RUC-NLPIR/Search-o1
🔍 Search-o1: Agentic Search-Enhanced Large Reasoning Models [EMNLP 2025]
Integrates agentic retrieval-augmented generation (RAG) with a "Reason-in-Documents" module that allows reasoning models to dynamically trigger web searches during inference when encountering knowledge gaps, then seamlessly incorporate retrieved documents back into the reasoning chain. Supports multiple reasoning benchmarks (GPQA, MATH, AMC, AIME, code tasks) and open-domain QA through modular pipelines that enable batch generation with interleaved search across different LRM backbones.
1,182 stars.
Stars
1,182
Forks
104
Language
Python
License
MIT
Category
Last pushed
Nov 17, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/RUC-NLPIR/Search-o1"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
deepsense-ai/ragbits
Building blocks for rapid development of GenAI applications
infiniflow/ragflow
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses...
GiovanniPasq/agentic-rag-for-dummies
A modular Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes.
truefoundry/cognita
RAG (Retrieval Augmented Generation) Framework for building modular, open source applications...
NVIDIA/context-aware-rag
Context-Aware RAG library for Knowledge Graph ingestion and retrieval functions.