多智能体动态检索知识，提升数学推理准确率7.4%
SIGMA: Search-Augmented On-Demand Knowledge Integration for Agentic Mathematical Reasoning
- 用多个专用智能体分别搜索、推理并由调解器整合
- 在MATH500等挑战性数据集上性能提升7.4%以上
- 适合需要复杂知识融合的数学与科学问题求解
解决数学推理问题不仅需要精准获取相关知识，还需多步缜密思考。但现有检索增强模型常依赖单一视角、采用僵化搜索策略，难以有效整合多源信息。我们提出SIGMA（Search-Augmented On-Demand Knowledge Integration for AGentic Mathematical reAsoning），一个统一框架，通过专业化智能体独立推理、执行定向搜索，并经由调解机制合成结果。每个智能体生成假设文本以优化其分析视角下的检索效果，确保知识整合既具上下文敏感性又计算高效。在MATH500、AIME及博士级科学问答GPQA等挑战性基准上，SIGMA持续超越开源与闭源系统，实现绝对性能提升7.4%。结果表明，多智能体、按需的知识融合显著提升推理准确率与效率，为复杂知识密集型问题求解提供可扩展方案。代码将于发表后公开。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。