Elamur Research⌕
☰
home / papers / 2026 / Workflow Closure Is Not Scientific Closure in Auto-Research Systems

Workflow Closure Is Not Scientific Closure in Auto-Research Systems

Paper · 2026 · Shuai Wang, Xinyuan Tian, Pangpang Liu et al.

Summary

This position paper asks what it actually means when an automated research system "closes the loop." The authors separate two notions. Workflow closure is a system's ability to run ideation, experiments, writing and evaluation without human input, judging itself with its own evaluators. Scientific closure requires outputs to face plural objectives, validators independent of the producer, and community uptake. They argue the first is a genuine engineering result but gives no scientific standing.

Drawing on a survey of over 100 papers and repositories and a structured audit of 21 documented systems, they identify three linked failures:

  • Objective collapse: a single proxy metric drives the loop, a Goodhart-type problem.
  • Validation collapse: checking stays within the same model family or benchmark regime.
  • Acceptance collapse: loops end in scores or paper-like artifacts rather than open critique and reuse.

Because these stem from design choices rather than limits of autonomy, the authors suggest remedies and advocate autonomous execution under external, non-autonomous epistemic control.

Key points

  • The evidence base is a survey of more than 100 recent works and repositories, plus an audit of 21 systems coded on three dimensions (L1 objective, L2 validation, L3 acceptance).
  • Each dimension is labeled using a three-way scheme:
    • Strong: the loop is governed only by internal signals.
    • Weak: external involvement is simulated from inside the system.
    • Mitigated: a truly external check binds the loop.
  • No audited system earned a Mitigated label on any dimension. For example, Karpathy autoresearch, ADAS, AIDE and AI-Scientist-v2 are Strong on all three.
  • SakanaAI/AI-Scientist, whose papers passed workshop peer review per the Nature publication, is coded S/W/W. AI-Researcher is the only system coded W/W/W.
  • CycleResearcher uses averaged reviewer scores as a SimPO reward, produced by a same-family reward model trained on ICLR-2024 review data. This is an illustration of validation collapse.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Yale UniversityNew Haven · United States112 works · 14,009 citations

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 19,503 worksArtificial Intelligence · 18,805 worksSocial Sciences · 2,009 worksSafety Research · 665 worksDecision Sciences · 306 worksInformation Systems and Management · 96 works

Cite

Cite as Shuai Wang, Xinyuan Tian, Pangpang Liu and Yize Zhao. 2026. Workflow Closure Is Not Scientific Closure in Auto-Research Systems. arXiv:2605.26200.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2605.26200 · arXiv 2605.26200

@misc{wang2026workflow,
  title = {{Workflow Closure Is Not Scientific Closure in Auto-Research Systems}},
  author = {Shuai Wang, Xinyuan Tian, Pangpang Liu and Yize Zhao},
  year = {2026},
  doi = {10.48550/arxiv.2605.26200},
  eprint = {2605.26200},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2605.26200}
}

References

122 references, 16 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. du-nlp-lab/MLR-Copilot, Aug. 2025. find
  2. aiming-lab/AutoResearchClaw, Apr. 2026. find
  3. davebcn87/pi-autoresearch, Apr. 2026. find
  4. drivelineresearch/autoresearch-claude-code, Apr. 2026. find
  5. eimenhmdt/autoresearcher, Apr. 2026. find
  6. Entrpi/autoresearch-everywhere, Apr. 2026. find
  7. greyhaven-ai/autocontext, Apr. 2026. find
  8. HKUDS/AI-Researcher, Apr. 2026. find
  9. HKUDS/ClawTeam, Apr. 2026. find
  10. hyperspaceai/agi, Apr. 2026. find
  11. james-s-tayler/lazy-developer, Apr. 2026. find
  12. JinheonBaek/ResearchAgent, Mar. 2026. find
  13. jmilinovich/goal-md, Apr. 2026. find
  14. leo-lilinxiao/codex-autoresearch, Apr. 2026. find
  15. LitLLM/LitLLM, Apr. 2026. find
  16. MASWorks/ML-Agent, Mar. 2026. find
  17. MaximeRobeyns/self_improving_coding_agent, Apr. 2026. find
  18. metauto-ai/HGM, Apr. 2026. find
  19. MrTsepa/autoevolve, Mar. 2026. find
  20. mutable-state-inc/autoresearch-at-home, Apr. 2026. find
  21. openags/OpenAGS, Apr. 2026. find
  22. OpenRaiser/NanoResearch, Apr. 2026. find
  23. Orchestra-Research/AI-Research-SKILLs, Apr. 2026. find
  24. peterskoett/self-improving-agent, Apr. 2026. find
  25. PouriaRouzrokh/LatteReview, Apr. 2026. find
  26. SakanaAI/AI-Scientist, Apr. 2026. find
  27. SakanaAI/AI-Scientist-v2, Apr. 2026. find
  28. SamuelSchmidgall/AgentLaboratory, Apr. 2026. find
  29. ShengranHu/ADAS, Apr. 2026. find
  30. Sibyl-Research-Team/AutoResearch-SibylSystem, Apr. 2026. find
  31. supratikpm/gemini-autoresearch, Apr. 2026. find
  32. uditgoenka/autoresearch, Apr. 2026. find
  33. wanshuiyin/Auto-claude-code-research-in-sleep, Apr. 2026. find
  34. WecoAI/aideml, Apr. 2026. find
  35. Why AI cannot do good science without humans. Nature, 653(8115):650–650, May 2026. find
  36. zkarimi22/autoresearch-anything, Apr. 2026. find
  37. S. Alexander, B. Bradley, L. Gouskos, and C. Niu. Autonomous Discovery of Particle Physics Theories from Experimental Data, Mar. 2026. find
  38. S. Alzubi, N. Provenzano, J. Bingham, W. Chen, and T. Vu. Evoskill: Automated skill discovery for multi-agent systems. arXiv preprint arXiv:2603.02766, 2026. — [arXiv:2603.02766](https://arxiv.org/abs/2603.02766) find
  39. E. Aygün, A. Belyaeva, G. Comanici, M. Coram, H. Cui, J. Garrison, R. Johnston, A. Kast, C. Y. McLean, P. Norgaard, Z. Shamsi, D. Smalling, J. Thompson, S. Venugopalan, B. P. Williams, C. He, S. Martinson, M. Plomecka, L. Wei, Y. Zhou, Q.-Z. Zhu, M. Abraham, E. Brand, A. Bulanova, J. A. Cardille, C.… — An AI system to help scientists write expert-level empirical software
  40. D. A. Boiko, R. MacKnight, B. Kline, and G. Gomes. Autonomous chemical research with large language models. Nature, 624:570–578, 2023.
  41. Y. Chen, C. Liu, Z. Chen, T. Liu, B. Han, and K. Zhang. CausalEvolve: Towards Open-Ended Discovery with Causal Scratchpad, Mar. 2026. find
  42. M. Cobelli and S. Sanvito. Agentic design of compositional descriptors via autoresearch for materials science applications. arXiv preprint arXiv:2605.14671, 2026. — [arXiv:2605.14671](https://arxiv.org/abs/2605.14671) find
  43. L. Fan, P. Dai, Z. Deng, H. Wang, X. Gong, Y. Zheng, and Y. Ou. Evolving Medical Imaging Agents via Experience-driven Self-skill Discovery, Mar. 2026. arXiv:2603.05860 [cs]. — [arXiv:2603.05860](https://arxiv.org/abs/2603.05860) find
  44. F. Ferreira, L. Wobbe, A. Krishnakumar, F. Hutter, and A. Zela. Can LLMs Beat Classical Hyperparameter Optimization Algorithms? A Study on autoresearch, Mar. 2026. find
  45. A. E. Ghareeb, B. Chang, L. Mitchener, A. Yiu, C. J. Szostkiewicz, D. Shved, G. J. Gyimesi, J. M. Laurent, S. M. Wright, M. T. Razzak, A. D. White, S. C. Finnemann, M. M. Hinks, and S. G. Rodriques. A multi-agent system for automating scientific discovery. Nature, May 2026. find
  46. J. Gottweis, W.-H. Weng, A. Daryin, T. Tu, P. Sirkovic, A. Myaskovsky, G. Glowaty, F. Weissenberger, A. Orlandi, D. Popovici, A. Palepu, K. Rong, R. Tanno, K. Saab, F. Zhang, J. Blum, A. Carroll, K. Kulkarni, N. Tomašev, D. Zverinski, I. Rendulic, E. Vedadi, F. Hasler, L. Rimanic, M. Boia, I. Budise… — Accelerating scientific discovery with Co-Scientist
  47. T. Han, Y. Zhang, W. Song, C. Fang, Z. Chen, Y. Sun, and L. Hu. Swe-skills-bench: Do agent skills actually help in real-world software engineering? arXiv preprint arXiv:2603.15401, 2026. — [arXiv:2603.15401](https://arxiv.org/abs/2603.15401) find
  48. C. He, X. Zhou, D. Wang, H. Xu, W. Liu, and C. Miao. The AutoResearch Moment: From Experimenter to Research Director, Mar. 2026. find
  49. M. He, F. Jiang, J. Jiao, M. Li, K. Li, Y. Liao, B. Liu, T. Liu, F. Qi, Z. Shang, W. Song, Y. Sun, X. Wang, H. Wang, D. Xiong, C. Yuan, B. Zhang, Z. Zhang, and X. Zhu. Dr.Sai: An agentic AI for real-world physics analysis at BESIII, Apr. 2026. arXiv:2604.22541 [hep-ex] version: 1. — [arXiv:2604.22541](https://arxiv.org/abs/2604.22541) find
  50. Y. Huang, Y. Chen, H. Zhang, K. Li, H. Zhou, M. Fang, L. Yang, X. Li, L. Shang, S. Xu, J. Hao, K. Shao, and J. Wang. Deep Research Agents: A Systematic Examination And Roadmap, Sept. 2025. arXiv:2506.18096 [cs]. — [arXiv:2506.18096](https://arxiv.org/abs/2506.18096) find
  51. V. Ilin. Semi-Autonomous Formalization of the Vlasov-Maxwell-Landau Equilibrium, Mar. 2026. find
  52. B. Jia, S. Kamboj, S. Katipomu, S. H. Han, N. Sengupta, and A. Jackson. Nomad: Autonomous Exploration and Discovery, Mar. 2026. find
  53. G. Jiang, Z. Su, X. Qu, and Y. R. Fung. Xskill: Continual learning from experience and skills in multimodal agents. arXiv preprint arXiv:2603.12056, 2026. — [arXiv:2603.12056](https://arxiv.org/abs/2603.12056) find
  54. A. Karpathy. karpathy/autoresearch, Apr. 2026. find
  55. J. Karwowski, O. Hayman, X. Bai, K. Kiendlhofer, C. Griffin, and J. M. V. Skalse. Goodhart’s law in reinforcement learning. In The Twelfth International Conference on Learning Representations, 2024. find
  56. N. Khandelwal and S. S. Gupta. Agent-Driven Autonomous Reinforcement Learning Research: Iterative Policy Improvement for Quadruped Locomotion, Mar. 2026. find
  57. L. Kong, X. Sun, W. Chow, L. Li, K. Q. Lin, X. B. Zhang, S. Wang, R. Li, Q. Wu, W. Gao, Y. Wang, S. Xie, J. Liu, L. Qu, S. Li, L. X. Ng, B. R. Cottereau, Z. Liu, T.-S. Chua, and W. T. Ooi. AI for Auto-Research: Roadmap & user guide. May 2026.
  58. S. Kuroki, T. Nakamura, T. Akiba, and Y. Tang. Agent skill acquisition for large language models via cycleqd. arXiv preprint arXiv:2410.14735, 2024. — [arXiv:2410.14735](https://arxiv.org/abs/2410.14735) find
  59. C.-Y. Lee, H. Liang, R. Kim, A. McDannald, C. A. R. Ocampo, A. G. Kusne, and I. Takeuchi. Real-time multi-instrument autonomous discovery of novel phase-change memory materials. May 2026. find
  60. F. Li, P. Tagkopoulos, and I. Tagkopoulos. Skillflow: Scalable and efficient agent skill retrieval system. arXiv e-prints, pages arXiv–2504, 2025. find
  61. H. Li, C. Mu, J. Chen, S. Ren, Z. Cui, Y. Zhang, L. Bai, and S. Hu. Organizing, orchestrating, and benchmarking agent skills at ecosystem scale. arXiv preprint arXiv:2603.02176, 2026. — [arXiv:2603.02176](https://arxiv.org/abs/2603.02176) find
  62. X. Li. Auto Researching, not hyperparameter tuning: Convergence Analysis of 10,000 Experiments, Mar. 2026. find
  63. X. Li. When single-agent with skills replace multi-agent systems and when they fail. arXiv preprint arXiv:2601.04748, 2026. — [arXiv:2601.04748](https://arxiv.org/abs/2601.04748) find
  64. X. Li, W. Chen, Y. Liu, S. Zheng, X. Chen, Y. He, Y. Li, B. You, H. Shen, J. Sun, et al. Skillsbench: Benchmarking how well agent skills work across diverse tasks. arXiv preprint arXiv:2602.12670, 2026. — [arXiv:2602.12670](https://arxiv.org/abs/2602.12670) find
  65. Y. Li, C. Shao, X. Liu, R. Zhao, P. Liu, H. Su, Z. Chen, Q. Yang, A. Xu, Y. Fang, et al. Autosota: An end-to-end automated research system for state-of-the-art ai model discovery. arXiv preprint arXiv:2604.05550, 2026.
  66. Y. Liang, R. Zhong, H. Xu, C. Jiang, Y. Zhong, R. Fang, J.-C. Gu, S. Deng, Y. Yao, M. Wang, et al. Skillnet: Create, evaluate, and connect ai skills. arXiv preprint arXiv:2603.04448, 2026. — [arXiv:2603.04448](https://arxiv.org/abs/2603.04448) find
  67. C. Liu, T. Li, M. Huang, X. Wei, P. Liu, Y. Shen, Y. Mao, and T. Cui. Protrlsearch: A multi-round multimodal protein search agent with large language models trained via reinforcement learning. arXiv preprint arXiv:2603.01464, 2026. — [arXiv:2603.01464](https://arxiv.org/abs/2603.01464) find
  68. F. Liu, J. Han, T. Lyu, W. Zhang, Z.-R. Yang, L. Dai, C. Liu, and H. Liu. Foundation models for scientific discovery: From paradigm enhancement to paradigm transition. Advances in Neural Information Processing Systems, 2025. find
  69. F. Liu, J. Xu, X. Cui, X. Wang, Z. Guo, J. Wang, S. M. Mousavi, X. Gu, H. Chen, B. Fei, L. Fang, F. Ling, Z. Li, and L. Bai. TRACE: A Multi-Agent System for Autonomous Physical Reasoning for Seismology, Mar. 2026. find
  70. J. Liu, Z. Ling, S. Qiu, Y. Liu, S. Han, P. Xia, H. Tu, Z. Zheng, C. Xie, C. Fleming, et al. Omni-simplemem: Autoresearch-guided discovery of lifelong multimodal agent memory. arXiv e-prints, pages arXiv–2604, 2026. find
  71. J. Liu, S. Qiu, M. Li, B. Li, H. Ji, S. Han, X. Ye, P. Xia, Z. Dong, C. Zhang, L. Zhang, G. Chen, H. Tu, X. Yang, L. Feng, X. Zhao, H. Chen, J. Zhou, X. Wang, W. Zhang, H. Zhu, Y. Li, J. Mei, H. Fei, J. Zhang, L. Li, L. Zhang, Y. Zhou, S. Wang, C. Xiong, J. Zou, Z. Zheng, C. Xie, M. Ding, and H. Yao… find
  72. J. Liu, J. Shen, S. Song, T. Li, X. Liu, R. Li, Z. Huang, J. Lin, J. Ning, C. Ji, S. Luo, W. Li, C. Ma, M. Hu, J. Xiong, J. Ye, B. Fu, N. Xu, Y. Chen, L. Jin, H. Chen, and J. He. MedProbeBench: Systematic Benchmarking at Deep Evidence Integration for Expert-level Medical Guideline, Apr. 2026. arXiv:… — [arXiv:2604.18418](https://arxiv.org/abs/2604.18418) find
  73. J. Liu, X. Ye, P. Xia, Z. Zheng, C. Xie, M. Ding, and H. Yao. Evolvemem: Self-evolving memory architecture via autoresearch for llm agents. arXiv preprint arXiv:2605.13941, 2026. — [arXiv:2605.13941](https://arxiv.org/abs/2605.13941) find
  74. C. Lu, C. Lu, R. T. Lange, Y. Yamada, S. Hu, J. Foerster, D. Ha, and J. Clune. Towards end-to-end automation of AI research. Nature, 651(8107):914–919, Mar. 2026. find
  75. D. Manheim and S. Garrabrant. Categorizing variants of goodhart’s law. arXiv preprint arXiv:1803.04585, 2018. — [arXiv:1803.04585](https://arxiv.org/abs/1803.04585) find
  76. L. Messeri and M. J. Crockett. Artificial intelligence and illusions of understanding in scientific research. Nature, 627:49–58, 2024. find
  77. J. Ni, Y. Liu, X. Liu, Y. Sun, M. Zhou, P. Cheng, D. Wang, X. Jiang, and G. Jiang. Trace2skill: Distill trajectory-local lessons into transferable agent skills. arXiv preprint arXiv:2603.25158, 2026.
  78. A. Novikov, M. Balog, M. P. Kumar, et al. AlphaEvolve: A coding agent for scientific and algorithmic discovery, 2025.
  79. OpenAI. Introducing deep research, 2025. find
  80. A. Pan, E. Jones, M. Jagadeesan, and J. Steinhardt. Feedback loops with language models drive in-context reward hacking. In Proceedings of the 41st International Conference on Machine Learning, volume 235 of Proceedings of Machine Learning Research, pages 39154–39200. PMLR, 2024.
  81. A. Panfilov, P. Romov, I. Shilov, Y.-A. d. Montjoye, J. Geiping, and M. Andriushchenko. Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs, Mar. 2026. find
  82. A. Pepe, C.-Y. Lin, D. Magka, B. Acun, Y. N. Wu, A. Protopopov, C.-J. Wu, and Y. Bachrach. Agentic discovery of neural architectures: AIRA-Compose and AIRA-Design. May 2026. find
  83. Y. Qian, X. Hu, J. Yu, S. Xin, X. Chen, J. Zhang, P.-T. Jiang, J. Liu, and H. B. Li. Medmaslab: A unified orchestration framework for benchmarking multimodal medical multi-agent systems. arXiv preprint arXiv:2603.09909, 2026. — [arXiv:2603.09909](https://arxiv.org/abs/2603.09909) find
  84. J. Qiao, W. Meng, Y. Cheng, Z. Lin, Z. Zhang, X. Tan, J. Gong, K. Shao, and Y. Xie. Memory intelligence agent. arXiv preprint arXiv:2604.04503, 2026. — [arXiv:2604.04503](https://arxiv.org/abs/2604.04503) find
  85. Y. Qin, Y. Yan, J. Pang, and X. Zhang. BloClaw: An Omniscient, Multi-Modal Agentic Workspace for Next-Generation Scientific Discovery, Apr. 2026. find
  86. A. Qu, H. Zheng, Z. Zhou, Y. Yan, Y. Tang, S. Y. Ong, F. Hong, K. Zhou, C. Jiang, M. Kong, et al. Coral: Towards autonomous multi-agent evolution for open-ended discovery. arXiv preprint arXiv:2604.01658, 2026.
  87. Y. Qu, K. Huang, M. Yin, K. Zhan, D. Liu, D. Yin, H. C. Cousins, W. A. Johnson, X. Wang, M. Shah, et al. Crispr-gpt for agentic automation of gene-editing experiments. Nature Biomedical Engineering, 10(2):245–258, 2026.
  88. Y. Qu and M. Lu. Bilevel Autoresearch: Meta-Autoresearching Itself, Mar. 2026. find
  89. M. Ríos-García, N. Alampara, C. Gupta, I. Mandal, S. Mannan, A. A. Aghajani, N. Krishnan, and K. M. Jablonka. Ai scientists produce results without reasoning scientifically. arXiv preprint arXiv:2604.18805, 2026. find
  90. B. Romera-Paredes, M. Barekatain, A. Novikov, M. Balog, M. P. Kumar, E. Dupont, F. J. R. Ruiz, J. S. Ellenberg, P. Wang, O. Fawzi, P. Kohli, and A. Fawzi. Mathematical discoveries from program search with large language models. Nature, 625:468–475, 2024.
  91. S. Schmidgall and M. Moor. AgentRxiv: Towards Collaborative Autonomous Research. arXiv preprint arXiv:2503.18102, Mar. 2025. Companion paper to Agent Laboratory repository.
  92. W. Shen, Y. Hu, C. Liu, J. Wu, J. Zhu, C. Shen, M. Xu, Y. Jin, B. Wiestler, D. Rueckert, and J. Pan. MedOpenClaw: Auditable Medical Imaging Agents Reasoning over Uncurated Full Studies, Mar. 2026. find
  93. Y. Shen, Z. Yi, Z. Zhao, L. Sun, D. Li, C.-T. Lin, and Y. Shi. An Empirical Study of Multi-Agent Collaboration for Automated Research, Mar. 2026. find
  94. L. Shi, Z. J. Zheng, X. Juan, Y. Wang, M. Yin, M. Sengupta, K. Wolinski, Y. Jia, J. Shi, D. Saucedo, N. Saggi, H. Guan, K. Watanabe, T. Taniguchi, A. Yazdani, M. Wang, and S. Wu. Qumus: Realization of an embodied AI quantum material experimentalist. May 2026. find
  95. N. Somasekharan, R. Pathak, M. Dhanakoti, T. Zhang, L. Yue, A. Zhu, and S. Pan. Ai cfd scientist: Toward open-ended computational fluid dynamics discovery with physics-aware ai agents. arXiv preprint arXiv:2605.06607, 2026. — [arXiv:2605.06607](https://arxiv.org/abs/2605.06607) find
  96. W. Song, J. Yue, and Z. Pang. Abstral: Automatic design of multi-agent systems through iterative refinement and topology optimization. arXiv preprint arXiv:2603.22791, 2026. — [arXiv:2603.22791](https://arxiv.org/abs/2603.22791) find
  97. J. Su, S. Tu, B. Sun, and X. Liang. STRIDE: A self-reflective agent framework for reliable automatic equation discovery. May 2026. find
  98. Z. Sun, Z. Liu, Y. Zang, Y. Cao, X. Dong, T. Wu, D. Lin, and J. Wang. Seagent: Self-evolving computer use agent with autonomous learning from experience. arXiv preprint arXiv:2508.04700, 2025. — [arXiv:2508.04700](https://arxiv.org/abs/2508.04700) find
  99. L. L. Team, S. M. Schmon, D. Pretorius, S. Mathis, R. Bartke-Croughan, A. Puvanendran, J. Vuckovic, H. Kenlay, M. Vlachynská, A. Bridgland, I. Grishin, S. Over, D. Li, B. Li, J. Crabbé, A. Hilmkil, A. W. R. Nelson, D. Yuan, A. Obika, and S. A. A. Kohl. Latent-Y: A Lab-Validated Autonomous Agent for… find
  100. M. Team, S. Bai, L. Bing, L. Lei, R. Li, X. Li, X. Lin, E. Min, L. Su, B. Wang, L. Wang, L. Wang, S. Wang, X. Wang, Y. Zhang, Z. Zhang, G. Chen, L. Chen, Z. Cheng, Y. Deng, Z. Huang, D. Ng, J. Ni, Q. Ren, X. Tang, B. L. Wang, H. Wang, N. Wang, C. Wei, Q. Wu, J. Xia, Y. Xiao, H. Xu, X. Xu, C. Xue, Z.… find
  101. J. D. Toscano, Z. Chai, and G. E. Karniadakis. GRAFT-ATHENA: Self-improving agentic teams for autonomous discovery and evolutionary numerical algorithms. May 2026. find
  102. J. Wang, Z. Tao, H. Zeng, Z. Yang, H. Zamani, and H. Yu. Tarse: Test-time adaptation via retrieval of skills and experience for reasoning agents. arXiv preprint arXiv:2603.01241, 2026. — [arXiv:2603.01241](https://arxiv.org/abs/2603.01241) find
  103. L. Wang, Y. He, P. Chen, A. Yehudai, Y. Liu, R. Ying, M. Shmueli-Scheuer, and A. Cohan. Time to REFLECT: Can we trust LLM judges for evidence-based research agents? 2026. find
  104. L. Wang, Y. Li, J. Wu, H. Gao, X. Bo, X. Chen, and J.-R. Wen. Llm agents as social scientists: A human-ai collaborative platform for social science automation. arXiv preprint arXiv:2604.01520, 2026. — [arXiv:2604.01520](https://arxiv.org/abs/2604.01520) find
  105. S. Wang, J. Jin, R. Fu, Z. Yan, X. Wang, M. Hu, E. Wang, X. Li, K. Zhang, L. Yao, W. Jiao, X. Cheng, Y. Lu, and Z. Ge. MuSEAgent: A Multimodal Reasoning Agent with Stateful Experiences, Mar. 2026. find
  106. Y. Wang, G. Sinenka, and X. Brace. Rhizome os-1: Rhizome’s semi-autonomous operating system for small molecule drug discovery. arXiv preprint arXiv:2604.07512, 2026. — [arXiv:2604.07512](https://arxiv.org/abs/2604.07512) find
  107. J. Wei, Y. Yang, X. Zhang, Y. Chen, X. Zhuang, Z. Gao, D. Zhou, G. Wang, Z. Gao, J. Cao, Z. Qiu, M. Hu, C. Ma, S. Tang, J. He, C. Song, X. He, Q. Zhang, C. You, S. Zheng, N. Ding, W. Ouyang, N. Dong, Y. Cheng, S. Sun, L. Bai, and B. Zhou. From AI for Science to Agentic Science: A Survey on Autonomou… — From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery
  108. Y. Weng, M. Zhu, G. Bao, H. Zhang, J. Wang, Y. Zhang, and L. Yang. Cycleresearcher: Improving automated research via automated review. In The Thirteenth International Conference on Learning Representations, 2025.
  109. H. Wu, B. Zheng, D. Song, Y. Jiang, J. Gao, L. Xing, L. Sun, and Y. Yuan. Towards a Medical AI Scientist, Mar. 2026. find
  110. P. Xia, J. Chen, H. Wang, J. Liu, K. Zeng, Y. Wang, S. Han, Y. Zhou, X. Zhao, H. Chen, et al. Skillrl: Evolving agents via recursive skill-augmented reinforcement learning. arXiv preprint arXiv:2602.08234, 2026. — [arXiv:2602.08234](https://arxiv.org/abs/2602.08234) find
  111. S. Xia, Y. Zhang, A. Chen, S. Wu, S. Yuan, and Y. Xiao. From AI Assistant to AI Scientist: Autonomous Discovery of LLM-RL Algorithms with LLM Agents, Mar. 2026. find
  112. Z. Xie, Y. Guo, and K. Xu. AwesomeLit: Towards Hypothesis Generation with Agent-Supported Literature Research, Mar. 2026. find
  113. L. Xu and T. Borrett. Beyond ai as assistants: Toward autonomous discovery in cosmology. arXiv preprint arXiv:2605.14791, 2026. find
  114. L. Xu, Y. Zhou, and S. Pokutta. Agentic mip research: Accelerated constraint handler generation. arXiv preprint arXiv:2605.09186, 2026. — [arXiv:2605.09186](https://arxiv.org/abs/2605.09186) find
  115. R. Xu and Y. Yan. Agent skills for large language models: Architecture, acquisition, security, and the path forward. arXiv preprint arXiv:2602.12430, 2026. — [arXiv:2602.12430](https://arxiv.org/abs/2602.12430) find
  116. W. Xu, T. Mi, Y. Liu, Y. Nan, Z. Zhou, L. Ye, L. Zhang, Y. Qiao, and P. Liu. ASI-Evolve: AI Accelerates AI, Mar. 2026. find
  117. Y. Yang, J. Li, Q. Pan, B. Zhan, Y. Cai, L. Du, J. Zhou, K. Chen, Q. Chen, X. Li, et al. Autoskill: Experience-driven lifelong learning via skill self-evolution. arXiv preprint arXiv:2603.01145, 2026. — [arXiv:2603.01145](https://arxiv.org/abs/2603.01145) find
  118. Z. Yang, X. Liu, and X. Xu. Sciintegrity-bench: A benchmark for evaluating academic integrity in ai scientist systems. arXiv preprint arXiv:2605.10246, 2026.
  119. Z. Zhang, N. Wang, S. Galhotra, and C. Cardie. How far are we from true auto-research? 2026.
  120. H. Zhou, S. Guo, A. Liu, Z. Yu, Z. Gong, B. Zhao, Z. Chen, M. Zhang, Y. Chen, J. Li, et al. Memento-skills: Let agents design agents. arXiv preprint arXiv:2603.18743, 2026. — [arXiv:2603.18743](https://arxiv.org/abs/2603.18743) find
  121. B. Zhu, Q. Jia, T. Lan, J. Ren, F. Gu, F. Jiang, L. Wang, Z. Xu, and W. Luo. Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Design, Mar. 2026. find
  122. Q. Zou, H. H. Lam, W. Zhao, T. Chen, Y. Tang, S. Yu, Y. Zhu, S. Anumasa, Z. Zhang, T. Zhang, C. Liu, Z. Jiang, A. Goyal, and D. Liu. FML-bench: A controlled study of AI research agent strategies from the perspective of search dynamics. May 2026. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/wang-2026-workflow-closure-scientific-closure/