cs.AINov 14, 2026

Assume/Guarantee Contracts for the Compositional Multi-Agent Reinforcement Learning of Heterogeneous Teams

Authors: Dominic Klukas, Cyrus Neary

Organizations: University of British Columbia, Vancouver, Canada

Abstract

Multi-agent reinforcement learning (MARL) problems for heterogeneous teams require agents to collaborate to complete team tasks while making the best use of diverse agent capabilities. We introduce assume/guarantee contracts for heterogeneous multi-agent systems (AGC-MAS) and Iterative Heterogeneous Assignment for MARL (IHA-MARL). AGC-MAS contracts are compositional objects that encode the assumptions provided to, and the guarantees required of, each subtask contributing to the overall team task. We formulate contracts as tuples that specify a subtask, an automaton, timeout and success-probability requirements, and dispatch behavior. The automaton tracks an agent's high-level progress through the subtask associated with its contract and provides a natural mechanism for synchronization across contracts. Our abstraction enables robust interaction across heterogeneous low-level subtask implementations, allows heterogeneous agents to substitute for one another in satisfying contracts, and supports reuse of previously satisfied contracts in new team contexts. Having defined our theoretical framework, we develop a decomposition algorithm that breaks down a team task into a set of contracts. We then propose an iterative algorithm for task assignment and MARL that alternates between assigning contracts representing subtasks to individual agents, training the assigned agents to satisfy their contracts, and assessing their resulting capabilities to inform the next round of task assignments until the team's success probability meets the desired threshold. Our experimental results demonstrate the versatility of contracts in enabling agent substitution and contract reuse. Across three benchmarks with five seeds each, IHA-MARL achieves observed 100%100\% final evaluation success. In CPU timing pilots, comparable baselines required approximately 77--11×11\times more training-loop time.

Figures & tables

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Graphon Mean-Field Subsampling for Cooperative Heterogeneous Multi-Agent Reinforcement Learning

    Feb 18, 2026Emile Anand, Richard Hoffmann, Sarah Liaw +1Reinforcement LearningCooperative MARL

  2. Hierarchical Lead Critic based Multi-Agent Reinforcement Learning

    Feb 25, 2026David Eckel, Henri MeeßHierarchical MARLMulti-Agent Reinforcement Learning

  3. History Matters: Meta-policy Delegation with Heterogeneous Multi-agent Reinforcement Learning

    Aug 4, 2026Ziqing Lu, Avinash Reddy Mudireddy, Sarra Alqahtani +1Multi-Agent SystemsCooperative MARL