Salvato in:
Dettagli Bibliografici
Autori principali: Poudel, Shiva, Ramachandran, Thiagarajan, Vasios, Orestis, Reiman, Andrew P.
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2604.09823
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915931786051584
author Poudel, Shiva
Ramachandran, Thiagarajan
Vasios, Orestis
Reiman, Andrew P.
author_facet Poudel, Shiva
Ramachandran, Thiagarajan
Vasios, Orestis
Reiman, Andrew P.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_09823
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Agentic Workflows for Resolving Conflict Over Shared Resources: A Power Grid Application
Poudel, Shiva
Ramachandran, Thiagarajan
Vasios, Orestis
Reiman, Andrew P.
Systems and Control
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.
title Agentic Workflows for Resolving Conflict Over Shared Resources: A Power Grid Application
topic Systems and Control
url https://arxiv.org/abs/2604.09823