SGVEF-LOOP: Coverage-Guided Progressive Topological Exploration and Fact-Grounded Metamorphic Evaluation for MCP Agents

Zenghao Liu, Yansong Zhang


Abstract
The rapid expansion of the Model Context Protocol (MCP) ecosystem introduces a combinatorially complex tool space, rendering existing frameworks inadequate for comprehensive agent evaluation. To address this problem, we propose SGVEF-LOOP, a coverage-guided framework for progressive topological exploration and fact-augmented metamorphic testing. SGVEF operates via a synergistic closed loop: it navigates sparse regions using adaptive sampling, synthesizes oracle-free metamorphic pairs grounded in static knowledge, enforces dual-constraint validation to ensure consistency and solvability, and leverages execution feedback to iteratively optimize exploration. Deploying this framework yields a high-fidelity benchmark achieving 100% node coverage and saturating 80.54% of the theoretical transition bound (estimated via Chao1). Evaluation of 8 diverse MCP Agents reveals capability stratification and exposes critical behavioral anomalies—such as reasoning instability—that conventional metrics fail to capture. Consequently, this work establishes a generalizable paradigm for scalable, rigorous agent evaluation in dynamic environments.
Anthology ID:
2026.acl-long.1224
Volume:
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2026
Address:
San Diego, California, United States
Editors:
Maria Liakata, Viviane P. Moreira, Jiajun Zhang, David Jurgens
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
26573–26599
Language:
URL:
https://aclanthology.org/2026.acl-long.1224/
DOI:
Bibkey:
Cite (ACL):
Zenghao Liu and Yansong Zhang. 2026. SGVEF-LOOP: Coverage-Guided Progressive Topological Exploration and Fact-Grounded Metamorphic Evaluation for MCP Agents. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 26573–26599, San Diego, California, United States. Association for Computational Linguistics.
Cite (Informal):
SGVEF-LOOP: Coverage-Guided Progressive Topological Exploration and Fact-Grounded Metamorphic Evaluation for MCP Agents (Liu & Zhang, ACL 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.acl-long.1224.pdf
Checklist:
 2026.acl-long.1224.checklist.pdf