hoc Teamwork (AHT) agent and an adversarial teammate generator. Unlike traditional two‑stage pipelines, ROTATE alternates between enhancing the agent and generating teammates that specifically probe its collaboration weaknesses. Experiments on Overcooked and Level‑Based Foraging show that ROTATE outperforms existing baselines on unseen teammates, setting a new benchmark for robust, generalizable teamwork.
The paper introduces ICRL4AHT, a large-scale benchmark for evaluating In-Context Reinforcement Learning (ICRL) in Ad-Hoc Teamwork (AHT) scenarios using Overcooked-V2. It provides a diverse teammate suite, a reproducible pipeline, and evaluates history-conditioned ICRL algorithms such as Algorithm Distillation and Decision-Pretrained Transformer. The results show that these methods often perform worse than random baselines and do not improve with longer horizons, underscoring the difficulty of strategic inference under partial observability in AHT.
arXiv:2610.31726v1 Announce Type: new Abstract: Effective human-machine teaming requires agents that coordinate with unpredictable human partners. Reinforcement learning from live human feedback or l...
arXiv:2609.39727v1 Announce Type: new Abstract: Cooperative language-model agents must coordinate over long horizons and adapt to changing environments and to partners with unfamiliar conventions, ye...
arXiv:2504. 03991v2 Announce Type: replace-cross Abstract: Understanding how humans collaborate and communicate in teams is essential for improving human-agent teaming and AI-assisted decision-making.
The paper introduces XPM-WM, a framework that uses learned world models to generate simulated trajectories for Cross-play Minimization (XPM) in Zero-Shot Coordination. By replacing costly Mixed-Play sampling with model-generated data, XPM-WM improves sample efficiency and scales linearly with population size, producing diverse partner agents that match the performance of existing methods. The approach also bootstraps training for subsequent agents and can be extended to other population‑based training techniques.
arXiv:2607. 04972v1 Announce Type: cross Abstract: Deploying robot teams in the real world requires simultaneous adaptation to unseen environments, unknown partners, and varying team sizes, yet existing approaches often address these challenges in isolation under the closed-world assumption of fixed teammates.
arXiv:2607. 27177v1 Announce Type: new Abstract: Effective collaboration with novel and diverse partners is a crucial skill for autonomous agents.
EvoTeam is a collaboration‑centric evolution framework for large‑language‑model based multi‑agent systems. It jointly evolves team organization, interaction rules, and individual agent skills using execution experience, while maintaining a library of reusable teams and guiding collaboration through team‑specific interaction rules. Experiments on four benchmarks show its effectiveness, and the code is publicly available on GitHub.
arXiv:2503. 13077v2 Announce Type: replace Abstract: Multi-agent reinforcement learning has shown promise in learning cooperative behaviors in team-based environments.
arXiv:2611.07066v1 Announce Type: new Abstract: Discovering cooperative behavior in multi-agent reinforcement learning (MARL) is challenging due to the combinatorial complexity of joint state-action...