Research / Library Library Source material we reference and synthesize — academic papers, industry research, and foundational work. Human–AI Collaboration Who's in Charge? On the Dynamics of Human-AI Disempowerment 2026 Sharma et al. — Anthropic How AI Impacts Skill Formation 2026 Shen, Tamkin — Anthropic Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity 2025 Becker, Rush, Barnes, Rein — METR The Effects of Generative AI on High-Skilled Work 2024 Cui et al. — Microsoft / Princeton / MIT Homogenization & Diversity Visual Elevator Music: Aesthetic Convergence in Iterative AI Generation 2026 Hintze et al. — Patterns / Cell Cultural Homogenization in AI-Assisted Writing 2025 Agarwal et al. — CHI 2025 Generative AI and Creativity: A Meta-Analysis 2025 Various — Meta-analysis, 28 studies Artificial Hivemind: The Homogenization of LLM Outputs 2025 Jiang et al. — NeurIPS 2025 Best Paper Generative AI Enhances Individual Creativity but Reduces Collective Diversity 2024 Doshi, Hauser — Science Advances Groups of Diverse Problem Solvers Can Outperform Groups of High-Ability Problem Solvers 2004 Hong, Page — PNAS Multi-Agent Systems Self-Reflecting LLMs: A Hegelian Dialectical Approach 2025 Abdali et al. — Microsoft Research Anka: A Domain-Specific Language for Reliable LLM Code Generation 2025 Al Mazrouei Towards a Science of Scaling Agent Systems 2025 Kim et al. — Google Research / DeepMind / MIT Agentic AI Needs a Systems Theory 2025 Miehling, Natesan Ramamurthy et al. — IBM Research Rethinking the Reliability of Multi-Agent Systems: A BFT Approach 2025 Zheng et al. Improving Factuality and Reasoning through Multiagent Debate 2024 Du, Li, Torralba, Tenenbaum, Mordatch — ICML 2024 Large Language Models Cannot Self-Correct Reasoning Yet 2024 Huang et al. — ICLR 2024 Debating with More Persuasive LLMs Leads to More Truthful Answers 2024 Khan et al. — ICML 2024 Best Paper Encouraging Divergent Thinking through Multi-Agent Debate 2024 Liang et al. — EMNLP 2024 Reaching Agreement in the Presence of Faults 1980 Pease, Shostak, Lamport — Dijkstra Prize 2005 Knowledge Representation Semantic Units: Organizing Knowledge Graphs into Semantically Meaningful Subgraphs 2024 Vogt, Kuhn, Hoehndorf StarE: Message Passing for Hyper-Relational Knowledge Graphs 2020 Galkin et al. — EMNLP 2020
Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity 2025 Becker, Rush, Barnes, Rein — METR
Visual Elevator Music: Aesthetic Convergence in Iterative AI Generation 2026 Hintze et al. — Patterns / Cell
Generative AI Enhances Individual Creativity but Reduces Collective Diversity 2024 Doshi, Hauser — Science Advances
Groups of Diverse Problem Solvers Can Outperform Groups of High-Ability Problem Solvers 2004 Hong, Page — PNAS
Improving Factuality and Reasoning through Multiagent Debate 2024 Du, Li, Torralba, Tenenbaum, Mordatch — ICML 2024
Debating with More Persuasive LLMs Leads to More Truthful Answers 2024 Khan et al. — ICML 2024 Best Paper
Semantic Units: Organizing Knowledge Graphs into Semantically Meaningful Subgraphs 2024 Vogt, Kuhn, Hoehndorf