awesome-agentic-search
🔍 Awesome Agentic Search is a curated list of papers, tools, and resources on agentic search—where AI agents plan, search, and reason to answer complex questions. Explore the latest research, benchmarks, and industry solutions for next-gen search-enhanced AI! 🤖✨
https://github.com/qhjqhj00/awesome-agentic-search
Last synced: 6 days ago
JSON representation
-
📚 Papers
-
🎓 Training-based
- An Empirical Study on Reinforcement Learning for Reasoning-Search Interleaved LLM Agents - R1?style=social)
- WebThinker: Empowering Large Reasoning Models with Deep Research Capability - NLPIR/WebThinker?style=social)
- DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments - NLP/DeepResearcher)](https://github.com/GAIR-NLP/DeepResearcher)
- R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning - Searcher)](https://github.com/RUCAIBox/R1-Searcher)
- Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning
- WebDancer: Towards Autonomous Information Seeking Agency - NLP/WebAgent)](https://github.com/Alibaba-NLP/WebAgent)
- ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning - RL/ReCall)](https://github.com/Agent-RL/ReCall)
- SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis
- ZeroSearch: Incentivize the Search Capability of LLMs without Searching - NLP/ZeroSearch)](https://github.com/Alibaba-NLP/ZeroSearch)
- Chain-of-Retrieval Augmented Generation
- IKEA: Reinforced Internal-External Knowledge Synergistic Reasoning for Efficient Adaptive Search Agent - r1)](https://github.com/hzy312/knowledge-r1)
- Scent of Knowledge: Optimizing Search-Enhanced Reasoning with Information Foraging
- R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning - Searcher-plus)](https://github.com/RUCAIBox/R1-Searcher-plus)
- - R1?style=social)
- Search and Refine During Think: Autonomous Retrieval-Augmented Reasoning of LLMs - cn/AutoRefine)](https://github.com/syr-cn/AutoRefine)
- Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning - Star)](https://github.com/dongguanting/Tool-Star)
- OTC: Optimal Tool Calls via Reinforcement Learning
-
🔄 Workflow-based
- Search-o1: Agentic Search-Enhanced Large Reasoning Models - o1?style=social)](https://github.com/sunnynexus/Search-o1)
- Agentic Reasoning: Reasoning LLMs with Tools for the Deep Research - Reasoning)](https://github.com/theworldofagents/Agentic-Reasoning)
- Coding Agents with Multimodal Browsing are Generalist Problem Solvers - Versa)](https://github.com/adityasoni9998/OpenHands-Versa)
-
📊 Evaluation and Dataset
- Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge - NLP-Group/Mind2Web-2)](https://github.com/OSU-NLP-Group/Mind2Web-2)
- InfoDeepSeek: Benchmarking Agentic Information Seeking for Retrieval-Augmented Generation
- BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents - evals)](https://github.com/openai/simple-evals)
- HealthBench: Evaluating Large Language Models Towards Improved Human Health - evals)](https://github.com/openai/simple-evals)
- ManuSearch: Democratizing Deep Search in Large Language Models with a Transparent and Open Multi-Agent Framework
- WebWalker: Benchmarking LLMs in Web Traversal - NLP/WebAgent)](https://github.com/Alibaba-NLP/WebAgent)
- DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
-
🖼️ Multi-Modal
- Multimodal-Search-R1: Incentivizing LMMs to Search - Lab/multimodal-search-r1)](https://github.com/EvolvingLMMs-Lab/multimodal-search-r1)
- Multimodal DeepResearcher: Generating Text-Chart Interleaved Reports From Scratch with Agentic Framework
- VideoDeepResearch: Long Video Understanding With Agentic Tool Using - 2000/VideoDeepResearch)](https://github.com/yhy-2000/VideoDeepResearch)
-
📚 Perspective and Survey
-
-
🎮 Demo
-
🏢 Industry Solutions
-
-
📝 Slides
-
🏢 Industry Solutions
-