Agentic Workflows for Resolving Conflict Over Shared Resources: A Power Grid Application

TL;DR

This paper introduces a domain-agnostic deconfliction framework for coordinating multiple LLM-based agents managing shared resources, demonstrated through a power grid case study involving conflicting optimization applications.

Contribution

It proposes a novel iterative weighted-consensus mechanism and three conflict resolution modes, enhancing multi-agent decision coordination without requiring complex optimization solutions.

Findings

Framework effectively resolves conflicts in power grid management scenarios.

Supports both numeric and non-numeric decision-making processes.

Demonstrates domain-agnostic applicability across different applications.

Abstract

The increasing use of LLM-based agents to support decision-making and control across diverse domains motivates the need for systematic deconfliction of their proposed actions. We present a deconfliction framework for coordinating multiple agents that formally encapsulate individual applications, each proposing potentially conflicting actions over shared resources. Conflicts are resolved through three deconfliction modes: bilateral negotiation, structured mediation, and procedural (deterministic) deconfliction. We define design principles for large language model-based client agents, including a chain-of-thought style reasoning process, and introduce an iterative weighted-consensus mechanism that does not require the applications themselves to solve optimization problems. The framework is domain agnostic and supports both numeric and non-numeric decisions. Its performance is demonstrated on a power distribution use case with conflicting advanced distribution management system applications for cost optimization and resilience, coordinating diesel generators and battery energy storage systems.