Chinese version: readme.zh.md

Survey

Title	site	Rec
From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents	Awesome-Deep-Research	⭐️⭐️⭐️
Deep Research Agents: A Systematic Examination And Roadmap	awesome-deep-research-agent	⭐️
A Comprehensive Survey of Deep Research: Systems, Methodologies, and Applications	deepresearch	⭐️

Resource indexes (Awesome / List)

Description	Repository	List	Rec
Curated site paired with the first survey paper	DavidZWZ / Awesome-Deep-Research	✓	⭐️⭐️⭐️
List paired with the second roadmap paper	ai-agents-2030 / awesome-deep-research-agent	✓	⭐️
List paired with the third survey paper	scienceaix / deepresearch	✓	⭐️

Open-Source Implementations

Sorted by GitHub repository stars (descending); counts follow Shields.io github/stars labels (approximate for k/m suffixes).

Open-source list and Works papers are aligned with DavidZWZ/Awesome-Deep-Research plus this repo’s extra rows; order is by stars, not upstream list order.

Project	Category	List	Rec	Desc	analysis
bytedance / deer-flow	End-to-end deep research agent	✓	⭐️⭐️⭐️	Long-horizon SuperAgent: research, code, create; sandboxes, subagents.
multi-agent research (Anthropic cookbook) · Blog	Tool-augmented reasoning & tutorial scaffolding			Official patterns for multi-agent research.
assafelovic / gpt-researcher	End-to-end deep research agent			Autonomous comprehensive research agent.
dzhng / deep-research	End-to-end deep research agent	✓	⭐️⭐️	Iterative web research: search, scrape, LLM synthesis (Aomni).
Alibaba-NLP / DeepResearch	End-to-end deep research agent	✓	⭐️⭐️⭐️	Tongyi open deep-research agent.
google-gemini / gemini-fullstack-langgraph-quickstart	Tool-augmented reasoning & tutorial scaffolding	✓	⭐️⭐️⭐️	Gemini + LangGraph fullstack agent quickstart.	⭐️
langchain-ai / open_deep_research	End-to-end deep research agent	✓	⭐️⭐️⭐️	LangChain official deep-research stack.	⭐️
langchain-ai / local-deep-researcher	Local / private data / privacy	✓	⭐️⭐️	Fully local web research and report writing.
zilliztech / deep-searcher	Local / private data / privacy	✓	⭐️⭐️	Reason and search on private data (Python).	⭐️
MervinPraison / PraisonAI	Multi-agent framework (incl. deep research)		⭐️⭐️	Production-oriented multi-agent stack with built-in deep research flows.
nickscamara / open-deep-research	End-to-end deep research agent	✓	⭐️⭐️	Open clone–style agent; heavy use of Firecrawl for web data.
HKUDS / AI-Researcher	Scientific discovery	✓	⭐️⭐️	NeurIPS-style autonomous scientific innovation agent.
jina-ai / node-DeepResearch	End-to-end deep research agent	✓	⭐️⭐️⭐️	TypeScript agent: search, read pages, reason until answer or budget.	⭐️
u14app / deep-research	End-to-end deep research agent			Deep research platform (u14app).
PeterGriffinJin / Search-R1	Search capability & RL / training	✓	⭐️⭐️	RL framework: interleaved reasoning + search (veRL).
LearningCircuit / local-deep-research	Local / private data / privacy	✓	⭐️⭐️	Local + cloud LLMs; many sources (arXiv, PubMed, web, files).
sentient-agi / OpenDeepSearch	Search capability & RL / training	✓	⭐️⭐️	Open deep search / reasoning agents (paper line).
SkyworkAI / DeepResearchAgent	End-to-end deep research agent	✓	⭐️⭐️	Hierarchical multi-agent; research and general tasks.
mshumer / OpenDeepResearcher	Tool-augmented reasoning & tutorial scaffolding	✓	⭐️	Notebook-oriented open deep researcher demo.
btahir / open-deep-research	End-to-end deep research agent			Another open deep-research implementation (≠ nickscamara).
murtaza-nasir / maestro	Application layer	✓	⭐️	App for streamlining complex research workflows.
HKUDS / Auto-Deep-Research	End-to-end deep research agent			Automated deep-research agent (HKUDS).
gomate-community / TrustRAG	RAG / trusted I/O	✓	⭐️	Trusted-input / trusted-output RAG framework.
Alibaba-NLP / ZeroSearch	Search capability & RL / training	✓	⭐️⭐️	Train search ability without real search (simulation).
deansaco / r1-reasoning-rag	RAG / trusted I/O		⭐️	Reasoning-augmented RAG.
antgroup / Research-Venus	End-to-end deep research agent		⭐️	Automated deep-research agent (AtomSearcher / Research Venus line).
foreveryh / langgraph-deep-research	Tool-augmented reasoning & tutorial scaffolding		⭐️	LangGraph deep-research workflows.
liyuan24 / nanoDeepResearch	End-to-end deep research agent		⭐️	Lightweight deep research toolkit.
human-re / Agentic-Reasoning	Tool-augmented reasoning & tutorial scaffolding	✓	⭐️	Tool use integrated into LLM reasoning (research line).

Works

Title	Date & Code	Base model	Optimization	Search Engine	Agent Architecture
Tongyi DeepResearch Technical Report	2025/10/28	Qwen3-30B-A3B-Base	SFT, RL	Web Search	Single-Agent
ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization	2025/09/16	Qwen3-30B-A3B-Thinking	GRPO, SFT	Web Search	Single-Agent
WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research	2025/09/16	Qwen3-30B-A3B-Instruct	SFT	Web Search	Single-Agent
WebResearcher: Unleashing Unbounded Reasoning Capability in Long-Horizon Agents	2025/09/16	Qwen3-30B-A3B	RFT, RL	Web Search	Multi-Agent
WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable RL	2025/09/16	Qwen3-30B-A3B	SFT, RL	Web Search, Local Retrieval	Single-Agent
AutoAgent: A Fully-Automated and Zero-Code Framework for LLM Agents	2025/02/18	Claude3.5-Sonnet	Prompting	Web Search	Multi-Agent
Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning🔥	2025/03/12	Qwen2.5-7B-Instruct, Qwen2.5-7B-Base, Qwen2.5-3B-Instruct, Qwen2.5-3B-Base	RL(PPO, GRPO)	Web Search	Single-Agent
Open Deep Search: Democratizing Search with Open-source Reasoning Agents	2025/03/26	Llama3.1-70B, Deepseek-R1	Prompting	Web Search	Single-Agent
Webthinker: Empowering large reasoning models with deep research capability	2025/04/30	GPT-o1, GPT-o3, Deepseek-R1, QwQ-32B, Qwen2.5-32B-Instruct	RL(DPO)	Web Search	Single-Agent
ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning	2025/03/25	Qwen2.5-7B-Instruct, Qwen2.5-32B-Instruct	RL(GRPO)	Web Search	Single-Agent
ZeroSearch: Incentivize the Search Capability of LLMs without Searching🔥	2025/05/07	Qwen2.5-3B-Base, Qwen2.5-7B-Base, Qwen2.5-7B-Instruct, Qwen2.5-3B-Instruct, Llama3.2-3B-Instruct, Llama3.2-3B-Base	RL(Reinforce, GRPO, PPO)	Web Search	Single-Agent
Enterprise Deep Research: Steerable MultiAgent Deep Research for Enterprise Analytics	2025/10/20	–	Prompting	Web Search	Multi-Agent
Search-o1: Agentic Search-Enhanced Large Reasoning Models	2025/01/09	QwQ-32B-Preview	Prompting	Web Search	Single-Agent
Beyond Outlining: Heterogeneous Recursive Planning for Adaptive Long-form Writing with Language Models	2025/03/11	GPT-4o, Claude3.5-Sonnet	Prompting	Web Search	Multi-Agent
s3 - Efficient Yet Effective Search Agent Training via RL	2025/05/20	Qwen2.5-7B-Instruct	RL(PPO)	Local Retrieval	Single-Agent
DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments	2025/03/26	Qwen2.5-7B-Instruct	RL(GRPO)	Web Search	Multi-Agent
R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning	2025/03/07	Qwen2.5-7B-Base, Llama3.1-8B-Instruct	SFT, RL(GRPO, Reinforce++)	Web Search, Local Retrieval	Single-Agent
CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery	2026/04/02	Claude (agent backbone)	Evolutionary Search (heartbeat-guided)	–	Multi-Agent
Dr. Zero: Self-Evolving Search Agents without Training Data	2026/01/11	Qwen2.5-3B-Instruct, Qwen2.5-7B-Instruct	HRPO	Web Search	Multi-Agent
MMSearch-R1: Incentivizing LMMs to Search	2025/06/25	Qwen2.5-VL-7B	RL(GRPO)	Web Search	Single-Agent
Atom-Searcher: Enhancing Agentic Deep Research via Fine-Grained Atomic Thought Reward	2025/08/18	Qwen2.5-7B	RL(GRPO)	Web Search	Single-Agent
Multi-Agent Deep Research: Training Multi-Agent Systems with M-GRPO	2025/11/17	Qwen3-30B-A3B	M-GRPO	Web Search	Multi-Agent
MaskSearch: A Universal Pre-Training Framework to Enhance Agentic Search Capability	2025/05/27	Llama3.1-8B, Llama3.2-3B, Llama3.2-1B, Llama3, Qwen2.5-7B, Qwen2.5-3B, Qwen2.5-1.5B, Qwen2.5	SFT, RL(DAPO)	Local Retrieval	Multi-Agent
VideoDeepResearch: Long Video Understanding With Agentic Tool Using	2025/06/12	GPT-4o, Gemini1.5-pro, Qwen2.5-VL-72B-Instruct	Prompting	Local Retrieval	Multi-Agent
RAG-Gym: Systematic Optimization of Language Agents for Retrieval-Augmented Generation	2025/05/31	Llama3.1-8B-Instruct, Qwen2.5-7B-Instruct, GPT-4o-mini	SFT, RL(PPO, DPO)	Local Retrieval	Single-Agent
SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis	2025/05/25	Qwen2.5-7B-Instruct, Qwen2.5-32B-Instruct, DeepseekDistilled-Qwen2.5-32B, QwQ-32B	SFT	Web Search	Single-Agent
WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents	2025/09/08	Qwen3-8B	GRPO, SFT	Web Search	Single-Agent
WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning	2025/05/22	Qwen2.5-3B, Llama3.1-8B	SFT, RL(M-GRPO)	Web Search	Single-Agent
Demystifying and Enhancing the Efficiency of Large Language Model Based Search Agents	2025/05/17	Qwen2.5-14B, Qwen2.5-7B	Prompting	Local Retrieval	Single-Agent
R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning	2025/05/22	Qwen2.5-7B-Instruct	SFT, RL	Local Retrieval	Single-Agent
Pangu Ultra: Pushing the Limits of Dense Large Language Models on Ascend NPUs	2025/04/11	Pangu Ultra-135B	SFT, RL	Local Retrieval	Single-Agent
Reinforced Internal-External Knowledge Synergistic Reasoning for Efficient Adaptive Search Agent	2025/05/12	Qwen2.5-3B-Instruct, Qwen2.5-7B-Instruct	RL(GRPO)	Local Retrieval	Single-Agent
Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning	2025/05/22	Qwen2.5-7B-Instruct	RL(DPO)	Local Retrieval	Single-Agent
SmartSearch: Process Reward-Guided Query Refinement for Search Agents	2026/01/08	Qwen2.5-3B-Instruct	SFT, DPO, GRPO	Web Search	Single-Agent
AutoTool: Efficient Tool Selection for Large Language Model Agents	2025/11/18	Llama4-Scout-17B	Prompting	Web Search	Single-Agent
O-Researcher: An Open Ended Deep Research Model via Multi-Agent Distillation and Agentic RL	2026/01/07	Qwen-2.5-72B-Instruct	GRPO	Web Search	Multi-Agent
HiPRAG: Hierarchical Process Rewards for Efficient Agentic Retrieval Augmented Generation	2025/10/09	Qwen2.5-3B-Instruct, Qwen2.5-7B-Instruct, Llama-3.2-3B-Instruct	PPO, GRPO	Web Search	Single-Agent
Towards Agentic Self-Learning LLMs in Search Environment	2025/10/16	Qwen-2.5-7B-Instruct	RL	Web Search	Multi-Agent
WebSeer: Training Deeper Search Agents through Reinforcement Learning with Self-Reflection	2025/10/21	Qwen-2.5-14B, Qwen-3-14B	RL (cold start + RL; self-reflection)	Web Search	Single-Agent
TOOLRM: Towards Agentic Tool-Use Reward Modeling	2025/10/30	Qwen3-4B, Qwen3-8B	RL	Web Search	Single-Agent
A2SEARCH: Ambiguity-Aware Question Answering with Reinforcement Learning	2025/10/09	Qwen-2.5 family	RL	Web Search	Single-Agent
Stop-RAG: Value-Based Retrieval Control for Iterative RAG	2025/10/16	Llama-3.1-8B-Instruct	Fine-tuning	Local Retrieval	Single-Agent
ResearStudio: A Human-Intervenable Framework for Building Controllable Deep-Research Agents	2025/10/14	gpt-4.1, gpt-4.1-mini, o4-mini, Llama-3.3-70B	Prompting	Web Search	Single-Agent
Agentic Reasoning: Reasoning LLMs with Tools for the Deep Research	2025/02/07	N/A	Prompting	Web Search	Multi-Agent
Multimodal DeepResearcher: Generating Text-Chart Interleaved Reports From Scratch with Agentic Framework	2025/06/03	Claude3.7-Sonnet, GPT-4o-mini, Qwen3-235B-A22B, Qwen2.5-VL-72B-Instruct	Prompting	Web Search	Multi-Agent
LEAPS: An LLM-Empowered Adaptive Plugin for Taobao AI Search	2026/01/09	Qwen3-14B	REINFORCE++, GRPO, GSPO	Local Retrieval	Single-Agent
WebAnchor: Anchoring Agent Planning to Stabilize Long-Horizon Web Reasoning	2026/01/06	WebSailor-3B/7B, Tongyi-DR-30B, Qwen-2.5-72B	GRPO	Local Retrieval	Single-Agent
Budget-Aware Tool-Use Enables Effective Agent Scaling	2025/11/21	Gemini-2.5-Flash, Gemini-2.5-Pro, Claude-Sonnet-4	Prompting	Web Search	Single-Agent
ToolScope: An Agentic Framework for Vision-Guided and Long-Horizon Tool Use	2025/10/31	GPT-4o, Gemini-2.5, Qwen2.5-VL, Llama-3.2-Vision	Prompting	Local Retrieval	Multi-Agent
GOAT: A Training Framework for Goal-Oriented Agent with Tools	2025/10/14	Qwen-2-7B, Llama-3-8B-Instruct, Llama-3-70B-Instruct	Fine-tuning	Web Search	Single-Agent
ReSeek: A Self-Correcting Framework for Search Agents with Instructive Rewards	2025/10/01	Qwen2.5-7B-Instruct, Qwen2.5-3B-Instruct	GRPO	Web Search, Local Retrieval	Single-Agent
Process-Supervised Reinforcement Learning for Interactive Multimodal Tool-Use Agents	2025/09/17	Qwen3-8B, Qwen2.5-Omni-7B	RL	Local Retrieval	Single-Agent