Strategic Multi-Agent Resource Allocation via Statistical Contracts
Abstract
We study a class of strategic hypothesis testing problems in which a principal aims to allocate resources among competing agents who possess data or data-generating mechanisms that may be relevant to the principal's goals. Each agent can pay a participation cost to opt into a statistical contract, in which case they generate data from a private distribution and receive an allocation based on a predetermined (and publicly known) mechanism. Each agent is either "null" or "non-null" and the principal's goal is to design the contract to limit the allocation to the former while maximizing transactions with the latter. Using e-values, we define a "continuous-closure," a set of allocations which prevents null agents from profiting in expectation and provides post-hoc risk control for general loss functions under arbitrary dependence. When the loss is the fraction of resources allocated to null agents, the region admits polynomial-time linear optimization. We also give explicit, interpretable closed-form approximations, and we analyze participation from a non-null agent's perspective, giving conditions under which entry into the contract is profitable. Finally, we extend the framework to support online arrival of the agents, in which case the principal has to make irrevocable on-the-fly decisions, and provide a method which gives time-uniform error-control in this setting.
Related
- Multi-view Semantic-aware Resource Allocation for Edge AI
- Multi-Task Active Learning with Efficient Resource Allocation
- A Token/KV-Cache Communication Media Selection and Resource Allocation Strategy for Multi-Agent Collaboration
- Statistical patterns in the Ethereum blockchain: Analysis of EOAs and smart contracts in ERC20 token network
- Optimal Dynamic Resource Allocation for Multicore Real-time Systems
BibTeX
@misc{chugg2026strategic,
title = {{Strategic Multi-Agent Resource Allocation via Statistical Contracts}},
author = {Ben Chugg and Michael I. Jordan and Aaditya Ramdas},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.18336},
eprint = {2610.18336},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.18336},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Strategic Multi-Agent Resource Allocation via Statistical Contracts
AU - Ben Chugg
AU - Michael I. Jordan
AU - Aaditya Ramdas
PY - 2026
DA - 2026/10/13
PB - arXiv
DO - 10.48550/arxiv.2610.18336
UR - https://arxiv.org/abs/2610.18336
AB - We study a class of strategic hypothesis testing problems in which a principal aims to allocate resources among competing agents who possess data or data-generating mechanisms that may be relevant to the principal's goals. Each agent can pay a participation cost to opt into a statistical contract, in which case they generate data from a private distribution and receive an allocation based on a predetermined (and publicly known) mechanism. Each agent is either "null" or "non-null" and the principal's goal is to design the contract to limit the allocation to the former while maximizing transactions with the latter. Using e-values, we define a "continuous-closure," a set of allocations which prevents null agents from profiting in expectation and provides post-hoc risk control for general loss functions under arbitrary dependence. When the loss is the fraction of resources allocated to null agents, the region admits polynomial-time linear optimization. We also give explicit, interpretable closed-form approximations, and we analyze participation from a non-null agent's perspective, giving conditions under which entry into the contract is profitable. Finally, we extend the framework to support online arrival of the agents, in which case the principal has to make irrevocable on-the-fly decisions, and provide a method which gives time-uniform error-control in this setting.
ER -