Skip to content

Papers catalog

Regenerated from papers/references.bib (the single source of truth for citations) plus docs/papers/notes/*.md (curator analysis + status) by scripts/build_indexes.py. Do not edit by hand.

Each entry's citation data (title, authors, year, venue, DOI/arXiv) comes from papers/references.bib; themes and analysis come from per-paper structured notes in docs/papers/notes/.

273 bibliographic entries; 256 have curator notes (48 fully read). Filter via the column headers or the search box.

Year Authors Title Venue Link Themes Citekey Note
2012 Aral et al. Information, Technology, and Information Worker Productivity Information Systems Research doi research-productivity is-methodology sociotechnical aral2012itproductivity read
2019 Sarker & others The Sociotechnical Axis of Cohesion for the IS Discipline: Its Historical Legacy and Its Continued Relevance MIS Quarterly doi sociotechnical is-methodology sarker2019sociotechnical read
2020 Maynez & others On Faithfulness and Factuality in Abstractive Summarization Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics doi hallucination reasoning-faithfulness evaluation-of-ai-research maynez2020faithfulness read
2023 Ji & others Survey of Hallucination in Natural Language Generation ACM Computing Surveys doi hallucination evaluation-of-ai-research ji2023hallucination read
2023 Korinek Generative AI for Economic Research: Use Cases and Implications for Economists Journal of Economic Literature doi research-productivity human-ai-research-collaboration sociotechnical korinek2023genai queued
2023 Lála et al. PaperQA: Retrieval-Augmented Generative Agent for Scientific Research arXiv doi (arXiv) hallucination agentic-tool-use evaluation-of-ai-research lala2023paperqa skimmed
2023 Mitchell & Krakauer The Debate over Understanding in AI's Large Language Models Proceedings of the National Academy of Sciences doi llm-cognition sociotechnical mitchell2023understanding read
2023 Noy & Zhang Experimental Evidence on the Productivity Effects of Generative Artificial Intelligence Science doi research-productivity human-ai-research-collaboration noy2023experimental read
2023 Park & others Generative Agents: Interactive Simulacra of Human Behavior Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology doi autonomous-research-agents sociotechnical llm-cognition park2023generative read
2023 Schick & others Toolformer: Language Models Can Teach Themselves to Use Tools Advances in Neural Information Processing Systems doi (arXiv) agentic-tool-use schick2023toolformer read
2023 Susarla et al. The Janus Effect of Generative AI: Charting the Path for Responsible Conduct of Scholarly Activities in Information Systems Information Systems Research doi is-methodology sociotechnical ai-publishing-ecosystems susarla2023janus read
2024 Agrawal et al. AI in Science National Bureau of Economic Research link research-productivity human-ai-research-collaboration llm-cognition sociotechnical agrawal2024aiscience read
2024 Alavi et al. A Knowledge Management Perspective of Generative Artificial Intelligence Journal of the Association for Information Systems doi sociotechnical is-methodology alavi2024kmperspective skimmed
2024 Asai et al. OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs arXiv doi (arXiv) hallucination evaluation-of-ai-research agentic-reasoning asai2024openscholar skimmed
2024 Avital Digital Transformation of Academic Publishing: A Call for the Decentralization and Democratization of Academic Journals Journal of the Association for Information Systems doi sociotechnical ai-publishing-ecosystems avital2024decentralization skimmed
2024 Baek et al. ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models arXiv doi (arXiv) autonomous-research-agents ai-peer-review human-ai-research-collaboration baek2024researchagent skimmed
2024 Benbya et al. Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work Journal of the Association for Information Systems doi sociotechnical research-productivity benbya2024navigating skimmed
2024 Böttcher & Klingebiel Organizational Selection of Innovation Organization Science doi · open sociotechnical bottcher2024organizational queued
2024 Chan et al. MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering arXiv doi (arXiv) evaluation-of-ai-research autonomous-research-agents agentic-tool-use chan2024mlebench queued
2024 D'Arcy et al. MARG: Multi-Agent Review Generation for Scientific Papers arXiv doi (arXiv) ai-peer-review evaluation-of-ai-research darcy2024marg skimmed
2024 Drori & Te'eni Human-in-the-Loop AI Reviewing: Feasibility, Opportunities, and Risks Journal of the Association for Information Systems doi ai-peer-review human-ai-research-collaboration drori2024humanloop skimmed
2024 Goldberg et al. Usefulness of LLMs as an Author Checklist Assistant for Scientific Papers: NeurIPS'24 Experiment arXiv doi (arXiv) peer-review ai-publishing-ecosystems evaluation-rigor neurips2024checklist read
2024 Gregor Responsible Artificial Intelligence and Journal Publishing Journal of the Association for Information Systems doi ai-peer-review sociotechnical is-methodology gregor2024responsible skimmed
2024 Jarvenpaa & Klein New Frontiers in Information Systems Theorizing: Human-gAI Collaboration Journal of the Association for Information Systems doi is-methodology human-ai-research-collaboration jarvenpaa2024theorizing skimmed
2024 Jiang et al. Into the Unknown Unknowns: Engaged Human Learning through Participation in Language Model Agent Conversations Proceedings of EMNLP 2024 doi (arXiv) human-ai-research-collaboration agentic-reasoning evaluation-of-ai-research jiang2024costorm skimmed
2024 Kankanhalli Peer Review in the Age of Generative AI Journal of the Association for Information Systems doi ai-peer-review sociotechnical kankanhalli2024peerreview skimmed
2024 Latona et al. The AI Review Lottery: Widespread AI-Assisted Peer Reviews Boost Paper Scores and Acceptance Rates arXiv doi (arXiv) ai-peer-review evaluation-of-ai-research ai-publishing-ecosystems latona2024reviewlottery read
2024 Liang et al. Mapping the Increasing Use of LLMs in Scientific Papers arXiv doi (arXiv) research-productivity evaluation-of-ai-research liang2024mapping read
2024 Liang et al. Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews arXiv doi (arXiv) ai-peer-review evaluation-of-ai-research sociotechnical liang2024monitoring read
2024 Lu et al. The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery arXiv doi (arXiv) autonomous-research-agents ai-peer-review evaluation-of-ai-research lu2024aiscientist skimmed
2024 Lund et al. The Impact of AI on Academic Research and Publishing arXiv doi (arXiv) ai-publishing-ecosystems research-ethics peer-review lund2024aiacademic read
2024 Musslick et al. AutoRA: Automated Research Assistant for Closed-Loop Empirical Research Journal of Open Source Software doi · open musslick2024autora —
2024 Narayanan et al. Aviary: training language agents on challenging scientific tasks arXiv doi (arXiv) agentic-tool-use agentic-reasoning evaluation-of-ai-research narayanan2024aviary skimmed
2024 Ngwenyama & Rowe Should We Collaborate with AI to Conduct Literature Reviews? Changing Epistemic Values in a Flattening World Journal of the Association for Information Systems doi is-methodology human-ai-research-collaboration evaluation-of-ai-research ngwenyama2024literature skimmed
2024 Riemer & Peter Conceptualizing Generative AI as Style Engines: Application Archetypes and Implications International Journal of Information Management doi style-engines is-methodology sociotechnical riemer2024styleengines read
2024 Sabherwal & Grover The Societal Impacts of Generative Artificial Intelligence: A Balanced Perspective Journal of the Association for Information Systems doi sociotechnical sabherwal2024societal skimmed
2024 Sarker et al. Democratizing Knowledge Creation Through Human-AI Collaboration in Academic Peer Review Journal of the Association for Information Systems doi ai-peer-review is-methodology human-ai-research-collaboration sarker2024democratizing skimmed
2024 Schwartz & Te'eni AI for Knowledge Creation, Curation, and Consumption in Context Journal of the Association for Information Systems doi is-methodology human-ai-research-collaboration ai-publishing-ecosystems schwartz2024kcc read
2024 Shao et al. Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models Proceedings of NAACL 2024 doi (arXiv) agentic-reasoning hallucination evaluation-of-ai-research shao2024storm skimmed
2024 Shmueli & Ray Reimagining the Journal Editorial Process: An AI-Augmented Versus an AI-Driven Future Journal of the Association for Information Systems doi ai-peer-review is-methodology shmueli2024editorial skimmed
2024 Siegel et al. CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmark arXiv doi (arXiv) replication-infrastructure evaluation-of-ai-research autonomous-research-agents siegel2024corebench queued
2024 Skarlinski et al. Language agents achieve superhuman synthesis of scientific knowledge arXiv doi (arXiv) hallucination agentic-tool-use evaluation-of-ai-research skarlinski2024paperqa2 skimmed
2024 Wang et al. AutoSurvey: Large Language Models Can Automatically Write Surveys Advances in Neural Information Processing Systems 37 (NeurIPS 2024) doi (arXiv) autonomous-research-agents evaluation-of-ai-research agentic-reasoning wang2024autosurvey skimmed
2024 Watson et al. Extending the Foresight of Phillip Ein-Dor: Causal Knowledge Analytics Journal of the Association for Information Systems doi is-methodology evaluation-of-ai-research watson2024causal skimmed
2024 Weber The Other Reviewer: RoboReviewer Journal of the Association for Information Systems doi ai-peer-review sociotechnical weber2024roboreviewer skimmed
2024 Yoo Evolving Epistemic Infrastructure: The Role of Scientific Journals in the Age of Generative AI Journal of the Association for Information Systems doi is-methodology sociotechnical evaluation-of-ai-research yoo2024epistemic skimmed
2025 Agarwal et al. AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise arXiv doi (arXiv) autonomous-research-agents agentic-reasoning evaluation-of-ai-research agarwal2025autodiscovery skimmed
2025 Ashery et al. Emergent social conventions and collective bias in LLM populations Science Advances doi · arXiv llm-cognition sociotechnical ashery2025emergent queued
2025 Banerjee et al. Where Did It All Go Wrong? A Hierarchical Look into Multi-Agent Error Attribution arXiv doi (arXiv) agentic-reasoning reasoning-faithfulness banerjee2025hierarchical queued
2025 Bapna et al. Agentic AI and Managers' Analytics Capabilities: An Exploration SSRN Working Paper link research-productivity human-ai-research-collaboration agentic-tool-use bapna2025analytics read
2025 Bianchi et al. Exploring the use of AI authors and reviewers at Agents4Science arXiv doi (arXiv) autonomous-research-agents ai-peer-review ai-publishing-ecosystems evaluation-of-ai-research bianchi2025exploring queued
2025 Bragg et al. AstaBench: Rigorous Benchmarking of AI Agents with a Scientific Research Suite arXiv doi (arXiv) evaluation-of-ai-research autonomous-research-agents agentic-tool-use bragg2025astabench skimmed
2025 Brodeur et al. Assessing Reproducibility in Economics Using Standardized Crowd-Sourced Analysis National Bureau of Economic Research link replication-infrastructure evaluation-of-ai-research brodeur2025reproducibility read
2025 Brynjolfsson et al. Generative AI at Work Quarterly Journal of Economics doi research-productivity human-ai-research-collaboration sociotechnical brynjolfsson2025genaiwork read
2025 Chen & others Reasoning Models Don't Always Say What They Think arXiv doi (arXiv) reasoning-faithfulness agentic-reasoning hallucination evaluation-of-ai-research chen2025reasoning read
2025 Collu et al. Misleading Large Language Models Used (or Misused) in Scientific Peer-Reviewing via Hidden Prompt-Injection Attacks arXiv doi (arXiv) ai-peer-review hallucination sociotechnical collu2025misleading read
2025 Cunningham Claude Code for Causal Inference Causal Inference Substack link cunningham2025claudecode —
2025 Eberhardt Claude Code for Applied Economists Markus Academy Substack link eberhardt2025claudecode —
2025 Editorial Transparent Peer Review to Be Extended to All Research Papers Nature Editorial, d41586-025-01880-9 link ai-peer-review ai-publishing-ecosystems sociotechnical naturePeerReview2025editorial read
2025 Filimonovic et al. Can GenAI Improve Academic Performance? Evidence from the Social and Behavioral Sciences arXiv doi (arXiv) research-productivity human-ai-research-collaboration evaluation-of-ai-research filimonovic2025genai read
2025 Gao et al. ToolUniverse: An open platform for democratizing AI scientists arXiv doi (arXiv) agentic-tool-use autonomous-research-agents gao2025tooluniverse skimmed
2025 Georgiev et al. Mathematical Exploration and Discovery at Scale arXiv doi (arXiv) georgiev2025alphaevolvemath —
2025 Gopal & others Inventing with Machines: Generative AI and the Evolving Landscape of IS Research Information Systems Research doi is-methodology human-ai-research-collaboration autonomous-research-agents sociotechnical gopal2025inventing read
2025 Gridach et al. Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directions arXiv doi (arXiv) autonomous-research-agents evaluation-of-ai-research gridach2025agenticsurvey skimmed
2025 Guo et al. ADRA-Bank: A Modular Benchmark for Academic Deep Research Agents arXiv doi (arXiv) evaluation-of-ai-research agentic-tool-use autonomous-research-agents guo2025adrabank queued
2025 Hu et al. REPRO-Bench: Can Agentic AI Systems Assess the Reproducibility of Social Science Research? arXiv doi (arXiv) replication-infrastructure evaluation-of-ai-research autonomous-research-agents hu2025reprobench queued
2025 Ifargan et al. Autonomous LLM-Driven Research — from Data to Human-Verifiable Research Papers NEJM AI doi agentic-pipelines traceability-verifiability end-to-end-research ifargan2024datatopaper read
2025 Karger et al. ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities arXiv doi (arXiv) evaluation-of-ai-research karger2025forecastbench queued
2025 Keuper Prompt Injection Attacks on LLM Generated Reviews of Scientific Publications arXiv doi (arXiv) ai-peer-review hallucination keuper2025promptinjection read
2025 Kim et al. Correlated Errors in Large Language Models arXiv doi (arXiv) llm-cognition agentic-reasoning kim2025correlated queued
2025 Korinek AI Agents for Economic Research: August 2025 Update of ``Generative AI for Economic Research: Use Cases and Implications for Economists'' Update to Journal of Economic Literature 61(4) link autonomous-research-agents agentic-tool-use research-productivity korinek2025agents skimmed
2025 Kusumegi et al. Scientific production in the era of Large Language Models Science doi · open research-productivity ai-publishing-ecosystems evaluation-of-ai-research style-engines kusumegi2025scientific queued
2025 Kwon & Yang Large Language Models in Academia: Boosting Productivity but Reinforcing Inequality Proceedings of the International Conference on Information Systems (ICIS) link research-productivity sociotechnical kwon2025inequality skimmed
2025 Li et al. R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization arXiv doi (arXiv) li2025rdagentquant —
2025 Liang et al. SurveyX: Academic Survey Automation via Large Language Models arXiv doi (arXiv) autonomous-research-agents evaluation-of-ai-research hallucination liang2025surveyx skimmed
2025 Luo et al. The More You Automate, the Less You See: Hidden Pitfalls of AI Scientist Systems arXiv doi (arXiv) evaluation-of-ai-research autonomous-research-agents replication-infrastructure reasoning-faithfulness luo2025you queued
2025 Matton & others Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations International Conference on Learning Representations (ICLR) doi (arXiv) reasoning-faithfulness hallucination evaluation-of-ai-research matton2025walkthetalk read
2025 Mikalef et al. Responsible AI Starts with the Artifact: Challenging the Concept of Responsible AI in IS Research European Journal of Information Systems doi sociotechnical is-methodology evaluation-of-ai-research mikalef2025responsible read
2025 Mitchener et al. Kosmos: An AI Scientist for Autonomous Discovery arXiv doi (arXiv) autonomous-research-agents hallucination research-productivity evaluation-of-ai-research mitchener2025kosmos skimmed
2025 Moussa et al. ScholarEval: Research Idea Evaluation Grounded in Literature arXiv doi (arXiv) moussa2025scholareval —
2025 Naddaf AI Is Transforming Peer Review — and Many Scientists Are Worried Nature doi ai-peer-review ai-publishing-ecosystems sociotechnical naddaf2025aipeer read
2025 Nathani et al. MLGym: A New Framework and Benchmark for Advancing AI Research Agents arXiv doi (arXiv) evaluation-of-ai-research autonomous-research-agents agentic-tool-use nathani2025mlgym skimmed
2025 Novikov et al. AlphaEvolve: A Coding Agent for Scientific and Algorithmic Discovery arXiv doi (arXiv) novikov2025alphaevolve —
2025 O'Brien et al. A survey of generative AI adoption and perceived productivity among scientists who program arXiv doi (arXiv) research-productivity human-ai-research-collaboration agentic-tool-use obrien2025survey queued
2025 Peter et al. The Benefits and Dangers of Anthropomorphic Conversational Agents Proceedings of the National Academy of Sciences doi sociotechnical llm-cognition peter2025anthropomorphic read
2025 Schmidgall et al. Agent Laboratory: Using LLM Agents as Research Assistants arXiv doi (arXiv) autonomous-research-agents human-ai-research-collaboration evaluation-of-ai-research schmidgall2025agentlaboratory skimmed
2025 Seo et al. Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning arXiv doi (arXiv) replication-infrastructure autonomous-research-agents seo2025paper2code skimmed
2025 Shen et al. Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems arXiv doi (arXiv) agentic-reasoning llm-cognition shen2025understanding queued
2025 Si et al. The Ideation-Execution Gap: Execution Outcomes of LLM-Generated versus Human Research Ideas arXiv doi (arXiv) reasoning-faithfulness evaluation-of-ai-research si2025ideationexecution queued
2025 Starace et al. PaperBench: Evaluating AI's Ability to Replicate AI Research arXiv doi (arXiv) evaluation-of-ai-research replication-infrastructure autonomous-research-agents starace2025paperbench queued
2025 Tang et al. AI-Researcher: Autonomous Scientific Innovation arXiv doi (arXiv) autonomous-research-agents evaluation-of-ai-research tang2025airesearcher queued
2025 Team Tongyi DeepResearch Technical Report arXiv doi (arXiv) agentic-reasoning agentic-tool-use tongyi2025deepresearch skimmed
2025 Tie et al. A Survey of AI Scientists arXiv doi (arXiv) autonomous-research-agents evaluation-of-ai-research tie2025aiscientistsurvey read
2025 Weng et al. DeepScientist: Advancing Frontier-Pushing Scientific Findings Progressively arXiv doi (arXiv) weng2025deepscientist —
2025 Wu & others Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) doi agentic-reasoning agentic-tool-use wu2025agenticreasoning read
2025 Xian et al. Reliable agent engineering should integrate machine-compatible organizational principles arXiv doi (arXiv) agentic-reasoning xian2025reliable queued
2025 Yamada et al. The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search arXiv doi (arXiv) autonomous-research-agents ai-peer-review evaluation-of-ai-research yamada2025aiscientistv2 skimmed
2025 Yang et al. R&D-Agent: An LLM-Agent Framework Towards Autonomous Data Science arXiv doi (arXiv) yang2025rdagent —
2025 Yang et al. Topological Structure Learning Should Be A Research Priority for LLM-Based Multi-Agent Systems arXiv doi (arXiv) agentic-reasoning yang2025topological queued
2025 Yu et al. ResearchTown: Simulator of Human Research Community Proceedings of the 42nd International Conference on Machine Learning (ICML 2025) doi (arXiv) autonomous-research-agents ai-peer-review sociotechnical evaluation-of-ai-research yu2025researchtown skimmed
2025 Zhang & others aiXiv: A Next-Generation Open Access Ecosystem for Scientific Discovery Generated by AI Scientists arXiv doi (arXiv) ai-publishing-ecosystems autonomous-research-agents ai-peer-review sociotechnical zhang2025aixiv read
2025 Zhang et al. Stop Overvaluing Multi-Agent Debate – We Must Rethink Evaluation and Embrace Model Heterogeneity arXiv doi (arXiv) agentic-reasoning llm-cognition zhang2025overvaluing queued
2025 Zheng et al. DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments arXiv doi (arXiv) agentic-tool-use agentic-reasoning hallucination zheng2025deepresearcher skimmed
2026 Abbasi & others ISR Special Issue: Generative AI and New Methods of Inquiry in Information Systems Research INFORMS Information Systems Research, Call for Papers link abbasi2026isr —
2026 Acemoglu et al. How AI Aggregation Affects Knowledge National Bureau of Economic Research link sociotechnical reasoning-faithfulness acemoglu2026ai queued
2026 Acemoglu et al. AI, Human Cognition and Knowledge Collapse SSRN Working Paper link sociotechnical evaluation-of-ai-research llm-cognition acemoglu2026collapse read
2026 Agarwal et al. ICML 2026 LLM Policy for Reviewing (Introduction to the ICML 2026 LLM Policy) ICML 2026 link ai-peer-review ai-publishing-ecosystems sociotechnical agarwal2026icml queued
2026 Ai et al. Beyond Majority Voting: LLM Aggregation by Leveraging Higher-Order Information arXiv doi (arXiv) agentic-reasoning ai2026majority queued
2026 Alizadeh et al. AI Coding Agents Can Reproduce Social Science Findings arXiv doi (arXiv) alizadeh2026coding —
2026 Alotaibi et al. Layered LLM Defenses as an Ensemble: Access Tiers, Inference Cost, and the Measured Failure Correlation Between Defense Layers arXiv doi (arXiv) agentic-reasoning llm-cognition alotaibi2026layered queued
2026 Andrews & Sarkar Dutch Books for Language Models arXiv doi (arXiv) evaluation-of-ai-research reasoning-faithfulness andrews2026dutch queued
2026 Angelini & Lyrvall Normative boundaries of AI in scientific work: Evidence from PhD researchers arXiv doi (arXiv) human-ai-research-collaboration sociotechnical research-productivity angelini2026normative queued
2026 Bara Epistemic Sybil Resistance: Multiplying AI Agents Without Multiplying Evidence arXiv doi (arXiv) agentic-reasoning llm-cognition sociotechnical reasoning-faithfulness bara2026epistemic queued
2026 Baumann et al. Stop Automating Peer Review Without Rigorous Evaluation arXiv doi (arXiv) ai-peer-review evaluation-of-ai-research ai-publishing-ecosystems baumann2026automating queued
2026 Begin et al. Preference Optimization Drives Monoculture in LLM Prediction Markets arXiv doi (arXiv) llm-cognition evaluation-of-ai-research agentic-reasoning begin2026preference queued
2026 Bertalanič & Fortuna The Cost of Consensus: Isolated Self-Correction Prevails Over Unguided Homogeneous Multi-Agent Debate ACM Conference on AI and Agentic Systems doi · arXiv llm-cognition agentic-reasoning bertalanic2026cost queued
2026 Bhargava et al. Fighting Fire with Fire: Infusing Artificial Intelligence into Peer Review to Sustain Quality Scholarship Management Science doi · open ai-peer-review ai-publishing-ecosystems human-ai-research-collaboration sociotechnical bhargava2026fighting queued
2026 Bhushan et al. Can LLM Agents Discover? Evaluating Creativity on ML Engineering Tasks arXiv doi (arXiv) evaluation-of-ai-research autonomous-research-agents agentic-reasoning llm-cognition bhushan2026llm queued
2026 Bick et al. The Rapid Adoption of Generative AI Management Science doi research-productivity sociotechnical ai-publishing-ecosystems bick2026rapidadoption read
2026 Bisht et al. Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery arXiv doi (arXiv) autonomous-research-agents evaluation-of-ai-research agentic-reasoning sociotechnical bisht2026agentic queued
2026 Biswas & Charlin NeurIPS 2026 AI-Assisted Reviewing Experiment NeurIPS 2026 link ai-peer-review evaluation-of-ai-research ai-publishing-ecosystems human-ai-research-collaboration biswas2026neurips queued
2026 Biswas et al. AI-Assisted Peer Review at Scale: The AAAI-26 AI Review Pilot arXiv doi (arXiv) ai-peer-review evaluation-of-ai-research ai-publishing-ecosystems biswas2026aiassisted queued
2026 Br\^\incoveanu et al. Augmenting Systematic Literature Reviews: A Human-AI Collaborative Framework German Conference on Artificial Intelligence (K\"unstliche Intelligenz) doi is-methodology human-ai-research-collaboration brincoveanu2026augmenting read
2026 Brown Editor's Comments: The Evolution of Research in MIS Quarterly Over Five Decades MIS Quarterly doi · open is-methodology research-productivity human-ai-research-collaboration ai-publishing-ecosystems brown2026editors queued
2026 Camelo-Guerrero & Diaz-Rodriguez How Closely Do LLM Reviews Align with Human Peer Review? arXiv doi (arXiv) ai-peer-review evaluation-of-ai-research llm-cognition cameloguerrero2026closely queued
2026 Camuffo et al. Beyond Black Boxes: Designing and Testing Agentic AI Systems for Strategy Strategy Science doi · open sociotechnical camuffo2026black queued
2026 Chairs ICLR 2026 Reviewer Guide (LLM disclosure and responsibility policy) ICLR 2026 link ai-peer-review ai-publishing-ecosystems iclr2026iclr queued
2026 Chawla Scientists decry conference's use of hidden prompts to snare AI peer reviews The Transmitter link ai-peer-review sociotechnical ai-publishing-ecosystems chawla2026scientists queued
2026 Chen et al. AgentEconomist: An End-to-end Agentic System Translating Economic Intuitions into Executable Computational Experiments arXiv doi (arXiv) chen2026agenteconomist —
2026 Chen et al. Diversity Collapse in Multi-Agent LLM Systems: Structural Coupling and Collective Failure in Open-Ended Idea Generation arXiv doi (arXiv) agentic-reasoning llm-cognition reasoning-faithfulness chen2026diversity queued
2026 Chen et al. Ideation Arena: Evaluating LLM Generated Research Ideas with Battle-style Human Expert Assessment arXiv doi (arXiv) evaluation-of-ai-research autonomous-research-agents human-ai-research-collaboration chen2026ideation queued
2026 Chen et al. LEAP: Likelihood Elicitation and Aggregation for LLM-based Probabilistic Forecasting arXiv doi (arXiv) agentic-reasoning evaluation-of-ai-research reasoning-faithfulness chen2026leap queued
2026 Chen et al. Toward an Organizational Science of Multi-Agent LLM Systems: Decoupling Who, How, and Which Algorithm arXiv doi (arXiv) agentic-reasoning sociotechnical chen2026organizational queued
2026 Cheng et al. PolyBench: Benchmarking LLM Forecasting and Trading Capabilities on Live Prediction Market Data arXiv doi (arXiv) agentic-reasoning evaluation-of-ai-research cheng2026polybench queued
2026 Csaszar & Eklund Revisiting the Unitary Actor Assumption: Toward Realistic Aggregation of Individual Preferences in Strategy Research arXiv doi (arXiv) agentic-reasoning sociotechnical csaszar2026revisiting queued
2026 Davison et al. Research Integrity Matters, But It Is Undermined by Generative AI Information Systems Journal doi · open ai-publishing-ecosystems is-methodology ai-peer-review research-productivity davison2026research queued
2026 Dell'Acqua et al. Navigating the Jagged Technological Frontier: Field Experimental Evidence of the Effects of Artificial Intelligence on Knowledge Worker Productivity and Quality Organization Science doi research-productivity human-ai-research-collaboration evaluation-of-ai-research dellacqua2026jagged read
2026 Deng et al. Examining and Addressing Barriers to Diversity in LLM-Generated Ideas arXiv doi (arXiv) reasoning-faithfulness llm-cognition deng2026examining queued
2026 Ding et al. Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap arXiv doi (arXiv) reasoning-faithfulness agentic-reasoning ding2026autonomous queued
2026 Dochkina Drop the Hierarchy and Roles: How Self-Organizing LLM Agents Outperform Designed Structures arXiv doi (arXiv) agentic-reasoning sociotechnical dochkina2026drop queued
2026 Douven Wisdom of LLM Crowds: Aggregation and Contamination in Language Model Ensembles arXiv doi (arXiv) agentic-reasoning evaluation-of-ai-research douven2026wisdom queued
2026 Dupont et al. Improving the matrix multiplication exponent with modern optimization and AlphaEvolve arXiv doi (arXiv) autonomous-research-agents dupont2026matrix skimmed
2026 Dylan et al. At Equal Inference Cost, Multi-Agent Structure Does Not Beat a Single Frozen Agent arXiv doi (arXiv) agentic-reasoning sociotechnical dylan2026equal queued
2026 Elahi & Di Eugenio Multiagent Protocols with Aggregated Confidence Signals arXiv doi (arXiv) agentic-reasoning elahi2026multiagent queued
2026 Elazar & Antoniak LLM-Generated or Human-Written? Comparing Review and Non-Review Papers on ArXiv arXiv doi (arXiv) ai-publishing-ecosystems evaluation-of-ai-research ai-peer-review elazar2026llmgenerated queued
2026 Fourati et al. The Boundaries of Automation: A Theory of Persistent Human Participation arXiv doi (arXiv) human-ai-research-collaboration sociotechnical llm-cognition fourati2026boundaries skimmed
2026 Gaddipati et al. MLReplicate: Benchmarking Autonomous Research Systems for Machine Learning Reproducibility arXiv doi (arXiv) evaluation-of-ai-research replication-infrastructure autonomous-research-agents hallucination gaddipati2026mlreplicate queued
2026 Gao et al. Testing Interchangeability in LLM Agent Teams arXiv doi (arXiv) agentic-reasoning gao2026testing queued
2026 Gartenberg et al. More Versus Better: Artificial Intelligence, Incentives, and the Emerging Crisis in Peer Review Organization Science doi ai-peer-review ai-publishing-ecosystems research-productivity gartenberg2026morebetter read
2026 Ghareeb et al. A Multi-Agent System for Automating Scientific Discovery Nature doi · arXiv agentic-pipelines multi-agent-systems autonomous-research-agents end-to-end-research ghareeb2026robin read
2026 Gottweis et al. Accelerating scientific discovery with Co-Scientist Nature doi · arXiv autonomous-research-agents agentic-reasoning human-ai-research-collaboration gottweis2026coscientist skimmed
2026 Guo et al. It's Not Always Sycophancy: Measuring LLM Conformity as a Function of Epistemic Uncertainty arXiv doi (arXiv) llm-cognition guo2026its queued
2026 Hanneke et al. Academic Publishing in the Age of Generative AI Business \& Information Systems Engineering doi · open hanneke2026academic —
2026 Hans & Bilionis Coding-agents can replicate scientific machine learning papers arXiv doi (arXiv) replication-infrastructure agentic-tool-use reasoning-faithfulness autonomous-research-agents hans2026codingagents queued
2026 Hao et al. Artificial intelligence tools expand scientists’ impact but contract science’s focus Nature doi · open research-productivity evaluation-of-ai-research sociotechnical human-ai-research-collaboration hao2026artificial queued
2026 He & Bu Academic journals’ AI policies fail to curb the surge in AI-assisted academic writing Proceedings of the National Academy of Sciences doi · open ai-publishing-ecosystems research-productivity sociotechnical style-engines he2026academic queued
2026 He & Yu The Illusion of Independent Quorums: Epistemic Fault Domains and Correlated Cognitive Failures in Agentic Quorums arXiv doi (arXiv) agentic-reasoning llm-cognition sociotechnical reasoning-faithfulness he2026illusion queued
2026 He et al. Beneath the Diff: Diagnosing and Mitigating Algorithmic Mode Collapse in Code-Level Autonomous Research Loops arXiv doi (arXiv) autonomous-research-agents evaluation-of-ai-research reasoning-faithfulness agentic-tool-use he2026beneath queued
2026 He et al. Minority Sentinel: When to Overturn Majority Voting in Multi-Agent LLM Debates arXiv doi (arXiv) agentic-reasoning llm-cognition he2026minority queued
2026 Hemmatian et al. Collective Cognition in Hybrid Groups: A Network Science Synthesis arXiv doi (arXiv) sociotechnical agentic-reasoning reasoning-faithfulness hemmatian2026collective queued
2026 Hill & Stein How Artificial Intelligence Shapes Science: Evidence from AlphaFold National Bureau of Economic Research doi · NBER research-productivity evaluation-of-ai-research human-ai-research-collaboration hill2026artificial queued
2026 Hirsch et al. Who is the Agent to Blame? Localizing Faithfulness and Citation Mistakes in Agentic Deep Research arXiv doi (arXiv) reasoning-faithfulness hallucination agentic-tool-use evaluation-of-ai-research hirsch2026who queued
2026 Hochberg & Thrall AI will reorganize science. Will research remain a human enterprise? Proceedings of the National Academy of Sciences doi · open ai-publishing-ecosystems autonomous-research-agents sociotechnical evaluation-of-ai-research hochberg2026ai queued
2026 Hoda et al. Antipatterns in AI-assisted Qualitative Data Analysis: A Catalog of Temptations and Pitfalls for Software Engineering Researchers arXiv doi (arXiv) human-ai-research-collaboration is-methodology sociotechnical hoda2026antipatterns queued
2026 Hu et al. SA-Bench: Evaluating Semantic Alignment in LLM-Based Paper Reproduction arXiv doi (arXiv) replication-infrastructure evaluation-of-ai-research autonomous-research-agents reasoning-faithfulness hu2026sabench queued
2026 Huang et al. Counterfactual Graph for Multi-Agent LLM Calibration arXiv doi (arXiv) agentic-reasoning llm-cognition huang2026counterfactual queued
2026 Hutson AI isn’t ready to research itself Nature doi · open autonomous-research-agents evaluation-of-ai-research ai-publishing-ecosystems hutson2026ai queued
2026 Jarzębowicz et al. The Landscape of Generative AI in Information Systems: A Synthesis of Secondary Reviews and Research Agendas arXiv doi (arXiv) is-methodology sociotechnical ai-publishing-ecosystems jarzebowicz2026landscape read
2026 Ji et al. Candidate supply and answer selection shape the value of LLM judging in multi-agent systems arXiv doi (arXiv) agentic-reasoning sociotechnical reasoning-faithfulness ji2026candidate queued
2026 Jiang et al. When Evidence Shapes Collaboration: Knowledge-Conditioned Topology Generation for Multi-Agent Systems arXiv doi (arXiv) agentic-reasoning jiang2026evidence queued
2026 Jiang et al. Specialize Roles, Mix Deployments: Pushing the Cost-Accuracy Frontier of LLM Agent Teams arXiv doi (arXiv) agentic-reasoning jiang2026specialize queued
2026 Jin et al. Toward Generalist Autonomous Research via Hypothesis-Tree Refinement arXiv doi (arXiv) autonomous-research-agents agentic-reasoning evaluation-of-ai-research jin2026arbor skimmed
2026 Jin et al. Remember and Reweight: Enhancing Multi-Agent Debate with Experience Memory and Confidence Estimation arXiv doi (arXiv) agentic-reasoning llm-cognition jin2026remember queued
2026 Kapetanovic et al. Anchoring Bias in LLM-as-a-Judge Systems: Prior Scores Compromise Evaluation Independence arXiv doi (arXiv) agentic-reasoning llm-cognition kapetanovic2026anchoring queued
2026 Kapur et al. Federation Is Nearly Free, Reasoning Is Not: Tradeoffs for AI Co-Scientists in Protein Characterization Workflows arXiv doi (arXiv) sociotechnical agentic-reasoning kapur2026federation queued
2026 Kasprova et al. Too Polite to Disagree: Understanding Sycophancy Propagation in Multi-Agent Systems arXiv doi (arXiv) llm-cognition agentic-reasoning kasprova2026polite queued
2026 Keramati et al. Early-Token Confidence Predicts Reasoning Quality in Multi-Agent LLM Debate arXiv doi (arXiv) reasoning-faithfulness agentic-reasoning keramati2026earlytoken queued
2026 Kim et al. Capable language models can outgrow the benefits of collaboration Nature Machine Intelligence doi · open agentic-reasoning sociotechnical kim2026capable queued
2026 Koch et al. BixBench3: Benchmarking AI agents on research-study-scale computational biology tasks arXiv doi (arXiv) evaluation-of-ai-research autonomous-research-agents agentic-tool-use koch2026bixbench3 queued
2026 Kohler et al. Read the Paper, Write the Code: Agentic Reproduction of Social-Science Results arXiv doi (arXiv) replication-infrastructure evaluation-of-ai-research kohler2026agenticreproduction skimmed
2026 Kong et al. Multi-LLM Systems Exhibit Robust Semantic Collapse arXiv doi (arXiv) agentic-reasoning llm-cognition reasoning-faithfulness kong2026multillm queued
2026 Kota Design and Evaluation of Multi-Agent AI Oracle Systems for Prediction Market Resolution arXiv doi (arXiv) agentic-reasoning evaluation-of-ai-research llm-cognition kota2026design queued
2026 Kumar et al. Agentic Artificial Intelligence as a New Frontier in Information Systems: Promise, Peril, and Research Opportunities Information \& Management doi autonomous-research-agents is-methodology sociotechnical kumar2025agenticadoption read
2026 Laban et al. LLMs Corrupt Your Documents When You Delegate arXiv doi (arXiv) agentic-tool-use hallucination evaluation-of-ai-research reasoning-faithfulness laban2026llmscorrupt read
2026 Li The Ideation Bottleneck: Decomposing the Quality Gap Between AI-Generated and Human Economics Research arXiv doi (arXiv) evaluation-of-ai-research autonomous-research-agents li2026ideation skimmed
2026 Li & Hai State-dependent error correlations shape voting thresholds in committees of AI agents arXiv doi (arXiv) agentic-reasoning llm-cognition sociotechnical reasoning-faithfulness li2026statedependent queued
2026 Li et al. Agentic AI and the Rise of in silico Team Science in Biomedical Research Nature Biotechnology doi agentic-pipelines multi-agent-systems autonomous-research-agents sociotechnical li2026agenticbiomedical read
2026 Li et al. Discovering Efficient and Explainable Communication Topologies for LLM-based Multi-Agent Systems via Causal Inference arXiv doi (arXiv) agentic-reasoning li2026discovering queued
2026 Li et al. Diverse Evidence, Better Forecasts: Multi-Agent Deliberation Under Information Asymmetry arXiv doi (arXiv) agentic-reasoning llm-cognition evaluation-of-ai-research li2026diverse queued
2026 Li et al. Gaming AI-Assisted Peer Reviews Poses New Risks to the Scientific Community arXiv doi (arXiv) ai-peer-review evaluation-of-ai-research ai-publishing-ecosystems li2026gaming queued
2026 Li et al. ReproRepo: Scaling Reproducibility Audits with GitHub Repository Issues arXiv doi (arXiv) replication-infrastructure evaluation-of-ai-research li2026reprorepo skimmed
2026 Lin et al. HalluPeer: A Taxonomy-driven Benchmark for Detecting Hallucinations in Scientific Peer Reviews arXiv doi (arXiv) ai-peer-review hallucination evaluation-of-ai-research lin2026hallupeer queued
2026 Liu et al. AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration arXiv doi (arXiv) autonomous-research-agents human-ai-research-collaboration hallucination evaluation-of-ai-research liu2026autoresearchclaw skimmed
2026 Liu et al. Breaking the Martingale Curse: Multi-Agent Debate via Asymmetric Cognitive Potential Energy arXiv doi (arXiv) agentic-reasoning llm-cognition liu2026breaking queued
2026 Liu et al. Citing Less Critically: LLMs Reshape the Rhetoric and Reach of Scientific Citation arXiv doi (arXiv) ai-publishing-ecosystems research-productivity style-engines sociotechnical liu2026citing queued
2026 Liu et al. Phase Transition for Budgeted Multi-Agent Synergy arXiv doi (arXiv) agentic-reasoning llm-cognition liu2026phase queued
2026 Liu et al. Social Networks of LLM Agents arXiv doi (arXiv) agentic-reasoning llm-cognition liu2026social queued
2026 Lopez-Lira ZeroPaper: An Autonomous Research System Institute for Automated Research working paper IAR-M-001; also SSRN 6687378 link autonomous-research-agents ai-publishing-ecosystems lopezlira2026zeropaper queued
2026 Lu et al. AI-Generated Papers in the NeurIPS 2026 Position Paper Track NeurIPS 2026 Blog link ai-publishing-ecosystems ai-peer-review evaluation-of-ai-research lu2026aigenerated queued
2026 Lu et al. Topological collapse of higher-order interactions bottlenecks collective intelligence in AI agent societies arXiv doi (arXiv) agentic-reasoning llm-cognition lu2026topological queued
2026 Lupidi et al. AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents arXiv doi (arXiv) evaluation-of-ai-research autonomous-research-agents lupidi2026airsbench skimmed
2026 Lyu et al. EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discovery arXiv doi (arXiv) agentic-pipelines multi-agent-systems self-improvement memory-systems evoscientist2026techreport read
2026 Marandi The impact of multi-agent debate protocols on debate quality: a controlled case study arXiv doi (arXiv) agentic-reasoning reasoning-faithfulness marandi2026impact queued
2026 Meng et al. ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence arXiv doi (arXiv) evaluation-of-ai-research hallucination autonomous-research-agents replication-infrastructure meng2026scientistone skimmed
2026 Miao et al. Reimagining research papers as interactive and reliable AI agents Nature doi · open agentic-tool-use autonomous-research-agents replication-infrastructure miao2026paper2agent skimmed
2026 Mitchell et al. AI Agents Push Humans Out of the Loop arXiv doi (arXiv) human-ai-research-collaboration sociotechnical llm-cognition mitchell2026ai queued
2026 Miyai et al. Jr. AI Scientist and Its Risk Report: Autonomous Scientific Exploration from a Baseline Paper arXiv doi (arXiv) autonomous-research-agents evaluation-of-ai-research human-ai-research-collaboration ai-publishing-ecosystems miyai2026jr queued
2026 Nechepurenko & Shuvalov Coordination as an Architectural Layer for LLM-Based Multi-Agent Systems arXiv doi (arXiv) agentic-reasoning evaluation-of-ai-research sociotechnical nechepurenko2026coordination queued
2026 Nee et al. The Generative AI Gold Rush in Theoretical and Computational Research arXiv doi (arXiv) research-productivity ai-publishing-ecosystems sociotechnical evaluation-of-ai-research nee2026generative queued
2026 Nguyen et al. Creative Generation via Multi-Agent Debate: Does Debate Suppress Diversity? arXiv doi (arXiv) agentic-reasoning llm-cognition nguyen2026creative queued
2026 Nguyen et al. ReplicatorBench: Benchmarking LLM Agents for Replicability in Social and Behavioral Sciences arXiv doi (arXiv) replication-infrastructure evaluation-of-ai-research agentic-tool-use autonomous-research-agents nguyen2026replicatorbench queued
2026 Ngwenyama et al. Platform Capture of Scientific Knowledge Production: Publishers' Dominance, Generative AI and Subsumption of Academic Labor European Journal of Information Systems doi sociotechnical ai-publishing-ecosystems ngwenyama2026platform read
2026 Novy-Marx & Velikov Artificial Intelligence–Powered (Finance) Scholarship Journal of Economic Literature doi · NBER autonomous-research-agents research-productivity evaluation-of-ai-research hallucination novymarx2026aifinance read
2026 Panigrahi et al. HeurekaBench: A Benchmarking Framework for AI Co-scientist arXiv doi (arXiv) panigrahi2026heurekabench —
2026 Park et al. Exploration and Exploitation Errors Are Measurable for Language Model Agents arXiv doi (arXiv) reasoning-faithfulness agentic-reasoning park2026exploration queued
2026 Patel Representational Collapse in Multi-Agent LLM Committees: Measurement and Diversity-Aware Consensus arXiv doi (arXiv) llm-cognition agentic-reasoning patel2026representational queued
2026 Patel et al. Are LLMs becoming similarly creative? Evidence from three years of models arXiv doi (arXiv) llm-cognition patel2026llms queued
2026 Preiss & Yang Guiding LLM Peer Reviewers: The Impact of Score Anchors on Review Evidence and Accuracy arXiv doi (arXiv) ai-peer-review evaluation-of-ai-research reasoning-faithfulness hallucination preiss2026guiding queued
2026 Qu et al. CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery arXiv doi (arXiv) autonomous-research-agents agentic-reasoning qu2026coral skimmed
2026 Rao et al. Detecting and Correcting Reference Hallucinations in Commercial LLMs and Deep Research Agents arXiv doi (arXiv) hallucination agentic-tool-use evaluation-of-ai-research replication-infrastructure rao2026detecting queued
2026 Ravideshik & Kejriwal Can AI Evaluate AI Scientists? A Benchmarking Study of Autonomous Research Generation Systems Using Automated Multi-Model Review arXiv doi (arXiv) evaluation-of-ai-research autonomous-research-agents ai-peer-review ravideshik2026ai queued
2026 Reif & Cummings The Generative AI Dilemma in Knowledge-Intensive Teams Academy of Management Review doi · open human-ai-research-collaboration sociotechnical research-productivity reif2026generative queued
2026 Renault et al. Scientific production in the era of large language models: Outcome-triggered treatment timing and spurious event-study dynamics Proceedings of the National Academy of Sciences doi · open research-productivity evaluation-of-ai-research replication-infrastructure renault2026scientific queued
2026 Riemer et al. Generative AI Is Neither Just Another IT Artefact nor a Colleague: Methodological Guidance for IS Scholarship Information Systems Journal doi · open is-methodology llm-cognition sociotechnical human-ai-research-collaboration riemer2026generative queued
2026 Russinovich et al. Phantom References: Hallucinated Citations That Survive Peer Review at Top-Tier Conferences arXiv doi (arXiv) hallucination ai-peer-review replication-infrastructure ai-publishing-ecosystems russinovich2026phantom queued
2026 Salatino et al. Are Researchers Being Replaced by Artificial Intelligence? arXiv doi (arXiv) human-ai-research-collaboration autonomous-research-agents sociotechnical ai-publishing-ecosystems salatino2026researchers queued
2026 Salgado et al. LLMs in Qualitative Research: Opportunities, Limitations, and Practical Considerations arXiv doi (arXiv) is-methodology human-ai-research-collaboration llm-cognition reasoning-faithfulness salgado2026llms queued
2026 Sharma et al. Value Over Language Model: Detecting Original Contribution in Writing arXiv doi (arXiv) ai-peer-review style-engines human-ai-research-collaboration evaluation-of-ai-research sharma2026value queued
2026 Shen & Wang Detecting AI-Generated Content in Academic Peer Reviews arXiv doi (arXiv) ai-peer-review ai-publishing-ecosystems evaluation-of-ai-research shen2026detecting queued
2026 Song et al. Beyond Consensus: Downward Bias and Role Asymmetry in Multi-Agent LLM Judges for Subjective Evaluation arXiv doi (arXiv) agentic-reasoning song2026consensus queued
2026 Song et al. PaperOrchestra: A Multi-Agent Framework for Automated AI Research Paper Writing arXiv doi (arXiv) song2026paperorchestra —
2026 Stevenson & Fischman Humans in the Loop: The Next Frontier in the Credibility Revolution SSRN working paper 6308160 link is-methodology replication-infrastructure human-ai-research-collaboration stevenson2026humans skimmed
2026 Stoyanov Ethical LLM-Assisted Research: A Framework for Responsible Delegation, Verification, and Epistemic Value arXiv doi (arXiv) human-ai-research-collaboration sociotechnical ai-publishing-ecosystems stoyanov2026ethical queued
2026 Sun et al. Agon: An Autonomous Large-Scale Omnidisciplinary Research System Built on Prompt Economy arXiv doi (arXiv) autonomous-research-agents evaluation-of-ai-research sun2026agon skimmed
2026 Tang et al. FARS: A Fully Automated Research System Deployed at Scale arXiv doi (arXiv) autonomous-research-agents evaluation-of-ai-research ai-publishing-ecosystems replication-infrastructure tang2026fars queued
2026 Thelwall Do Large Language Models Favour Any Research Topics? arXiv doi (arXiv) ai-peer-review evaluation-of-ai-research llm-cognition thelwall2026large queued
2026 Tieman & Markou Inferred Generative-Process Diversity Predicts Correlated Failure Across Language Models arXiv doi (arXiv) llm-cognition reasoning-faithfulness agentic-reasoning tieman2026inferred queued
2026 Tran & Kiela Single-Agent LLMs Outperform Multi-Agent Systems on Multi-Hop Reasoning Under Equal Thinking Token Budgets arXiv doi (arXiv) sociotechnical agentic-reasoning tran2026singleagent queued
2026 Turtel et al. How Proper Scoring Rules Shape LLM Forecasting arXiv doi (arXiv) agentic-reasoning evaluation-of-ai-research reasoning-faithfulness turtel2026proper queued
2026 Virk et al. SwarmResearch: Orchestrating Coding Agents for Open-Ended Discovery arXiv doi (arXiv) virk2026swarmresearch —
2026 Wang & Luan PARNESS: A Paper Harness for End-to-End Automated Scientific Research with Dynamic Workflows, Full-Text Indexing, and Cross-Run Knowledge Accumulation arXiv doi (arXiv) wang2026parness —
2026 Wang & Yang The Consistency Illusion: How Multi-Agent Debate Hides Reasoning Misalignment arXiv doi (arXiv) reasoning-faithfulness agentic-reasoning wang2026consistency queued
2026 Wang et al. Act As a Real Researcher: A Suite of Benchmarks Evaluating Frontier LLMs and Agentic Harnesses in Research Lifecycle arXiv doi (arXiv) evaluation-of-ai-research autonomous-research-agents agentic-reasoning wang2026aarribench skimmed
2026 Wang et al. From Agent Traces to Trust: A Survey of Evidence Tracing and Execution Provenance in LLM Agents arXiv doi (arXiv) reasoning-faithfulness wang2026agent queued
2026 Wang et al. Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents arXiv doi (arXiv) autonomous-research-agents evaluation-of-ai-research agentic-reasoning replication-infrastructure wang2026learning queued
2026 Wang et al. NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers? arXiv doi (arXiv) evaluation-of-ai-research replication-infrastructure autonomous-research-agents wang2026naturebench skimmed
2026 Wang et al. OrgAgent: Organize Your Multi-Agent System like a Company arXiv doi (arXiv) agentic-reasoning sociotechnical wang2026orgagent queued
2026 Wang et al. PaperGym: Rubric-Centered Evolution for Research-Plan Generation arXiv doi (arXiv) evaluation-of-ai-research autonomous-research-agents agentic-reasoning wang2026papergym queued
2026 Wang et al. Smaller, Younger, and More Impactful: How AI-Assisted Writing Transforms Research Teams arXiv doi (arXiv) research-productivity human-ai-research-collaboration sociotechnical wang2026smaller queued
2026 Willner & Yanagizawa-Drott Verifying the Verifiers: Towards Autonomous Policy Evaluation Social Catalyst Lab / University of Zurich working paper link evaluation-of-ai-research ai-peer-review replication-infrastructure willner2026verifying skimmed
2026 Wolfrath et al. Model Retirement Creates Reproducibility Risk in Biomedical AI Publications arXiv doi (arXiv) replication-infrastructure ai-publishing-ecosystems research-productivity wolfrath2026model queued
2026 Wu From production to verification: generative AI, doctoral formation, and the leadership of digital education Frontiers in Education doi · open human-ai-research-collaboration research-productivity sociotechnical is-methodology wu2026production queued
2026 Xu & Yang Scaling Reproducibility: An AI-Assisted Workflow for Large-Scale Replication and Reanalysis arXiv doi (arXiv) replication-infrastructure research-productivity evaluation-of-ai-research xu2026scaling queued
2026 Xu et al. ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research arXiv doi (arXiv) evaluation-of-ai-research autonomous-research-agents replication-infrastructure xu2026researchclawbench queued
2026 Yadav et al. More Capable, Less Cooperative? When LLMs Fail At Zero-Cost Collaboration arXiv doi (arXiv) agentic-reasoning sociotechnical yadav2026capable queued
2026 Yamada et al. Towards End-to-End Automation of AI Research Nature doi · open autonomous-research-agents ai-publishing-ecosystems evaluation-of-ai-research yamada2026endtoend queued
2026 Yang et al. ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration arXiv doi (arXiv) agentic-pipelines multi-agent-systems evaluation-rigor harness-engineering yang2026aris read
2026 Yang et al. Beyond Human-Likeness: Mapping the Scientific Critique Profiles of LLMs and Human Reviewers arXiv doi (arXiv) ai-peer-review evaluation-of-ai-research human-ai-research-collaboration yang2026humanlikeness queued
2026 Yang et al. TruthInsightBench: An Evidence-Grounded Benchmark for Automated Evaluation of Open-Ended Scientific Discovery Agents arXiv doi (arXiv) evaluation-of-ai-research autonomous-research-agents agentic-reasoning replication-infrastructure yang2026truthinsightbench queued
2026 Ye et al. Hindcast: Replaying Prediction Markets to Evaluate LLM Forecasters arXiv doi (arXiv) evaluation-of-ai-research reasoning-faithfulness ye2026hindcast queued
2026 Yoon et al. ArcticSwarm: Deferring Early Consensus in Long-Horizon Multi-Agent Research arXiv doi (arXiv) agentic-reasoning llm-cognition sociotechnical reasoning-faithfulness yoon2026arcticswarm queued
2026 Youngblood et al. Collective creativity in hybrid societies arXiv doi (arXiv) sociotechnical reasoning-faithfulness youngblood2026collective queued
2026 Yu et al. Codebook Agent: Amortized Topology Design for LLM Multi-Agent Systems arXiv doi (arXiv) agentic-reasoning yu2026codebook queued
2026 Yu et al. Beyond Execution: Auditing Experimental Fidelity in LLM-Driven Scientific Research arXiv doi (arXiv) evaluation-of-ai-research autonomous-research-agents hallucination replication-infrastructure yu2026execution queued
2026 Zhang et al. Agora: Git as Shared Memory for Collective AutoResearch arXiv doi (arXiv) autonomous-research-agents agentic-reasoning evaluation-of-ai-research zhang2026agora skimmed
2026 Zhang et al. AI for Computational Design Science: A Responsible Human-AI Framework and Case Study on Short-Form Video Safety Surveillance arXiv doi (arXiv) is-methodology human-ai-research-collaboration autonomous-research-agents replication-infrastructure zhang2026ai queued
2026 Zhang et al. More Criticism Does Not Make a Better Review: EquiReview-R arXiv doi (arXiv) ai-peer-review evaluation-of-ai-research reasoning-faithfulness replication-infrastructure zhang2026criticism queued
2026 Zhang et al. ToolGate: An Executable Acceptance Pipeline for Tool-Dependent Scientific Benchmark Construction arXiv doi (arXiv) evaluation-of-ai-research agentic-tool-use replication-infrastructure zhang2026toolgate queued
2026 Zhao et al. LLM hallucinations in the wild: Large-scale evidence from non-existent citations arXiv doi (arXiv) hallucination ai-publishing-ecosystems research-productivity evaluation-of-ai-research zhao2026llm queued
2026 Zheng et al. AI co-mathematician: Accelerating mathematicians with agentic AI arXiv doi (arXiv) human-ai-research-collaboration autonomous-research-agents agentic-tool-use zheng2026comathematician skimmed
2026 Zhu & Chang ClaimReceipt: Verifying Evidence Sufficiency and Coverage in Agent Evaluations arXiv doi (arXiv) reasoning-faithfulness zhu2026claimreceipt queued
2026 Zhu et al. Demystifying Multi-Agent Debate: The Role of Confidence and Diversity arXiv doi (arXiv) agentic-reasoning llm-cognition zhu2026demystifying queued
2026 Zhu et al. pAI-Econ-claude: A Gated Human-in-the-Loop Multi-Agent Architecture for AI-Assisted Economic Theory Development arXiv doi (arXiv) human-ai-research-collaboration autonomous-research-agents zhu2026paieconclaude skimmed
Browse by theme

agentic-pipelines

agentic-reasoning

agentic-tool-use

ai-peer-review

ai-publishing-ecosystems

autonomous-research-agents

end-to-end-research

evaluation-of-ai-research

evaluation-rigor

hallucination

harness-engineering

human-ai-research-collaboration

is-methodology

llm-cognition

memory-systems

multi-agent-systems

peer-review

reasoning-faithfulness

replication-infrastructure

research-ethics

research-productivity

self-improvement

sociotechnical

style-engines

traceability-verifiability

Browse by year

107/256 notes have been filled with abstract-grounded summaries; 149 remain as stubs marked ⚠️ (front-matter verified, but Summary / Contribution / Method / Critique not yet written).

2026

2025

2024

2023

2020

2019

2012

How to add a paper

  1. Add the BibTeX entry to papers/references.bib with a citekey of the form lastnameYEARword (lowercase, no punctuation).
  2. Create docs/papers/notes/<citekey>.md from the schema template at papers/schema.md.
  3. Fill in the structured summary sections.
  4. Open a pull request.