Awesome Deep Research Projects

For more detailed report, please refer to A Comprehensive Survey of Deep Research: Systems, Methodologies, and Applications

Projects

Category	Subcategory	Name	URL
Open-source	Agent Framework	XAgent	https://github.com/OpenBMB/XAgent
Open-source	Agent Framework	AutoGen	https://github.com/microsoft/autogen
Open-source	Agent Framework	Qwen-Agent	https://github.com/QwenLM/Qwen-Agent
Open-source	Agent Framework	OpenAI Agents SDK	https://github.com/openai/openai-agents-python
Open-source	Agent Framework	N8n	https://github.com/n8n-io/n8n
Open-source	Agent Framework	AutoChain	https://github.com/Forethought-Technologies/AutoChain
Open-source	Agent Framework	AgentGPT	https://github.com/reworkd/AgentGPT
Open-source	Agent Framework	Open-operator	https://github.com/browserbase/open-operator
Open-source	Agent Framework	BabyAGI	https://github.com/yoheinakajima/babyagi
Open-source	Agent Framework	AutoGPT	https://github.com/Significant-Gravitas/AutoGPT
Open-source	Agent Framework	MetaGPT	https://github.com/geekan/MetaGPT
Open-source	Agent Framework	Llama_index	https://github.com/run-llama/llama_index
Open-source	Agent Framework	LangGraph	https://github.com/langchain-ai/langgraph
Open-source	Agent Framework	GoogleADK	https://google.github.io/adk-docs/
Open-source	Agent Framework	CrewAI	https://github.com/crewAIInc/crewAI
Open-source	Agent Framework	Agno	https://github.com/agno-agi/agno
Open-source	Agent Framework	Temporal	https://github.com/temporalio/temporal
Open-source	Agent Framework	Orkes	https://orkes.io/use-cases/agentic-workflows
Open-source	Agent Framework	Pydantic-AI	https://github.com/pydantic/pydantic-ai
Open-source	Agent Framework	Letta	https://github.com/letta-ai/letta
Open-source	Agent Framework	Mastra	https://github.com/mastra-ai/mastra
Open-source	Agent Framework	Semantic Kernel	https://github.com/microsoft/semantic-kernel
Open-source	Agent Orchestration Platform	Dify	https://github.com/langgenius/dify
Closed-source	Agent Orchestration Platform	Coze Space	https://www.coze.cn/space-preview
Closed-source	Agent Orchestration Platform	Flowise	https://flowiseai.com/
Closed-source	​AI Assistant Tools​	NotebookLm	https://notebooklm.google/
Closed-source	​AI Assistant Tools​	MGX.dev	https://mgx.dev
Closed-source	​AI Assistant Tools​	You	https://you.com/about
Closed-source	​AI Assistant Tools​	Microsoft Copilot	https://www.microsoft.com/en-us/microsoft-copilot/organizations
Closed-source	Workflow​	Claude Research	https://www.anthropic.com/news/research
Open-source	Workflow​	Google-gemini/gemini-fullstack-langgraph-quickstart	https://github.com/google-gemini/gemini-fullstack-langgraph-quickstart
Open-source	Workflow​	Dzhng/deep-research	https://github.com/dzhng/deep-research
Open-source	Workflow​	Jina-AI/node-DeepResearch	https://github.com/jina-ai/node-DeepResearch
Open-source	Workflow​	LangChain-AI/open_deep_research	https://github.com/langchain-ai/open_deep_research
Open-source	Workflow​	TheBlewish/Automated-AI-Web-Researcher-Ollama	https://github.com/TheBlewish/Automated-AI-Web-Researcher-Ollama
Open-source	Workflow​	Btahir/open_deep_research	https://github.com/btahir/open-deep-research
Open-source	Workflow​	Nickscamara/open-deep-research	https://github.com/nickscamara/open-deep-research
Open-source	Workflow​	Mshumer/OpenDeepResearcher	https://github.com/mshumer/OpenDeepResearcher
Open-source	Workflow​	Grapeot/deep_research_agent	https://github.com/grapeot/deep_research_agent
Open-source	Workflow​	Smolagents/open_deep_research	https://github.com/huggingface/smolagents/tree/main/examples/open_deep_research
Open-source	Workflow​	Assafelovic/GPT-Researcher	https://github.com/assafelovic/gpt-researcher/
Open-source	Workflow​	HKUDS/Auto-Deep-Research	https://github.com/HKUDS/Auto-Deep-Research
Open-source	Workflow​	AgentLaboratory	https://github.com/SamuelSchmidgall/AgentLaboratory
Closed-source	Multi-modal Agent UI​	Manus	https://manus.im/
Closed-source	Multi-modal Agent UI​	Flowith-Oracle Mode	https://flowith.net/
Open-source	Multi-modal Agent UI​	OpenManus	https://github.com/FoundationAgents/OpenManus
)
Open-source	Multi-modal Agent UI​	Camel-AI/OWL	https://github.com/camel-ai/owl
Open-source	Multi-modal Agent UI​	TARS	https://github.com/bytedance/UI-TARS-desktop
Open-source	Multi-modal Agent UI​	Nanobrowser	https://github.com/nanobrowser/nanobrowser
Open-source	Multi-modal Agent UI​	JARVIS	https://github.com/microsoft/JARVIS
Closed-source	Multi-modal Agent UI​	Devin	https://devin.ai/
Closed-source	Foundation Models​	OpenAI Deep Research	https://openai.com/index/introducing-deep-research/
Closed-source	Foundation Models​	Gimini Deep Research	https://blog.google/products/gemini/google-gemini-deep-research/
Closed-source	Foundation Models​	Perplexity Deep Research	https://www.perplexity.ai/hub/blog/introducing-perplexity-deep-research
Closed-source	Foundation Models​	Grok 3 Beta	https://x.ai/news/grok-3
Closed-source	Foundation Models​	AutoGLM-Research	https://autoglm-research.zhipuai.cn/
Closed-source	Foundation Models​	DeepSeek-R1	https://arxiv.org/abs/2501.12948
Closed-source	Developer Tools​	Vercel	https://vercel.com/
Closed-source	Developer Tools​	Bolt	https://bolt.new/
Closed-source	Developer Tools​	Cursor	https://www.cursor.com/
Closed-source	Developer Tools​	Github Copilot	https://github.com/features/copilot?ref=nav.poetries.top
Open-source	Developer Tools​	Cline	https://github.com/cline/cline
Open-source	Developer Tools​	GPT-pilot	https://github.com/Pythagora-io/gpt-pilot
Open-source	Developer Tools​	Restate	https://restate.dev/
Open-source	Developer Tools​	OpenAI Codex	https://github.com/openai/codex
Closed-source	​Research/Academic Search	Elicit	https://elicit.com/?redirected=true
Closed-source	​Research/Academic Search	ResearchRabbit	https://www.researchrabbit.ai/
Closed-source	​Research/Academic Search	STORM	https://storm.genie.stanford.edu/
Closed-source	​Research/Academic Search	Consensus	https://consensus.app/
Closed-source	​Research/Academic Search	Scite	https://scite.ai/
Closed-source	​Research/Academic Search	Scispace	https://scispace.com/
Closed-source	​Research/Academic Search	FutureHouse Platform	https://www.futurehouse.org/research-announcements/launching-futurehouse-platform-ai-agents
Open-source	​Research/Academic Search	PaperQA	https://github.com/Future-House/paper-qa
Open-source	​Research/Academic Search	HKUDS/AI-Researcher	https://github.com/HKUDS/AI-Researcher
Open-source	Model Training Frameworks​	Agent-RL/ReSearch	https://github.com/Agent-RL/ReSearch
Open-source	Model Training Frameworks​	DSPy	https://github.com/stanfordnlp/dspy
Open-source	Model Training Frameworks​	Gair-NLP/DeepResearcher	https://github.com/GAIR-NLP/DeepResearcher
Open-source	Model Training Frameworks​	ModelTC/lightllm	https://github.com/ModelTC/lightllm
Open-source	Other LLM Tools​	Ollama	https://github.com/ollama/ollama
Open-source	Other LLM Tools​	Vllm	https://github.com/vllm-project/vllm
Open-source	Other LLM Tools​	Web-LLM	https://github.com/mlc-ai/web-llm

Papers

Category	Paper Title	URL
​AI Agent Frameworks & Development​	AutoAgent: A Fully-Automated and Zero-Code Framework for LLM Agents	https://arxiv.org/pdf/2502.05957
​AI Agent Frameworks & Development​	Building effective agents	https://www.anthropic.com/engineering/building-effective-agents
​AI Agent Frameworks & Development​	OpenAgents: An Open Platform for Language Agents in the Wild	https://arxiv.org/pdf/2310.10634
​AI Agent Frameworks & Development​	Agentic Reasoning: Reasoning LLMs with Tools for the Deep Research	https://arxiv.org/pdf/2502.04644
​AI Agent Frameworks & Development​	AutoGLM: Autonomous Foundation Agents for GUIs	https://arxiv.org/pdf/2411.00820
​AI Agent Frameworks & Development​	TapeAgents: A Holistic Framework for Agent Development and Optimization	https://arxiv.org/pdf/2412.08445
​AI Agent Frameworks & Development​	How to think about agent frameworks	https://blog.langchain.dev/how-to-think-about-agent-frameworks/
​AI for Scientific Research​	Towards an AI Co-Scientist	https://storage.googleapis.com/coscientist_paper/ai_coscientist.pdf
​AI for Scientific Research​	DeepResearcher: Scaling Deep Research via Reinforcement Learning	https://arxiv.org/pdf/2504.03160
​AI for Scientific Research​	AI Achieves Silver-Medal Standard Solving IMO Problems	https://deepmind.google/discover/blog/ai-solves-imo-problems-at-silver-medal-level/
​AI for Scientific Research​	Accelerating Scientific Research Through Multi-LLM Frameworks	https://arxiv.org/pdf/2502.07960
​AI for Scientific Research​	The AI Scientist: Fully Automated Open-Ended Scientific Discovery	https://arxiv.org/pdf/2408.06292
​AI for Scientific Research​	Transforming Science with LLMs: Survey on AI-Assisted Discovery	https://arxiv.org/pdf/2502.05151
​AI for Scientific Research​	AI's Deep Research Revolution in Biomedical Literature	https://journals.lww.com/jcma/citation/9900/ai_s_deep_research_revolution__transforming.508.aspx
​AI for Scientific Research​	Unlocking AI Researchers' Potential in Scientific Discovery	https://arxiv.org/pdf/2503.05822
​AI for Scientific Research​	Empowering Biomedical Discovery with AI Agents	https://arxiv.org/pdf/2404.02831
​AI for Scientific Research​	Automated Scientific Discovery Systems	https://arxiv.org/abs/2305.02251
​LLM Tool Integration & API Control​	ToolLLM: Mastering 16K+ Real-World APIs	https://arxiv.org/pdf/2307.16789
​LLM Tool Integration & API Control​	MetaGPT: Multi-Agent Collaborative Framework	https://arxiv.org/pdf/2308.00352
​LLM Tool Integration & API Control​	AutoGen: Next-Gen LLM Apps via Multi-Agent Conversation	https://arxiv.org/pdf/2308.08155
​LLM Tool Integration & API Control​	LLaVA-Plus: Creating Multimodal Agents with Tools	https://arxiv.org/pdf/2311.05437
​LLM Tool Integration & API Control​	ChemCrow: Augmenting LLMs with Chemistry Tools	https://arxiv.org/pdf/2304.05376
​LLM Tool Integration & API Control​	TORL: Scaling Tool-Integrated Reinforcement Learning	https://arxiv.org/pdf/2503.23383
​Deep Research Systems​	OpenAI's 'Deep Research' Tool: Usefulness for Scientists	https://www.nature.com/articles/d41586-025-00377-9
​Deep Research Systems​	OpenAI's Deep Research: Functionality and Applications	https://www.youreverydayai.com/openais-deep-research-how-it-works-and-what-to-use-it-for/
​Deep Research Systems​	Deep Research System Card	https://cdn.openai.com/deep-research-system-card.pdf
​Deep Research Systems​	Gemini Launches Deep Research on Gemini 2.5 Pro	https://www.ctol.digital/news/gemini-deep-research-launch-2-5-pro-vs-openai/
​Deep Research Systems​	Deep Research Now Available on Gemini 2.5 Pro Experimental	https://blog.google/products/gemini/deep-research-gemini-2-5-pro-experimental/
​Deep Research Systems​	ChatGPT's Deep Research vs. Google's Gemini 1.5 Pro: Comparison	https://whitebeardstrategies.com/ai-prompt-engineering/chatgpts-deep-research-vs-googles-gemini-1-5-pro-with-deep-research-a-detailed-comparison/
​Deep Research Systems​	ChatGPT Deep Research vs Perplexity: Comparative Analysis	https://blog.getbind.co/2025/02/03/chatgpt-deep-research-is-it-better-than-perplexity/
​Deep Research Systems​	Sonar by Perplexity [Technical Documentation]	https://docs.perplexity.ai/guides/model-cards#research-models
​RAG Technology​	Ragnarök: Reusable RAG Framework for TREC 2024	http://arxiv.org/pdf/2406.16828
​RAG Technology​	From Documents to Dialogue: KG-RAG Enhanced AI Assistants	https://arxiv.org/pdf/2502.15237
​RAG Technology​	GEAR-Up: AI-Augmented Scholarly Search for Systematic Reviews	https://arxiv.org/pdf/2312.09948
​RAG Technology​	Survey on RAG for Large Language Models	https://arxiv.org/pdf/2405.06211
​RAG Technology​	Knowledge Retrieval Based on Generative AI	https://arxiv.org/pdf/2501.04635
​LLM Reasoning & Optimization​	Self-Consistency Improves Chain-of-Thought Reasoning	https://arxiv.org/pdf/2203.11171
​LLM Reasoning & Optimization​	Chain-of-Thought Prompting Elicits Reasoning in LLMs	https://arxiv.org/pdf/2201.11903
​LLM Reasoning & Optimization​	Training LLMs to Follow Instructions with Human Feedback	https://arxiv.org/pdf/2203.02155
​LLM Reasoning & Optimization​	Debate Enhances Weak-to-Strong Generalization	https://arxiv.org/pdf/2501.13124
​LLM Reasoning & Optimization​	Mask-DPO: Factuality Alignment for LLMs	https://arxiv.org/pdf/2503.02846
​LLM Reasoning & Optimization​	QuestBench: Can LLMs Ask Optimal Questions?	https://arxiv.org/abs/2503.22674
​Multi-Agent Systems​	AgentVerse: Multi-Agent Collaboration and Emergent Behaviors	https://arxiv.org/pdf/2308.10848
​Multi-Agent Systems​	MetaAgents: Human Behavior Simulation for Task Coordination	https://arxiv.org/pdf/2310.06500
​Multi-Agent Systems​	CAMEL: Communicative Agents for LLM Society Exploration	https://arxiv.org/pdf/2303.17760
​Multi-Agent Systems​	Many Heads Improve Scientific Idea Generation	https://arxiv.org/pdf/2410.09403
​Multi-Agent Systems​	Why Multi-Agent LLM Systems Fail	https://arxiv.org/pdf/2503.13657
​Multi-Agent Systems​	Multi-Agent System for Cosmological Parameter Analysis	https://arxiv.org/pdf/2412.00431
​Code & Software Development​	CodeA11y: Accessible Web Development with AI	https://arxiv.org/pdf/2502.10884
​Code & Software Development​	AutoDev: Automated AI-Driven Development	https://arxiv.org/pdf/2403.08299
​Code & Software Development​	ChatDev: Communicative Agents for Software Development	https://aclanthology.org/2024.acl-long.810.pdf
​Code & Software Development​	Natural Language as a Programming Language	https://drops.dagstuhl.de/storage/00lipics/lipics-vol071-snapl2017/LIPIcs.SNAPL.2017.4/LIPIcs.SNAPL.2017.4.pdf
​Code & Software Development​	AIDE: AI-Driven Code Exploration	https://arxiv.org/pdf/2502.13138
​Code & Software Development​	AI-Assisted Programming: Big Code NLP	https://arxiv.org/pdf/2307.02503
​Code & Software Development​	AI-Assisted SQL Authoring at Industry Scale	https://arxiv.org/pdf/2407.13280
​Code & Software Development​	Steward: Natural Language Web Automation	https://arxiv.org/pdf/2409.15441
​Domain-Specific AI Tools​	MatPilot: AI Materials Scientist	https://arxiv.org/pdf/2411.08063
​Domain-Specific AI Tools​	EvoPat: Multi-LLM Patent Summarization Agent	https://arxiv.org/pdf/2412.18100
​Domain-Specific AI Tools​	ChartCitor: Fine-Grained Chart Attribution Framework	https://arxiv.org/pdf/2502.00989
​Domain-Specific AI Tools​	PatentGPT: Knowledge-Based Patent Drafting	https://arxiv.org/pdf/2409.00092
​Domain-Specific AI Tools​	SciAgents: Multi-Agent Scientific Discovery	https://arxiv.org/pdf/2409.05556
​Domain-Specific AI Tools​	Dolphin: Closed-Loop Open-Ended Auto-Research	https://arxiv.org/pdf/2501.03916
​Domain-Specific AI Tools​	SeqMate: Automating RNA Sequencing with LLMs	https://arxiv.org/pdf/2407.03381
​Domain-Specific AI Tools​	Knowledge Synthesis of Photosynthesis via LLMs	https://arxiv.org/pdf/2502.01059
​Domain-Specific AI Tools​	GeoLLM: Geospatial Knowledge Extraction from LLMs	https://arxiv.org/pdf/2310.06213
​HCI & AI User Experience​	System Usability Scale: Evolution and Future	https://doi.org/10.1080/10447318.2018.1455307
​HCI & AI User Experience​	CARE: Collaborative AI Reading Environment	https://arxiv.org/pdf/2302.12611
​HCI & AI User Experience​	VISAR: Visual Argumentative Writing Assistant	https://arxiv.org/pdf/2304.07810
​HCI & AI User Experience​	AdaptoML-UX: User-Centered AutoML Toolkit	https://arxiv.org/pdf/2410.17469
​HCI & AI User Experience​	AI Assistants for Semi-Automated Data Wrangling	https://arxiv.org/pdf/2211.00192
​HCI & AI User Experience​	Documentation Matters: Human-Centered AI Systems	https://arxiv.org/pdf/2102.12592
​HCI & AI User Experience​	Need Help? Proactive Programming Assistants	https://arxiv.org/abs/2410.04596
​HCI & AI User Experience​	Large-Scale Survey on AI Programming Assistant Usability	https://arxiv.org/abs/2303.17125
​AI Evaluation & Benchmarking​	TruthfulQA: Measuring Model Mimicry of Human Falsehoods	https://arxiv.org/pdf/2109.07958
​AI Evaluation & Benchmarking​	HotpotQA: Dataset for Multi-hop Question Answering	https://arxiv.org/pdf/1809.09600
​AI Evaluation & Benchmarking​	WebArena: Web Agent Benchmark	https://github.com/web-arena-x/webarena
​AI Evaluation & Benchmarking​	Measuring Short-Form Factuality in LLMs	https://cdn.openai.com/papers/simpleqa.pdf
​AI Evaluation & Benchmarking​	Survey on LLM-Generated Text Detection	https://arxiv.org/pdf/2310.14724
​AI Evaluation & Benchmarking​	Evaluating AI-Assisted Code Generation Tools	https://arxiv.org/pdf/2304.10778
​AI Evaluation & Benchmarking​	Benchmarking ChatGPT, Codeium, and GitHub Copilot	https://arxiv.org/pdf/2409.19922
​AI Evaluation & Benchmarking​	FinEval: Chinese Financial Knowledge Benchmark	https://arxiv.org/pdf/2308.09975
​AI Evaluation & Benchmarking​	Knowledge-Based Evaluation Methodology for AI Assistants	https://arxiv.org/pdf/2406.05603
​AI Evaluation & Benchmarking​	GRADE Guidelines: Rating Evidence Quality	https://pubmed.ncbi.nlm.nih.gov/21208779/
​AI Evaluation & Benchmarking​	Holistic Evaluation of Language Models	https://arxiv.org/pdf/2211.09110
​AI Evaluation & Benchmarking​	AGIEvalA Human-Centric Benchmark for Evaluating Foundation Models	https://arxiv.org/pdf/2304.06364
​AI Evaluation & Benchmarking​	GAIA:A Benchmark for General AI Assistants	https://arxiv.org/pdf/2311.12983
​AI Evaluation & Benchmarking​	MMLU benchmarkTesting LLMs multi-task capabilities	https://www.bracai.eu/post/mmlu-benchmark
​AI Evaluation & Benchmarking​	Enabling AI Scientists to Recognize InnovationA Domain-Agnostic Algorithm for Assessing Novelty	https://arxiv.org/pdf/2503.01508
​AI Evaluation & Benchmarking​	The impact of AI and peer feedback on research writing skillsa study using the CGScholar platform among Kazakhstani scholars	https://arxiv.org/pdf/2503.05820
​AI Evaluation & Benchmarking​	Supporting the development of Machine Learning for fundamental science in a federated Cloud with the AI_INFN platform	https://arxiv.org/pdf/2502.21266
​AI Evaluation & Benchmarking​	EAIRAEstablishing a Methodology for Evaluating AI Models as Scientific Research Assistants	https://arxiv.org/pdf/2502.20309
​AI Evaluation & Benchmarking​	Bridging Logic Programming and Deep Learning for Explainability through ILASP	https://arxiv.org/pdf/2502.09227
​AI Evaluation & Benchmarking​	Self-Explanation in Social AI Agents	https://arxiv.org/pdf/2501.13945
​AI Evaluation & Benchmarking​	Fine-Grained Appropriate RelianceHuman-AI Collaboration with a Multi-Step Transparent Decision Workflow for Complex Task Decomposition	https://arxiv.org/pdf/2501.10909
​AI Evaluation & Benchmarking​	CATERLeveraging LLM to Pioneer a Multidimensional, Reference-Independent Paradigm in Translation Quality Evaluation	https://arxiv.org/pdf/2412.11261
​AI Evaluation & Benchmarking​	GigaCheckDetecting LLM-generated Content	https://arxiv.org/pdf/2410.23728
​AI Evaluation & Benchmarking​	Vital InsightAssisting Experts' Context-Driven Sensemaking of Multi-modal Personal Tracking Data Using Visualization and Human-In-The-Loop LLM Agents	https://arxiv.org/pdf/2410.14879
​AI Evaluation & Benchmarking​	Aligning AI-driven discovery with human intuition	https://arxiv.org/pdf/2410.07
​AI Evaluation & Benchmarking​	Theoretical Physics Benchmark (TPBench) -- a Dataset and Study of AI Reasoning Capabilities in Theoretical Physics	https://arxiv.org/pdf/2502.15815
​AI Evaluation & Benchmarking​	Insect-FoundationA Foundation Model and Large Multimodal Dataset for Vision-Language Insect Understanding	https://arxiv.org/pdf/2502.09906
​AI Evaluation & Benchmarking​	MinervaA Programmable Memory Test Benchmark for Language Models	https://arxiv.org/pdf/2502.03358
​AI Evaluation & Benchmarking​	UGPhysicsA Comprehensive Benchmark for Undergraduate Physics Reasoning with Large Language Models	https://arxiv.org/pdf/2502.00334
​AI Evaluation & Benchmarking​	Learning to Coordinate with Experts	https://arxiv.org/pdf/2502.09583
​AI Evaluation & Benchmarking​	Auto-BenchAn Automated Benchmark for Scientific Discovery in LLMs	https://arxiv.org/pdf/2502.15224
​AI Evaluation & Benchmarking​	How Well Do LLMs Generate Code for Different Application Domains? Benchmark and Evaluation	https://arxiv.org/pdf/2412.18573
​AI Evaluation & Benchmarking​	LLM4DSEvaluating Large Language Models for Data Science Code Generation	https://arxiv.org/pdf/2411.11908
​AI Evaluation & Benchmarking​	RedCodeRisky Code Execution and Generation Benchmark for Code Agents	https://arxiv.org/pdf/2411.07781
​AI Evaluation & Benchmarking​	SeafloorAIA Large-scale Vision-Language Dataset for Seafloor Geological Survey	https://arxiv.org/pdf/2411.00172
​AI Evaluation & Benchmarking​	INQUIREA Natural World Text-to-Image Retrieval Benchmark	https://arxiv.org/pdf/2411.02537
​AI Evaluation & Benchmarking​	AAAR-1.0Assessing AI's Potential to Assist Research	https://arxiv.org/pdf/2410.22394
​AI Evaluation & Benchmarking​	AutoPenBenchBenchmarking Generative Agents for Penetration Testing	https://arxiv.org/pdf/2410.03225
​AI Evaluation & Benchmarking​	CodeMMLUA Multi-Task Benchmark for Assessing Code Understanding Capabilities of CodeLLMs	https://arxiv.org/pdf/2410.01999
​AI Evaluation & Benchmarking​	UniSumEvalTowards Unified, Fine-Grained, Multi-Dimensional Summarization Evaluation for LLMs	https://arxiv.org/pdf/2409.19898
​AI Evaluation & Benchmarking​	CI-BenchBenchmarking Contextual Integrity of AI Assistants on Synthetic Data	https://arxiv.org/pdf/2409.13903
​AI Evaluation & Benchmarking​	ChemDFM-XTowards Large Multimodal Model for Chemistry	https://arxiv.org/pdf/2409.13194
​AI Evaluation & Benchmarking​	DSBenchHow Far Are Data Science Agents to Becoming Data Science Experts?	https://arxiv.org/pdf/2409.07703
​AI Evaluation & Benchmarking​	GMAI-MMBenchA Comprehensive Multimodal Evaluation Benchmark Towards General Medical AI	https://arxiv.org/pdf/2408.03361
​AI Evaluation & Benchmarking​	MMSciA Dataset for Graduate-Level Multi-Discipline Multimodal Scientific Understanding	https://arxiv.org/pdf/2407.04903
​AI Evaluation & Benchmarking​	SciCodeA Research Coding Benchmark Curated by Scientists	https://arxiv.org/pdf/2407.13168
​AI Evaluation & Benchmarking​	MASSWA New Dataset and Benchmark Tasks for AI-Assisted Scientific Workflows	https://arxiv.org/pdf/2406.06357
​AI Evaluation & Benchmarking​	Turing Tests For An AI Scientist	https://arxiv.org/pdf/2405.13352
​AI Evaluation & Benchmarking​	LHRS-BotEmpowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model	https://arxiv.org/pdf/2402.02544
​AI Evaluation & Benchmarking​	GAIAa benchmark for General AI Assistants	https://arxiv.org/pdf/2311.12983
​AI Evaluation & Benchmarking​	OceanGPTA Large Language Model for Ocean Science Tasks	https://arxiv.org/pdf/2310.02031
​AI Evaluation & Benchmarking​	LatEvalAn Interactive LLMs Evaluation Benchmark with Incomplete Information from Lateral Thinking Puzzles	https://arxiv.org/pdf/2308.10855
​AI Evaluation & Benchmarking​	BOLAABenchmarking and Orchestrating LLM-augmented Autonomous Agents	https://arxiv.org/pdf/2308.05960
​AI Evaluation & Benchmarking​	MegaWikaMillions of reports and their sources across 50 diverse languages	https://arxiv.org/pdf/2307.07049
​AI Evaluation & Benchmarking​	Learn to ExplainMultimodal Reasoning via Thought Chains for Science Question Answering	https://arxiv.org/pdf/2209.09513
​AI Evaluation & Benchmarking​	Benchmarking Agentic Workflow Generation	https://arxiv.org/abs/2410.07869
​AI Evaluation & Benchmarking​	TheAgentCompanyBenchmarking LLM Agents on Consequential Real World Tasks	https://arxiv.org/abs/2412.14161

Citation

@misc{xu2025comprehensive,
    title={A Comprehensive Survey of Deep Research: Systems, Methodologies, and Applications},
    author={Renjun Xu and Jingwen Peng},
    year={2025},
    eprint={2506.12594},
    archivePrefix={arXiv},
    primaryClass={cs.AI}
}