SIGMA: Search-Augmented On-Demand Knowledge Integration for Agentic Mathematical Reasoning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Asgarov, Ali, Suleymanov, Umid, Khatri, Aadyant
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908622779318272
author Asgarov, Ali
Suleymanov, Umid
Khatri, Aadyant
author_facet Asgarov, Ali
Suleymanov, Umid
Khatri, Aadyant
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_27568
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SIGMA: Search-Augmented On-Demand Knowledge Integration for Agentic Mathematical Reasoning
Asgarov, Ali
Suleymanov, Umid
Khatri, Aadyant
Artificial Intelligence
Computation and Language
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.
title SIGMA: Search-Augmented On-Demand Knowledge Integration for Agentic Mathematical Reasoning
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2510.27568