Publications
For news about publications, follow us on X: 
Click on any author names or tags to filter publications.
All topic tags:
surveydeep-rlmulti-agent-rlagent-modellingad-hoc-teamworkautonomous-drivinggoal-recognitionexplainable-aicausalgeneralisationsecurityemergent-communicationiterated-learningintrinsic-rewardsimulatorstate-estimationdeep-learningtransfer-learningLLM
Selected tags (click to remove):
DAIJiangbo-Shangguan
2025
Charlie Masters, Advaith Vellanki, Jiangbo Shangguan, Bart Kultys, Alastair Moore, Stefano V. Albrecht
Orchestrating Human-AI Teams: The Manager Agent as a Unifying Research Challenge
International Conference on Distributed Artificial Intelligence, 2025
Abstract | BibTex | arXiv | Code
DAImulti-agent-rlLLM
Abstract:
While agentic AI has advanced in automating individual tasks, managing complex multi-agent workflows remains a challenging problem. This paper presents a research vision for autonomous agentic systems that orchestrate collaboration within dynamic human-AI teams. We propose the Autonomous Manager Agent as a core challenge: an agent that decomposes complex goals into task graphs, allocates tasks to human and AI workers, monitors progress, adapts to changing conditions, and maintains transparent stakeholder communication. We formalize workflow management as a Partially Observable Stochastic Game and identify four foundational challenges: (1) compositional reasoning for hierarchical decomposition, (2) multi-objective optimization under shifting preferences, (3) coordination and planning in ad hoc teams, and (4) governance and compliance by design. To advance this agenda, we release an open-source simulation and evaluation framework for multi-agent workflow orchestration. Evaluating GPT-5-based Manager Agents across 20 workflows, we find they struggle to jointly optimize for goal completion, constraint adherence, and workflow runtime--underscoring workflow management as a difficult open problem. We conclude with organizational and ethical implications of autonomous management systems.
@inproceedings{manager_agent_gym_2025,
title = {Orchestrating Human-AI Teams: The Manager Agent as a Unifying Research Challenge},
author = {Masters, Charlie and Vellanki, Advaith and Shangguan, Jiangbo and Kultys, Bart and Moore, Alastair and Albrecht, Stefano V.},
booktitle = {Proceedings of the International Conference on Distributed Artificial Intelligence (DAI 2025)},
year = {2025}
}