{"slug": "evaluating-sagemath-augmented-llm-agents-for-computational-and-experimental", "title": "Evaluating SageMath-Augmented LLM Agents for Computational and Experimental Mathematics", "summary": "Researchers proposed a ReAct-style agentic setup combining LLM reasoning with SageMath for solving research-level mathematical problems, achieving an average performance gain of 9.7 percentage points across models. GPT-5.5 achieved the highest solve rate of 75.2% with the lowest token usage, while Qwen 3.7-Max benefited most from SageMath access. The findings suggest CAS-augmented agents are promising for computational mathematics and automated conjecture discovery.", "body_md": "arXiv:2607.06820v1 Announce Type: new\nAbstract: Recent advances in AI for Mathematics have focused largely on autoformalization and theorem proving, leaving the role of Computer Algebra Systems (CAS) in agentic LLM workflows underexplored. We propose a ReAct-style agentic setup that combines LLM reasoning with verifiable feedback from SageMath, together with Context7 for the up-to-date documentation. We evaluate this agentic setup across frontier models for solving research-level mathematical problems from the RealMath benchmark in a setting that emulates a computational-mathematics research loop. We also propose a refinement to the RealMath benchmark by introducing a multi-step post-processing procedure and a multi-stage validation pipeline, both of which improve the quality and reliability of the extracted problem set. Our experiments reveal substantial performance gains from SageMath access across all evaluated models on +9.7~pp on average, the gains range from 1.5~pp to 27.8~pp and narrow the gap between open-weight and closed models. Qwen~3.7-Max benefits from SageMath the most, while GPT-5.5 achieves the highest solve rate of $75.2\\%$ and the lowest token usage among tool-enabled configurations. Our findings suggest that CAS-augmented agents represent a promising direction for assisting mathematicians in computational exploration, and we believe that this work is a step towards automated conjecture discovery. The project repository is available online.", "url": "https://wpnews.pro/news/evaluating-sagemath-augmented-llm-agents-for-computational-and-experimental", "canonical_source": "https://arxiv.org/abs/2607.06820", "published_at": "2026-07-09 04:00:00+00:00", "updated_at": "2026-07-09 04:17:05.484130+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-agents", "ai-research"], "entities": ["SageMath", "GPT-5.5", "Qwen 3.7-Max", "RealMath", "Context7"], "alternates": {"html": "https://wpnews.pro/news/evaluating-sagemath-augmented-llm-agents-for-computational-and-experimental", "markdown": "https://wpnews.pro/news/evaluating-sagemath-augmented-llm-agents-for-computational-and-experimental.md", "text": "https://wpnews.pro/news/evaluating-sagemath-augmented-llm-agents-for-computational-and-experimental.txt", "jsonld": "https://wpnews.pro/news/evaluating-sagemath-augmented-llm-agents-for-computational-and-experimental.jsonld"}}