MV

Multi-agent learning · Robotics · Autonomy

Manav Vora

Scalable multi-agent learning & decision-making.

Ph.D. candidate in Aerospace Engineering at UIUC, advised by Prof. Melkior Ornik.

I develop scalable learning and decision-making methods for autonomous multi-agent systems operating under resource, information, communication, and sensing constraints.

My research connects scalable coordination and communication, resource-aware planning under budget and capacity limits, and information-efficient robotics. Current work includes sparse multi-agent diffusion, heterogeneous-sensor search and rescue, Nash-bargaining foundation models for conflict resolution, and occlusion-aware trajectory prediction.

I spent Summer 2026 at Nokia Bell Labs as an ML/AI Research Intern and Summer 2025 at Rivian as a Machine Learning Intern. Before UIUC, I studied Aerospace Engineering at IIT Bombay.

CV Scholar GitHub LinkedIn

Portrait of Manav Vora

Selected work

Research

All publications

2026

  1. RLC
    2026

    SCoUT: Scalable Communication via Utility-Guided Temporal Grouping in Multi-Agent Reinforcement Learning

    Manav Vora , Gokul Puthumanaillam , Hiroyasu Tsukamoto and Melkior Ornik

    Reinforcement Learning Journal Oral presentation
    • multi agent
    • RL

    Paper arXiv Project Code

    BibTeX 
    @article{vora2026scout,
  title = {SCoUT: Scalable Communication via Utility-Guided Temporal Grouping in Multi-Agent Reinforcement Learning},
  author = {Vora, Manav and Puthumanaillam, Gokul and Tsukamoto, Hiroyasu and Ornik, Melkior},
  journal = {Reinforcement Learning Journal},
  year = {2026},
  volume = {7},
}

2025

  1. CoRL
    2025

    Belief-Conditioned One-Step Diffusion: Real-Time Trajectory Planning with Just-Enough Sensing

    Gokul Puthumanaillam , Aditya Penumarti , Manav Vora , Paulo Padrao , Jose Fuentes , Leonardo Bobadilla , Jane Shin and Melkior Ornik

    Conference on Robot Learning Oral presentation · top 5%
    • robotics
    • Generative Models
    • planning
    • Information & Sensing

    Paper arXiv Project Code

    BibTeX 
    @inproceedings{puthumanaillam2025bcod,
  title = {Belief-Conditioned One-Step Diffusion: Real-Time Trajectory Planning with Just-Enough Sensing},
  author = {Puthumanaillam, Gokul and Penumarti, Aditya and Vora, Manav and Padrao, Paulo and Fuentes, Jose and Bobadilla, Leonardo and Shin, Jane and Ornik, Melkior},
  booktitle = {Conference on Robot Learning},
  year = {2025},
  volume = {305},
  pages = {68--92},
}

2026

  1. TMLR
    2026

    Solving Truly Massive Budgeted Monotonic POMDPs with Oracle-Guided Meta-Reinforcement Learning

    Manav Vora , Jonas Liang , Michael N Grussing and Melkior Ornik

    Transactions on Machine Learning Research
    • multi agent
    • RL
    • planning
    • pomdps
    • Resource-aware

    Paper arXiv OpenReview Code

    BibTeX 
    @article{vora2024solving,
  title = {Solving Truly Massive Budgeted Monotonic POMDPs with Oracle-Guided Meta-Reinforcement Learning},
  author = {Vora, Manav and Liang, Jonas and Grussing, Michael N and Ornik, Melkior},
  journal = {Transactions on Machine Learning Research},
  year = {2026},
}

2025

  1. IEEE RA-L
    2025

    Capacity-Aware Planning and Scheduling in Budget-Constrained Multi-Agent MDPs: A Meta-RL Approach

    Manav Vora , Ilan Shomorony and Melkior Ornik

    IEEE Robotics and Automation Letters
    • multi agent
    • RL
    • planning
    • Resource-aware

    Paper arXiv Code DOI

    BibTeX 
    @article{vora2024capacity,
  title = {Capacity-Aware Planning and Scheduling in Budget-Constrained Multi-Agent MDPs: A Meta-RL Approach},
  author = {Vora, Manav and Shomorony, Ilan and Ornik, Melkior},
  journal = {IEEE Robotics and Automation Letters},
  year = {2025},
  volume = {10},
  number = {11},
  pages = {11944--11951},
  doi = {10.1109/LRA.2025.3617726},
}

Now