Exodia Distilling SotA open-endedness through open-endedness.
Last updated: 2026-10-10 · upstream jennyzzt/awesome-open-ended@966c9ec · run #29

Trends over time

How open-endedness research shifts year over year, derived from 103 curated entries (from 2017 on): which concepts are rising, where citations concentrate, which models, datasets and tasks dominate, and how venues and categories change. Charts are interactive — hover for values, and click legend entries to toggle series.

Most-cited papers

The most-cited entries in the list (Semantic Scholar citation counts).

  1. 1 Voyager: An Open-Ended Embodied Agent with Large Language Models · Preprint (arXiv) 2023 1,830
  2. 2 The AI Scientist: Towards fully automated open-ended scientific discovery · Preprint (arXiv) 2024 865
  3. 3 Eureka: Human-Level Reward Design via Coding Large Language Models · ICLR 2023 630
  4. 4 Genie: Generative Interactive Environments · Preprint (arXiv) 2024 629
  5. 5 MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge · NeurIPS 2022 579
  6. 6 Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution · Preprint (arXiv) 2023 490
  7. 7 The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search · Preprint (arXiv) 2025 348
  8. 8 Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design · NeurIPS 2020 315
  9. 9 Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions · GECCO 2019 299
  10. 10 Automated design of agentic systems · ICLR 2025 295
  11. 11 Debating with More Persuasive LLMs Leads to More Truthful Answers · Preprint (arXiv) 2024 269
  12. 12 Evolutionary Optimization of Model Merging Recipes · Nat Mach Intell (2025) 2024 265
  13. 13 Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents · ICLR 2026 237
  14. 14 Open-Ended Learning Leads to Generally Capable Agents · Preprint (arXiv) 2021 229
  15. 15 Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts · NeurIPS 2024 221

What the field says comes next

The forward-looking sections of every paper — “future work”, “conclusion”, “limitations”, “open questions” — mined for the curated concepts authors flag as open. Ranked by how many papers propose each direction; ▲ recent marks concepts where most of those calls land in the last few years (rising momentum).

Charts over time

Share of each year's entries engaging each curated open-endedness concept (matched across full text) — watch the shift toward LLM / agent work.
Share of each year's papers whose “future work / conclusion / limitations” sections explicitly propose each curated concept (detected only in those forward-looking sections). Concepts that papers keep naming as open — increasingly so — are the emerging hot topics.
Share of each publication-year's total citations captured by each concept — weights every entry by how often it's cited, so it tracks where impact concentrates, not merely how many papers appear.
Share of each year's entries mentioning a model / algorithm family (keyword-based, approximate) — the LLM families climb fast.
Share of each year's entries mentioning an AI lab / model provider (keyword-based, approximate).
Share of each year's entries mentioning a dataset / benchmark / environment (keyword-based, approximate).
Share of each year's entries mentioning a task type (keyword-based, approximate).
Primary arXiv categories of the papers each year — which subfields drive open-endedness (from arXiv metadata, not keywords).
Share of each year's papers that link to code — a reproducibility signal. Blog posts and videos are excluded since they can't ship a repository.
Median (bars) and mean (line) citations per paper by publication year. Recent years are necessarily under-counted — citations accrue with age.
How the leading themes wax and wane year over year.
Linear trend of each consensus keyphrase's yearly mentions — green is rising, red is fading.
How the leading venues' yearly counts stack up (the arXiv-preprint share shows how much work stays unpublished).
Entries by curated category each year.