Research

Paper

TESTING March 12, 2026

Verified Multi-Agent Orchestration: A Plan-Execute-Verify-Replan Framework for Complex Query Resolution

Authors

Xing Zhang, Yanwei Cui, Guanghui Wang, Qucy Wei Qiu, Ziyuan Li, Fangwei Han, Yajing Huang, Hengzhi Qiu, Bin Zhu, Peiyang He

Abstract

We present Verified Multi-Agent Orchestration (VMAO), a framework that coordinates specialized LLM-based agents through a verification-driven iterative loop. Given a complex query, our system decomposes it into a directed acyclic graph (DAG) of sub-questions, executes them through domain-specific agents in parallel, verifies result completeness via LLM-based evaluation, and adaptively replans to address gaps. The key contributions are: (1) dependency-aware parallel execution over a DAG of sub-questions with automatic context propagation, (2) verification-driven adaptive replanning that uses an LLM-based verifier as an orchestration-level coordination signal, and (3) configurable stop conditions that balance answer quality against resource usage. On 25 expert-curated market research queries, VMAO improves answer completeness from 3.1 to 4.2 and source quality from 2.6 to 4.1 (1-5 scale) compared to a single-agent baseline, demonstrating that orchestration-level verification is an effective mechanism for multi-agent quality assurance.

Metadata

arXiv ID: 2603.11445
Provider: ARXIV
Primary Category: cs.AI
Published: 2026-03-12
Fetched: 2026-03-13 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.11445v1</id>\n    <title>Verified Multi-Agent Orchestration: A Plan-Execute-Verify-Replan Framework for Complex Query Resolution</title>\n    <updated>2026-03-12T02:10:10Z</updated>\n    <link href='https://arxiv.org/abs/2603.11445v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.11445v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>We present Verified Multi-Agent Orchestration (VMAO), a framework that coordinates specialized LLM-based agents through a verification-driven iterative loop. Given a complex query, our system decomposes it into a directed acyclic graph (DAG) of sub-questions, executes them through domain-specific agents in parallel, verifies result completeness via LLM-based evaluation, and adaptively replans to address gaps. The key contributions are: (1) dependency-aware parallel execution over a DAG of sub-questions with automatic context propagation, (2) verification-driven adaptive replanning that uses an LLM-based verifier as an orchestration-level coordination signal, and (3) configurable stop conditions that balance answer quality against resource usage. On 25 expert-curated market research queries, VMAO improves answer completeness from 3.1 to 4.2 and source quality from 2.6 to 4.1 (1-5 scale) compared to a single-agent baseline, demonstrating that orchestration-level verification is an effective mechanism for multi-agent quality assurance.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.MA'/>\n    <published>2026-03-12T02:10:10Z</published>\n    <arxiv:comment>ICLR 2026 Workshop on MALGAI</arxiv:comment>\n    <arxiv:primary_category term='cs.AI'/>\n    <author>\n      <name>Xing Zhang</name>\n    </author>\n    <author>\n      <name>Yanwei Cui</name>\n    </author>\n    <author>\n      <name>Guanghui Wang</name>\n    </author>\n    <author>\n      <name>Qucy Wei Qiu</name>\n    </author>\n    <author>\n      <name>Ziyuan Li</name>\n    </author>\n    <author>\n      <name>Fangwei Han</name>\n    </author>\n    <author>\n      <name>Yajing Huang</name>\n    </author>\n    <author>\n      <name>Hengzhi Qiu</name>\n    </author>\n    <author>\n      <name>Bin Zhu</name>\n    </author>\n    <author>\n      <name>Peiyang He</name>\n    </author>\n  </entry>"
}