AI-powered research assistant has attracted great attention in the community. It is a key step for mankind to move towards general artificial intelligence (AGI)! This repo is dedicated to organizing the current technical routes and papers of Deep Research, hoping to help research in this field.
📢NOTE: This is a popular work recently, so the codes of many papers have not been open sourced. If you know that some work has been updated, please leave a message in the issues and I will update it in time!
📢NOTE: I'm updating relevant research all the time...
📢NOTE: If you have any questions, please don't hesitate to contact us at any of the following emails: fengpeilin@pjlab.org.cn
⭐ This repository hosts a curated collection of literature associated with Deep Research(AI-powered research assistant). Please share a ⭐ if this project does help!
| Date | Paper | Link |
|---|---|---|
| 25.02 | Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation | Link |
| 25.02 | Survey on Vision-Language-Action Models | Link |
| 24.12 (ITiCSE-WGR 2024) | Beyond the Hype: A Comprehensive Review of Current Trends in Generative AI Research, Teaching Practices, and Tools | Link |
| 24.08 | A Multi-Year Grey Literature Review on AI-assisted Test Automation | Link |
| 24.05 | A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models | Link |
| 24.04 | From Persona to Personalization: A Survey on Role-Playing Language Agents | Link |
| 24.02 (Artif. Intell 2024) | Artificial Intelligence for Literature Reviews: Opportunities and Challenges | Link |
| 23.10 | A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions | Link |
| 23.07 | Natural Language Generation and Understanding of Big Code for AI-Assisted Programming: A Review | Link |
These widely used open source frameworks can effectively help the development of Deep Research.
| Date | Repository | Description | Link |
|---|---|---|---|
| 23.08 | AutoGen | AutoGen is a framework for creating multi-agent AI applications that can act autonomously or work alongside humans | Link |
| 23.08 | lightllm | A Python-based LLM (Large Language Model) inference and serving framework | Link |
| 23.06 | AutoChain | Building generative agents based on objectives expressed in natural language | Link |
| 23.06 | ollama | A framework that simplifies the development of large-scale machine learning models | Link |
| 23.06 | vllm | A fast and easy-to-use library for LLM inference and serving | Link |
| 23.06 | web-llm | WebLLM is a high-performance in-browser LLM inference engine that brings language model inference directly onto web browsers with hardware acceleration. | Link |
| 23.04 | AgentGPT | AgentGPT allows you to configure and deploy Autonomous AI agents | Link |
| 23.04 | JARVIS | The mission of JARVIS is to explore artificial general intelligence (AGI) and deliver cutting-edge research to the whole community. | Link |
| 23.04 | camel | CAMEL is an open-source community dedicated to finding the scaling laws of agents. | Link |
| 23.03 | AutoGPT | AutoGPT is a powerful platform that allows you to create, deploy, and manage continuous AI agents that automate complex workflows. | Link |
| 22.11 | langchain | A framework for developing applications powered by large language models (LLMs). | Link |
| 22.11 | llama_index | LlamaIndex (GPT Index) is a data framework for your LLM application | Link |
| Date | Paper | Figure | Link | Code |
|---|---|---|---|---|
| 2025.03 | Mask-DPO: Generalizable Fine-grained Factuality Alignment of LLMs |  |
Link | Code |
| 2023.10🔥 | OpenAgents: An Open Platform for Language Agents in the Wild |  |
Link | Code |
| 2023.10🔥 | MetaAgents: Simulating Interactions of Human Behaviors for LLM-based Task-oriented Coordination via Collaborative Generative Agents |  |
Link | Code |
| 2023.08 (ICLR 2024)🔥 | MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework |  |
Link | Code |
| 2023.08🔥 | AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation |  |
Link | Code |
| 2022.03 (ICLR 2023) | Self-Consistency Improves Chain of Thought Reasoning in Language Models |  |
Link | |
| 2022.03 (NeurIPS 2022) | Training language models to follow instructions with human feedback |  |
Link | |
| 2022.01 (NeurIPS 2022) | Chain-of-Thought Prompting Elicits Reasoning in Large Language Models |  |
Link | |
| 2017 (SNAPL 2017) | Natural Language is a Programming Language: Applying Natural Language Processing to Software Development |  |
Link |
| Date | Paper | Figure | Link | Code |
|---|---|---|---|---|
| 2025.01 | Debate Helps Weak-to-Strong Generalization |  |
Link | |
| 2024.12 | LLMs as Debate Partners: Utilizing Genetic Algorithms and Adversarial Search for Adaptive Arguments |  |
Link | |
| 2024.06 | Generative AI Voting: Fair Collective Choice is Resilient to LLM Biases and Inconsistencies |  |
Link | Code |
| 2023.08 (ICLR 2024)🔥 | AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors |  |
Link | Code |
| 2023.08 (ICLR 2024) | ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate |  |
Link | Code |
| 2023.07 (ACL 2024)🔥 | ChatDev: Communicative Agents for Software Development |  |
Link | Code |
| 2023.03 (NeurIPS 2023)🔥 | CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society |  |
Link | Code |
| Date | Paper | Figure | Link | Code |
|---|---|---|---|---|
| 2025.03🔥 | AI-Researcher: Fully-Automated Scientific Discovery with LLM Agents |  |
Coming soon! | Code |
| 2025.03🔥 | DeepReview: Improving LLM-based Paper Review with Human-like Deep Thinking Process |  |
Link | Code Demo |
| 2025.02 | AI-Instruments: Embodying Prompts as Instruments to pdftract & Reflect Graphical Interface Commands as General-Purpose Tools |  |
Link | |
| 2025.02 | From Documents to Dialogue: Building KG-RAG Enhanced AI Assistants |  |
Link | |
| 2025.02 | CodeA11y: Making AI Coding Assistants Useful for Accessible Web Development |  |
Link | Code |
| 2025.02 | Automated Capability Discovery via Model Self-Exploration |  |
Link | Code |
| 2025.02 | Accelerating Scientific Research Through a Multi-LLM Framework |  |
Link | |
| 2025.02 | Knowledge Synthesis of Photosynthesis Research Using a Large Language Model |  |
Link | Code |
| 2025.02 | ChartCitor: Multi-Agent Framework for Fine-Grained Chart Visual Attribution |  |
Link | |
| 2025.02 | Towards an AI co-scientist |  |
Link | |
| 2025.02🔥 | AIDE: AI-Driven Exploration in the Space of Code |  |
Link | Code |
| 2025.02🔥 | AutoAgent: A Fully-Automated and Zero-Code Framework for LLM Agents |  |
Link | Code |
| 2025.01 | Automating Care by Self-maintainability for Full Laboratory Automation |  |
Link | |
| 2025.01 | Knowledge Retrieval Based on Generative AI |  |
Link | |
| 2025.01 | Dolphin: Closed-loop Open-ended Auto-research through Thinking, Practice, and Feedback |  |
Link | Code |
| 2025.01🔥 | Agent Laboratory: Using LLM Agents as Research Assistants |  |
Link | Code |
| 2024.12 | Automated Code Review In Practice |  |
Link | |
| 2024.12 | VISION: A Modular AI Assistant for Natural Human-Instrument Interaction at Scientific User Facilities |  |
Link | Video |
| 2024.12 | EvoPat: A Multi-LLM-based Patents Summarization and Analysis Agent |  |
Link | |
| 2024.12 | LLMs can Realize Combinatorial Creativity: Generating Creative Ideas via LLMs for Scientific Research |  |
Link | |
| 2024.12 (Technique Report) | TapeAgents: a Holistic Framework for Agent Development and Optimization |  |
Link | Code |
| 2024.12 | Multi-Agent System for Cosmological Parameter Analysis |  |
Link | Code |
| 2024.12 | MetaScientist: A Human-AI Synergistic Framework for Automated Mechanical Metamaterial Design |  |
Link | Demo |
| 2024.12 | A Retrieval-Augmented Generation Framework for Academic Literature Navigation in Data Science |  |
Link | |
| 2024.11 | CycleResearcher: Improving Automated Research via Automated Review |  |
Link | Code |
| 2024.11 | AIGS: Generating Science from AI-Powered Automated Falsification |  |
Link | Code |
| 2024.11 | MatPilot: an LLM-enabled AI Materials Scientist under the Framework of Human-Machine Collaboration |  |
Link | |
| 2024.11 | Semantic Navigation for AI-assisted Ideation |  |
Link | |
| 2024.10 | AiSciVision: A Framework for Specializing Large Multimodal Models in Scientific Image Classification |  |
Link | Code |
| 2024.10 | Leveraging Large Language Models for Code Translation and Software Development in Scientific Computing |  |
Link | |
| 2024.10 | AdaptoML-UX: An Adaptive User-centered GUI-based AutoML Toolkit for Non-AI Experts and HCI Researchers |  |
Link | Code |
| 2024.10 (EMNLP 2024) | Enhancing AI Assisted Writing with One-Shot Implicit Negative Feedback |  |
Link | Code |
| 2024.10 | Beyond-RAG: Question Identification and Answer Generation in Real-Time Conversations |  |
Link | |
| 2024.10 | A Multi-LLM Orchestration Engine for Personalized, Context-Rich Assistance | |||
| 2024.10 | Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent System |  |
Link | Code |
| 2024.09 | NoTeeline: Supporting Real-Time, Personalized Notetaking with LLM-Enhanced Micronotes |  |
Link | Code |
| 2024.09 | Steward: Natural Language Web Automation |  |
Link | Code |
| 2024.09 | PatentGPT: A Large Language Model for Patent Drafting Using Knowledge-based Fine-tuning Method |  |
Link | |
| 2024.09 (Technique Report) | SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning |  |
Link | Code |
| 2024.09 | Collective Predictive Coding as Model of Science: Formalizing Scientific Activities Towards Generative Science |  |
Link | |
| 2024.08 | Genesis: Towards the Automation of Systems Biology Research |  |
Link | |
| 2024.08 (Technique Report)🔥 | The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery |  |
Link | Code |
| 2024.07 | AI-Assisted SQL Authoring at Industry Scale |  |
Link | |
| 2024.07 | SeqMate: A Novel Large Language Model Pipeline for Automating RNA Sequencing |  |
Link | |
| 2024.07 (UIST 2024) | Improving Steering and Verification in AI-Assisted Data Analysis with Interactive Task Decomposition |  |
Link | |
| 2024.06 | The Use of AI-Robotic Systems for Scientific Discovery | Link | ||
| 2024.04 (ETRA 2024) | SARA: Smart AI Reading Assistant for Reading Comprehension |  |
Link | |
| 2024.06 | BugBlitz-AI: An Intelligent QA Assistant |  |
Link | |
| 2024.05 (ACL 2024) | Automated Focused Feedback Generation for Scientific Writing Assistance |  |
Link | Code |
| 2024.05 (NLDB 2024) | A FAIR and Free Prompt-based Research Assistant |  |
Link | |
| 2024.05 | A System for Quantifying Data Science Workflows with Fine-Grained Procedural Logging and a Pilot Study |  |
Link | |
| 2024.04 (XP 2024) | Exploring Human-AI Collaboration in Agile: Customised LLM Meeting Assistants |  |
Link | |
| 2024.04 | ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models |  |
Link | Code |
| 2024.04 | Empowering Biomedical Discovery with AI Agents |  |
Link | |
| 2024.04 (NAACL 2024) | DOCMASTER: A Unified Platform for Annotation, Training, & Inference in Document Question-Answering |  |
Link | Code |
| 2024.03🔥 | ChatDBG: An AI-Powered Debugging Assistant |  |
Link | Code |
| 2024.03 | AutoDev: Automated AI-Driven Development |  |
Link | |
| 2024.02 | Streamlining the Selection Phase of Systematic Literature Reviews (SLRs) Using AI-Enabled GPT-4 Assistant API | Link | ||
| 2024.02 (SIGSOFT 2024) | Multi-line AI-assisted Code Authoring |  |
Link | |
| 2024.02 | An Autonomous Large Language Model Agent for Chemical Literature Data Mining |  |
Link | |
| 2024.02 (ICML 2024) | DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning |  |
Link | Code |
| 2024.02 | Prompt-Time Symbolic Knowledge Capture with Large Language Models | Link | Code |
|
| 2024.01 (Technique Report) | Weaver: Foundation Models for Creative Writing |  |
Link | Demo |
| 2024.01 | LLM-Powered Code Vulnerability Repair with Reinforcement Learning and Semantic Reward |  | ||
| 2023.12 (AAAI 2024) | GEAR-Up: Generative AI and External Knowledge-based Retrieval Upgrading Scholarly Article Searches for Systematic Reviews |  |
Link | Demo |
| 2023.12 | Agent-based Learning of Materials Datasets from Scientific Literature |  |
Link | Code |
| 2023.12 | Open Datasheets: Machine-readable Documentation for Open Datasets and Responsible AI Assessments |  |
Link | Code |
| 2023.11 (Technique Report) | AcademicGPT: Empowering Academic Research |  |
Link | |
| 2023.11 (ECCV 2024)🔥 | LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents |  |
Link | Code |
| 2023.10 (ICLR 2024) | GeoLLM: Extracting Geospatial Knowledge from Large Language Models |  |
Link | Code |
| 2023.07 (ICLR 2024)🔥 | ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs |  |
Link | Code |
| 2023.06 | AssistGPT: A General Multi-modal Assistant that can Plan, Execute, Inspect, and Learn |  |
Link | Code |
| 2023.06 | Interactive Editing for Text Summarization |  |
Link | |
| 2023.06 | Accelerating science with human-aware artificial intelligence |  |
Link | |
| 2023.04🔥 | ChemCrow: Augmenting large-language models with chemistry tools |  |
Link | Code |
| 2023.04 | Beyond Summarization: Designing AI Support for Real-World Expository Writing Tasks |  |
Link | |
| 2023.02 (ACL 2023) | CARE: Collaborative AI-Assisted Reading Environment |  |
Link | Code |
| 2022.11 (IEEE Trans 2023) | AI Assistants: A Framework for Semi-Automated Data Wrangling |  |
Link | |
| 2022.10 | Artificial Intelligence for Scientific Research: Authentic Research Education Framework |  |
Link | |
| 2022.08 | Effidit: Your AI Writing Assistant |  |
Link | Code |
| 2022.02 (AAAI 2021) | AI Research Associate for Early-Stage Scientific Discovery |  |
Link | |
| 2021.04 | Accelerating science with human versus alien artificial intelligences |  |
Link | |
| 2021.02 (ACM Trans 2022) | Documentation Matters: Human-Centered AI System to Assist Data Science Code Documentation in Computational Notebooks |  |
Link |
| Date | Paper | Figure | Link | Code |
|---|---|---|---|---|
| 2025.03 | Enabling AI Scientists to Recognize Innovation: A Domain-Agnostic Algorithm for Assessing Novelty |  |
Link | |
| 2025.03 | The impact of AI and peer feedback on research writing skills: a study using the CGScholar platform among Kazakhstani scholars |  |
Link | |
| 2025.02 | Supporting the development of Machine Learning for fundamental science in a federated Cloud with the AI_INFN platform |  |
Link | |
| 2025.02 | EAIRA: Establishing a Methodology for Evaluating AI Models as Scientific Research Assistants |  |
Link | |
| 2025.02 | Bridging Logic Programming and Deep Learning for Explainability through ILASP |  |
Link | |
| 2025.01 | Self-Explanation in Social AI Agents |  |
Link | |
| 2025.01 | Fine-Grained Appropriate Reliance: Human-AI Collaboration with a Multi-Step Transparent Decision Workflow for Complex Task Decomposition |  |
Link | |
| 2024.12 | CATER: Leveraging LLM to Pioneer a Multidimensional, Reference-Independent Paradigm in Translation Quality Evaluation | Link | ||
| 2024.10 | GigaCheck: Detecting LLM-generated Content |  |
Link | |
| 2024.10 | Vital Insight: Assisting Experts' Context-Driven Sensemaking of Multi-modal Personal Tracking Data Using Visualization and Human-In-The-Loop LLM Agents |  |
Link | |
| 2024.10 | Aligning AI-driven discovery with human intuition |  |
Link | Code |
| 2024.09 | Benchmarking ChatGPT, Codeium, and GitHub Copilot: A Comparative Study of AI-Driven Programming and Debugging Assistants | Link | ||
| 2024.06 (SSDBM 2024) | AI Data Readiness Inspector (AIDRIN) for Quantitative Assessment of Data Readiness for AI |  |
Link | |
| 2024.06 | A Knowledge-Component-Based Methodology for Evaluating AI Assistants | Link | ||
| 2023.04 | Evaluating the Code Quality of AI-Assisted Code Generation Tools: An Empirical Study on GitHub Copilot, Amazon CodeWhisperer, and ChatGPT |  |
Link | Code |
| 2023.04 (UIST 2023) | VISAR: A Human-AI Argumentative Writing Assistant with Visual Programming and Rapid Draft Prototyping |  |
Link | |
| 2021.10 | Explaining Reward Functions to Humans for Better Human-Robot Collaboration |  |
Link | |
| 2021.10 (ICANN 2021) | Learning to Assist Agents by Observing Them |  |
Link |
| Date | Paper | Figure | Link | Dataset |
|---|---|---|---|---|
| 2025.02 | Theoretical Physics Benchmark (TPBench) -- a Dataset and Study of AI Reasoning Capabilities in Theoretical Physics |  |
Link | Project |
| 2025.02 | Insect-Foundation: A Foundation Model and Large Multimodal Dataset for Vision-Language Insect Understanding |  |
Link | Project |
| 2025.02 | Minerva: A Programmable Memory Test Benchmark for Language Models |  |
Link | Project |
| 2025.02 | UGPhysics: A Comprehensive Benchmark for Undergraduate Physics Reasoning with Large Language Models |  |
Link | Code |
| 2025.02 | Learning to Coordinate with Experts |  |
Link | Code |
| 2025.02 | Auto-Bench: An Automated Benchmark for Scientific Discovery in LLMs |  |
Link | Project |
| 2024.12 | How Well Do LLMs Generate Code for Different Application Domains? Benchmark and Evaluation |  |
Link | Project |
| 2024.11 | LLM4DS: Evaluating Large Language Models for Data Science Code Generation |  |
Link | Project |
| 2024.11 (NeurIPS 2024) | RedCode: Risky Code Execution and Generation Benchmark for Code Agents |  |
Link | Project |
| 2024.11 (NeurIPS 2024) | SeafloorAI: A Large-scale Vision-Language Dataset for Seafloor Geological Survey |  |
Link | Project |
| 2024.11 (NeurIPS 2024) | INQUIRE: A Natural World Text-to-Image Retrieval Benchmark |  |
Link | Project |
| 2024.10 | AAAR-1.0: Assessing AI's Potential to Assist Research |  |
Link | Project |
| 2024.10 | AutoPenBench: Benchmarking Generative Agents for Penetration Testing |  |
Link | Project |
| 2024.10 | CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding Capabilities of CodeLLMs |  |
Link | Project |
| 2024.09 (EMNLP 2024) | UniSumEval: Towards Unified, Fine-Grained, Multi-Dimensional Summarization Evaluation for LLMs |  |
Link | Project |
| 2024.09 | CI-Bench: Benchmarking Contextual Integrity of AI Assistants on Synthetic Data |  |
Link | Project |
| 2024.09 | ChemDFM-X: Towards Large Multimodal Model for Chemistry |  |
Link | Project |
| 2024.09 | DSBench: How Far Are Data Science Agents to Becoming Data Science Experts? |  |
Link | Project |
| 2024.08 (NeurIPS 2024) | GMAI-MMBench: A Comprehensive Multimodal Evaluation Benchmark Towards General Medical AI |  |
Link | Project |
| 2024.07 | MMSci: A Dataset for Graduate-Level Multi-Discipline Multimodal Scientific Understanding |  |
Link | Project |
| 2024.07 (NeurIPS 2024) | SciCode: A Research Coding Benchmark Curated by Scientists |  |
Link | Project |
| 2024.06 | MASSW: A New Dataset and Benchmark Tasks for AI-Assisted Scientific Workflows |  |
Link | Project |
| 2024.05 | "Turing Tests" For An AI Scientist |  |
Link | Project |
| 2024.02 (ECCV 2024) | LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model |  |
Link | Project |
| 2023.11 (ICLR 2024) | GAIA: a benchmark for General AI Assistants |  |
Link | Dataset |
| 2023.10 (ACL 2024) | OceanGPT: A Large Language Model for Ocean Science Tasks |  |
Link | Project |
| 2023.08 (COLING 2024) | LatEval: An Interactive LLMs Evaluation Benchmark with Incomplete Information from Lateral Thinking Puzzles |  |
Link | Dataset |
| 2023.08 | BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agents |  |
Link | Dataset |
| 2023.07 | MegaWika: Millions of reports and their sources across 50 diverse languages |  |
Link | |
| 2022.09 (NeurIPS 2022) | Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering |  |
Link | Dataset |
| Date | Paper | Link | Keywords |
|---|---|---|---|
| 2025.03 | Unlocking the Potential of AI Researchers in Scientific Discovery: What Is Missing? | Link | AI researchers, scientific discovery, AI4Science, Diffusion of Innovation, integration of AI expertise |
| 2025.03 | Position: AI agents should be regulated based on autonomous action sequences | Link | AI agents, regulation, autonomous action sequences, existential risks, inference-time computation |
| 2025.02 | Performance Evaluation of Large Language Models in Statistical Programming | Link | Large Language Models, Statistical Programming, SAS Programming, Performance Evaluation, Automatic Code Generation |
| 2025.02 | Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path? | Link | AI safety, generalist AI agents, Scientist AI, non-agentic AI, precautionary principle |
| 2025.02 | Evaluating Sakana's AI Scientist for Autonomous Research: Wishful Thinking or an Emerging Reality Towards 'Artificial Research Intelligence' (ARI)? | Link | Artificial Research Intelligence (ARI), AI Scientist, autonomous research, Sakana, research automation |
| 2025.01 | "It makes you think": Provocations Help Restore Critical Thinking to AI-Assisted Knowledge Work | Link | Generative AI, Critical Thinking, Knowledge Work, Provocations, Metacognitive Thinking |
| 2025.01 | Experience with GitHub Copilot for Developer Productivity at Zoominfo | Link | GitHub Copilot, Developer Productivity, Zoominfo, AI-assisted software development, Enterprise deployment |
| 2025.01 | Towards Decoding Developer Cognition in the Age of AI Assistants | Link | AI assistants, developer productivity, cognitive load, programming tools, expertise levels |
| 2024.12 | Hints Help Finding and Fixing Bugs Differently in Python and Text-based Program Representations | Link | AI programming assistants, bug fixing, hints, program representations, user understanding |
| 2024.12 | The impact of AI on engineering design procedures for dynamical systems | Link | Artificial Intelligence, Engineering Design, Dynamical Systems, Mechatronic Systems, V-model Design Process |
| 2024.11 | Probing the limitations of multimodal language models for chemistry and materials research | Link | Artificial Intelligence, Multimodal Language Models, Chemistry, Materials Science, Benchmark Evaluation |
| 2024.11 | AI-Empowered Human Research Integrating Brain Science and Social Sciences Insights | Link | Artificial Intelligence, Human Research, Brain Science, Social Sciences, Human-AI Joint Research |
| 2024.11 | Disrupting Test Development with AI Assistants | Link | AI Assistants, Test Development, Software Development, Test Pyramid, Automated Testing |
| 2024.10 | Need Help? Designing Proactive AI Assistants for Programming | Link | Proactive AI Assistants, Programming, Large Language Models, Mixed-Initiative Interaction, User Experience |
| 2024.10 (EMNLP 2024) | How Does the Disclosure of AI Assistance Affect the Perceptions of Writing? | Link | AI assistance, writing perceptions, disclosure, quality evaluations, human-AI co-creation |
| 2024.10 | The why, what, and how of AI-based coding in scientific research | Link | AI-based coding, scientific research, large language models, coding assistance, workflow strategies |
| 2024.09 | Mining Causality: AI-Assisted Search for Instrumental Variables | Link | Instrumental Variables, Causal Inference, Large Language Models, Counterfactual Reasoning, Regression Discontinuity Design |
| 2024.09 | Towards Ethical Personal AI Applications: Practical Considerations for AI Assistants with Long-Term Memory | Link | Long-Term Memory, Personal AI Assistants, Ethical Considerations, Large Language Models, Deployment Implications |
| 2024.09 | Emerging Reliance Behaviors in Human-AI Text Generation: Hallucinations, Data Quality Assessment, and Cognitive Forcing Functions | Link | Human-AI collaborative text generation, hallucinations, cognitive forcing functions, data quality assessment, Large Language Models (LLMs) |
| 2024.08 | Generative AI Tools in Academic Research: Applications and Implications for Qualitative and Quantitative Research Methodologies | Link | Generative Artificial Intelligence, academic research, qualitative research, quantitative research, ethical implications |
| 2024.07 | Exploring the Evidence-Based Beliefs and Behaviors of LLM-Based Programming Assistants | Link | Artificial Intelligence, Large Language Models, Software Engineering, Evidence-Based Practices, Programming Assistants |
| 2024.07 | The Great AI Witch Hunt: Reviewers Perception and (Mis)Conception of Generative AI in Research Writing | Link | Generative AI, peer reviewers, research writing, AI-augmented manuscripts, impartial evaluations |
| 2024.07 | Large Language Models as Misleading Assistants in Conversation | Link | Large Language Models, Misleading Assistants, Conversation, Deception, Reading Comprehension Task |
| 2024.06 (EMNLP 2024) | Boosting Scientific Concepts Understanding: Can Analogy from Teacher Models Empower Student Models? | Link | Analogy, Teacher Models, Student Models, Scientific Concepts Understanding, Analogical Reasoning |
| 2024.06 | Explain the Black Box for the Sake of Science: the Scientific Method in the Era of Generative Artificial Intelligence | Link | Scientific Method, Generative Artificial Intelligence, Explainable AI, Scientific Discovery, Interpretability-guided Explanations (IGEs) |
| 2024.06 (Inf. Softw.2025) | Using AI-Based Coding Assistants in Practice: State of Affairs, Perceptions, and Ways Forward | Link | AI assistants, software development, usage patterns, developer perceptions, future improvements |
| 2024.05 | Using ChatGPT for Thematic Analysis | Link | AI-driven tools, qualitative thematic analysis, GPT model, research efficiency, ethical concerns |
| 2024.05 | What Can Natural Language Processing Do for Peer Review? | Link | Natural Language Processing, Peer Review, Scientific Articles, Quality Control, Large Language Models |
| 2024.05 | Transforming Software Development with Generative AI: Empirical Insights on Collaboration and Workflow | Link | Generative AI, software development, collaboration, workflow, ChatGPT |
| 2024.05 | From Complexity to Clarity: How AI Enhances Perceptions of Scientists and the Public's Understanding of Science | Link | AI, science communication, public understanding, linguistic simplicity, scientific dissemination |
| 2024.04 | Augmenting the Author: Exploring the Potential of AI Collaboration in Academic Writing | Link | Generative AI, Academic Writing, Prompt Design, Human-Computer Interaction, AI Collaboration |
| 2024.04 | How far are AI-powered programming assistants from meeting developers' needs? | Link | AI-powered programming assistants, software development tasks, code quality, productivity, user experience |
| 2024.04 | Deceptive Patterns of Intelligent and Interactive Writing Assistants | Link | Large Language Models, Intelligent Writing Assistants, Deceptive Design Patterns, Chatbot-like UI, Interaction Design Impact |
| 2024.03 (ICSE 2024) | Envisioning the Next-Generation AI Coding Assistants: Insights & Proposals | Link | AI coding assistants, in-IDE, AI for Software Engineering, backend designs, app data collection |
| 2024.03 | "It is there, and you need it, so why do you not use it?" Achieving better adoption of AI systems by domain experts, in the case study of natural science research | Link | Artificial Intelligence, adoption, domain experts, natural science research, human-AI collaboration |
| 2024.01 (ICML 2024)🔥 | Can AI Assistants Know What They Don't Know? | Link | AI Assistants, Large Language Models (LLMs), Open-domain Question Answering, Factual Errors, "I don't know" (Idk) dataset |
| 2023.12 | Exploring the intersection of Generative AI and Software Development | Link | Generative AI, Software Engineering, Zero-shot prompting, Multimodal chain-of-thought, Vector embeddings |
| 2023.12 | Generative AI in Writing Research Papers: A New Type of Algorithmic Bias and Uncertainty in Scholarly Work | Link | Generative AI, Algorithmic Bias, Uncertainty, Scholarly Work, Research Manuscripts |
| 2023.12 | Drivers and Barriers of AI Adoption and Use in Scientific Research | Link | Artificial Intelligence, Adoption, Scientific Research, Human Capital, Barriers and Drivers |
| 2023.11 (EMNLP 2023) | Unraveling Downstream Gender Bias from Large Language Models: A Study on AI Educational Writing Assistance | Link | Large Language Models, Gender Bias, AI Writing Support, Educational Writing, Bias Transfer |
| 2023.10 | Conversational Challenges in AI-Powered Data Science: Obstacles, Needs, and Design Opportunities | Link | Large Language Models, data science, conversational challenges, design recommendations, AI-powered chatbots |
| 2023.10 | AI for Mathematics: A Cognitive Science Perspective | Link | Artificial Intelligence, Mathematics, Cognitive Science, Large Language Models, Mathematical Systems |
| 2023.07 | AI empowering research: 10 ways how science can benefit from AI | Link | Artificial Intelligence, Scientific Research, Data Analysis, Human-AI Collaboration, Creativity in Science |
| 2023.07 | The Future of Fundamental Science Led by Generative Closed-Loop Artificial Intelligence | Link | Artificial Intelligence, Generative AI, Large Language Models, Scientific Discovery, Fundamental Science |
| 2023.07 | What Should Data Science Education Do with Large Language Models? | Link | Large Language Models, Data Science Education, ChatGPT, AI-guided Programming, Pedagogy Evolution |
| 2023.06 | The Future of AI-Assisted Writing | Link | Artificial Intelligence, Natural Language Generation, AI-Assisted Writing, Information Retrieval, User Study |
| 2023.05 | Science in the Era of ChatGPT, Large Language Models and Generative AI: Challenges for Research Ethics and How to Respond | Link | Artificial Intelligence, Research Ethics, ChatGPT, Generative AI, Scientific Integrity |
| 2023.05 | Automated Scientific Discovery: From Equation Discovery to Autonomous Discovery Systems | Link | Automated Scientific Discovery, Equation Discovery, Autonomous Discovery Systems, Deep Neural Networks, Nobel Turing Grand Challenge |
| 2023.03 (Nature 2023)🔥 | ChatGPT and large language models in academia: opportunities and challenges | Link | LLMs, Academic Writing, Ethical Implications, Bias and Accuracy |
| 2023.03 (ICSE 2024)🔥 | A Large-Scale Survey on the Usability of AI Programming Assistants: Successes and Challenges | Link | AI Programming Assistants, Usability, Developers, Software Engineering, Cognitive Effort |
| 2023.03 (SEKE 2023)🔥 | Practices and Challenges of Using GitHub Copilot: An Empirical Study | Link | GitHub Copilot, AI Pair Programmer, programming languages, IDEs, challenges |
| 2023.02 (Sage 2023)🔥 | The Challenges and Opportunities of AI-Assisted Writing: Developing AI Literacy for the AI Age | Link | Generative AI, Business Communication, AI Literacy, Critical Thinking, AI-Assisted Writing |
| 2023.01 (CHIIR 2023) | How Data Scientists Review the Scholarly Literature | Link | Data Scientists, Scholarly Literature, Literature Review Practices, Information Overload, Interdisciplinary Field |
| 2021.11 (Inf. Fusion 2023) | Automated scholarly paper review: Concepts, technologies, and challenges | Link | Automated scholarly paper review, Artificial intelligence, Peer review, Research evaluation, Academic publishing |
| 2021.03 | Toward Building Science Discovery Machines | Link | Scientific Discovery, Machine Learning, AI Systems, Problem-Solving, Principles of Science Discovery |
| 2021.01🔥 | How Much Automation Does a Data Scientist Want? | Link | Data Science, Machine Learning, Automation, User-Centered, AutoML Framework |