{"ID":2847662,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.27568","arxiv_id":"2510.27568","title":"SIGMA: Search-Augmented On-Demand Knowledge Integration for Agentic Mathematical Reasoning","abstract":"Solving mathematical reasoning problems requires not only accurate access to relevant knowledge but also careful, multi-step thinking. However, current retrieval-augmented models often rely on a single perspective, follow inflexible search strategies, and struggle to effectively combine information from multiple sources. We introduce SIGMA (Search-Augmented On-Demand Knowledge Integration for AGentic Mathematical reAsoning), a unified framework that orchestrates specialized agents to independently reason, perform targeted searches, and synthesize findings through a moderator mechanism. Each agent generates hypothetical passages to optimize retrieval for its analytic perspective, ensuring knowledge integration is both context-sensitive and computation-efficient. When evaluated on challenging benchmarks such as MATH500, AIME, and PhD-level science QA GPQA, SIGMA consistently outperforms both open- and closed-source systems, achieving an absolute performance improvement of 7.4%. Our results demonstrate that multi-agent, on-demand knowledge integration significantly enhances both reasoning accuracy and efficiency, offering a scalable approach for complex, knowledge-intensive problem-solving. We will release the code upon publication.","short_abstract":"Solving mathematical reasoning problems requires not only accurate access to relevant knowledge but also careful, multi-step thinking. However, current retrieval-augmented models often rely on a single perspective, follow inflexible search strategies, and struggle to effectively combine information from multiple source...","url_abs":"https://arxiv.org/abs/2510.27568","url_pdf":"https://arxiv.org/pdf/2510.27568v1","authors":"[\"Ali Asgarov\",\"Umid Suleymanov\",\"Aadyant Khatri\"]","published":"2025-10-31T15:51:00Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.CL\"]","methods":"[]","has_code":false}