Agentic Workflows for Resolving Conflict Over Shared Resources: A Power Grid Application
For developers of multi-agent systems in critical infrastructure, this work provides a practical framework for resolving conflicts without requiring agents to solve optimization problems.
The paper presents a domain-agnostic deconfliction framework for coordinating multiple LLM-based agents that propose conflicting actions over shared resources, demonstrated on a power grid use case with conflicting cost optimization and resilience applications.
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.