Software & Data Downloads — LLawCo

Embodied agents must do more than act—they must coordinate, communicate, and adapt with partners under uncertainty. LLawCo introduces a powerful way to align LLM-based agents by learning task-specific behavioral “laws” from past failures, enabling agents to reason with principles such as “talk when necessary” and “wait for partner.” Inspired by Asimov’s Three Laws but grounded in experience, LLawCo turns failure into cooperative intelligence, improving decentralized teamwork in PARTNR-Dialog and TDW-MAT environments. We are publicly releasing our implementation to foster research into this important topic.

• MERL Contact

  • 

    Anoop
    Cherian
     

• Related Research Highlight

  • LLawCo: Learning Laws of Cooperation for Modeling Embodied Multi-Agent Behavior

• Related Publications

   Zhou, Q., Gan, C., Cherian, A., "LLawCo: Learning Laws of Cooperation for Modeling Embodied Multi-Agent Behavior", International Conference on Machine Learning (ICML), June 2026.

  BibTeX TR2026-081 PDF Video Software

  • @inproceedings{Zhou2026jun,
  • author = {Zhou, Qinhong and Gan, Chuang and Cherian, Anoop},
  • title = {{LLawCo: Learning Laws of Cooperation for Modeling Embodied Multi-Agent Behavior}},
  • booktitle = {International Conference on Machine Learning (ICML)},
  • year = 2026,
  • month = jun,
  • url = {https://www.merl.com/publications/TR2026-081}
  • }



Software & Data Downloads

Access software at https://github.com/merlresearch/llawco.