Do Multi-Agents Solve Better Than Single? Evaluating Agentic Frameworks for Diagram-Grounded Geometry Problem Solving and Reasoning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917154427764736 |
|---|---|
| author | Sobhani, Mahbub E Sayeedi, Md. Faiyaz Abdullah Alam, Mohammad Nehad Progga, Proma Hossain Shatabda, Swakkhar |
| author_facet | Sobhani, Mahbub E Sayeedi, Md. Faiyaz Abdullah Alam, Mohammad Nehad Progga, Proma Hossain Shatabda, Swakkhar |
| contents | Diagram-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-2.5-VL (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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_16698 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Do Multi-Agents Solve Better Than Single? Evaluating Agentic Frameworks for Diagram-Grounded Geometry Problem Solving and Reasoning Sobhani, Mahbub E Sayeedi, Md. Faiyaz Abdullah Alam, Mohammad Nehad Progga, Proma Hossain Shatabda, Swakkhar Artificial Intelligence Computational Geometry Diagram-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-2.5-VL (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 |
| title | Do Multi-Agents Solve Better Than Single? Evaluating Agentic Frameworks for Diagram-Grounded Geometry Problem Solving and Reasoning |
| topic | Artificial Intelligence Computational Geometry |
| url | https://arxiv.org/abs/2512.16698 |