Sobhani, Mahbub E.Sayeedi, Md Faiyaz AbdullahAlam, Mohammad NehadProgga, Proma HossainShatabda, Swakkhar2026-09-072026-09-072026-01-01E Sobhani, M., Sayeedi, Md. F. A., Alam, M. N., Progga, P. H., & Shatabda, S. (2026). Do multi-agents solve better than single? Evaluating agentic frameworks for diagram-grounded geometry problem solving and reasoning. Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop), 27–47. https://doi.org/10.18653/v1/2026.eacl-srw.497988917638382-s2.0-105040187831https://hdl.handle.net/10361/29790Diagram-grounded geometry problem solving is a critical benchmark for multimodal large language models (MLLMs), yet the benefits of multi-agent design over single-agent remain unclear. We systematically compare single-agent and multi-agent pipelines on four visual math benchmarks: Geometry3K, MathVerse, OlympiadBench, and We-Math. For open-source models, multi-agent consistently improves performance. For example, Qwen-2.5-VL (7B) gains +6.8 points and Qwen-2.5VL (32B) gains +3.3 on Geometry3K, and both Qwen-2.5-VL variants see further gains on OlympiadBench and We-Math. In contrast, the closed-source Gemini-2.0-Flash generally performs better in single-agent mode on classic benchmarks, while multi-agent yields only modest improvements on the newer We-Math dataset. These findings show that multi-agent pipelines provide clear benefits for open-source models and can assist strong proprietary systems on newer, less familiar benchmarks, but agentic decomposition is not universally optimal. All code, data, and reasoning files are available at https://github.com/faiyazabdullah/Interpreter-Solver. © 2026 Association for Computational Linguistics27 - 47en-USBenchmarkingComputational geometryComputational linguisticsComputer hardware description languagesIntelligent agentsNatural language processing systemsOpen source softwareOpen systemsOptimal systemsPipelinesProblem solvingGeometry--Data processing.Artificial intelligence--Evaluation.Multimodal user interfaces (Computer systems).Natural language processing (Computer science).Conference Paper10.18653/v1/2026.eacl-srw.4