Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lee, YenTing, Koneru, Keerthi, Moslemi, Zahra, Kumar, Sheethal, Radhakrishnan, Ramesh
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2601.11903
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911382409052160
author Lee, YenTing
Koneru, Keerthi
Moslemi, Zahra
Kumar, Sheethal
Radhakrishnan, Ramesh
author_facet Lee, YenTing
Koneru, Keerthi
Moslemi, Zahra
Kumar, Sheethal
Radhakrishnan, Ramesh
contents Evaluating large language model (LLM)-based multi-agent systems remains a critical challenge, as these systems must exhibit reliable coordination, transparent decision-making, and verifiable performance across evolving tasks. Existing evaluation approaches often limit themselves to single-response scoring or narrow benchmarks, which lack stability, extensibility, and automation when deployed in enterprise settings at multi-agent scale. We present AEMA (Adaptive Evaluation Multi-Agent), a process-aware and auditable framework that plans, executes, and aggregates multi-step evaluations across heterogeneous agentic workflows under human oversight. Compared to a single LLM-as-a-Judge, AEMA achieves greater stability, human alignment, and traceable records that support accountable automation. Our results on enterprise-style agent workflows simulated using realistic business scenarios demonstrate that AEMA provides a transparent and reproducible pathway toward responsible evaluation of LLM-based multi-agent systems. Keywords Agentic AI, Multi-Agent Systems, Trustworthy AI, Verifiable Evaluation, Human Oversight
format Preprint
id arxiv_https___arxiv_org_abs_2601_11903
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AEMA: Verifiable Evaluation Framework for Trustworthy and Controlled Agentic LLM Systems
Lee, YenTing
Koneru, Keerthi
Moslemi, Zahra
Kumar, Sheethal
Radhakrishnan, Ramesh
Artificial Intelligence
Evaluating large language model (LLM)-based multi-agent systems remains a critical challenge, as these systems must exhibit reliable coordination, transparent decision-making, and verifiable performance across evolving tasks. Existing evaluation approaches often limit themselves to single-response scoring or narrow benchmarks, which lack stability, extensibility, and automation when deployed in enterprise settings at multi-agent scale. We present AEMA (Adaptive Evaluation Multi-Agent), a process-aware and auditable framework that plans, executes, and aggregates multi-step evaluations across heterogeneous agentic workflows under human oversight. Compared to a single LLM-as-a-Judge, AEMA achieves greater stability, human alignment, and traceable records that support accountable automation. Our results on enterprise-style agent workflows simulated using realistic business scenarios demonstrate that AEMA provides a transparent and reproducible pathway toward responsible evaluation of LLM-based multi-agent systems. Keywords Agentic AI, Multi-Agent Systems, Trustworthy AI, Verifiable Evaluation, Human Oversight
title AEMA: Verifiable Evaluation Framework for Trustworthy and Controlled Agentic LLM Systems
topic Artificial Intelligence
url https://arxiv.org/abs/2601.11903