#253 Search o1: Agentic Search-Enhanced Large Reasoning Models

Large reasoning models (LRMs) like OpenAI-o1 have demonstrated impressive long stepwise reasoning capabilities through large-scale reinforcement learning. However, their extended reasoning processes often suffer from knowledge insufficiency, leading to frequent uncertainties and potential errors. To address this limitation, Search-o1 is introduced, a framework that enhances LRMs with an agentic retrieval-augmented generation (RAG) mechanism and a Reason-in-Documents module for refining retrieved documents. Search-o1 integrates an agentic search workflow into the reasoning process, enabling dynamic retrieval of external knowledge when LRMs encounter uncertain knowledge points. Additionally, due to the verbose nature of retrieved documents, a separate Reason-in-Documents module is designed to deeply analyze the retrieved information before injecting it into the reasoning chain, minimizing noise and preserving coherent reasoning flow. Extensive experiments on complex reasoning tasks in science, mathematics, and coding, as well as six open-domain QA benchmarks, demonstrate the strong performance of Search-o1. This approach enhances the trustworthiness and applicability of LRMs in complex reasoning tasks, paving the way for more reliable and versatile intelligent systems. In this video, I talk about the following: What is the Search-o1 framework? How does Search-o1 work? How does Search-o1 perform? Example of Search-o1 in action. For more details, please look at https://arxiv.org/pdf/2501.05366 and https://github.com/sunnynexus/Search-o1 Li, Xiaoxi, Guanting Dong, Jiajie Jin, Yuyao Zhang, Yujia Zhou, Yutao Zhu, Peitian Zhang, and Zhicheng Dou. "Search-o1: Agentic search-enhanced large reasoning models." arXiv preprint arXiv:2501.05366 (2025). Thanks for watching! LinkedIn: http://aka.ms/manishgupta HomePage: https://sites.google.com/view/manishg/