Elamur Research⌕
☰
home / papers / 2026 / EvoSci: A Bio-Inspired Multi-Agent Framework for the Evolution of Scientific Discovery

EvoSci: A Bio-Inspired Multi-Agent Framework for the Evolution of Scientific Discovery

Paper · 2026 · Xiaoyu Xiong, Yuqi Ren and Deyi Xiong

Summary

LLM-based systems for generating research ideas usually run one fixed pass on a set topic. They also treat the model as a passive step in a rigid pipeline, which misses how real science unfolds over many rounds and through teamwork. EvoSci addresses this with a multi-agent framework that has four stages:

  • Problem-space construction: a mentor agent builds research problems over a light discipline–entity knowledge graph. The graph is derived from Wikipedia, and cross-domain links are added by embedding similarity.
  • Collaborative execution: a prime researcher leads a team of agents grounded in a dataset of real scientists' profiles.
  • Review: a reviewer agent scores ideas on novelty, feasibility, effectiveness, excitement and overall quality.
  • Evolution: a bio-inspired loop applies selection, crossover and mutation to the concept clusters across rounds.

On ten interdisciplinary topics, EvoSci beat strong baselines in LLM-simulated peer review and Elo-style ranking. This suggests that iterative, feedback-driven recombination of concepts yields more novel ideas. The cost is sometimes lower practical feasibility.

Key points

  • Peer-review scores (DeepSeek-v3 backbone): ICLR 4.90 and NeurIPS 3.95, versus 4.68 and 3.72 for the next-best baseline.
  • Ranking metrics: in the introduction's DeepSeek-v3 setting, EvoSci reaches Avg Wins 4.19 and a Top-10 Count of 47. The abstract instead cites Top-10 = 54, and the paper text provided does not explain the difference.
  • Agent roles: mentor, a team of researchers, and a reviewer. The mentor redistributes subtasks based on intermediate feedback.
  • Iteration analysis: each topic ran 10 iterations producing 50 ideas. Later rounds improved Novelty and/or Overall scores mainly on less-explored topics, with little gain on engineering-oriented ones.
  • Qualitative case study (Grokking): ideas shifted from general notions of learning toward narrower themes such as generalization that arrives late, abrupt phase-like transitions and the restructuring of internal representations, and several conceptual lineages continued in parallel.

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

🎓Tianjin UniversityTianjin · China52 works · 1,128 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksArts and Humanities · 17,450 worksLanguage and Linguistics · 17,296 works

Cite

Cite as Xiaoyu Xiong, Yuqi Ren and Deyi Xiong. 2026. EvoSci: A Bio-Inspired Multi-Agent Framework for the Evolution of Scientific Discovery. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.acl-long.447

@inproceedings{xiong2026evosci,
  title = {{EvoSci: A Bio-Inspired Multi-Agent Framework for the Evolution of Scientific Discovery}},
  author = {Xiaoyu Xiong, Yuqi Ren and Deyi Xiong},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.447},
  url = {https://doi.org/10.18653/v1/2026.acl-long.447}
}

References

44 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Jinheon Baek, Sujay Kumar Jauhar, Silviu Cucerzan, and Sung Ju Hwang. 2024. Researchagent: Iterative research idea generation over scientific literature with large language models. arXiv preprint arXiv:2404.07738.
  2. Markus J Buehler. 2024. Accelerating scientific discovery with generative knowledge extraction, graph-based representation, and multimodal intelligent graph reasoning. Machine Learning: Science and Technology, 5(3):035083. find
  3. Gary Charness, Brian Jabarian, and John A. List. 2025. The next generation of experimental research with LLMs. Nature Human Behaviour, 9(5):833–835. find
  4. Saaketh Desai, Sadhvikas Addamane, Jeffrey Y Tsao, Igal Brener, Laura P Swiler, Remi Dingreville, and Prasad P Iyer. 2025. Autoscilab: A self-driving laboratory for interpretable scientific discovery. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 146–154. find
  5. Zane Durante, Qiuyuan Huang, Naoki Wake, Ran Gong, Jae Sung Park, Bidipta Sarkar, Rohan Taori, Yusuke Noda, Demetri Terzopoulos, Yejin Choi, and 1 others. 2024. Agent ai: Surveying the horizons of multimodal interaction. arXiv preprint arXiv:2401.03568. — [arXiv:2401.03568](https://arxiv.org/abs/2401.03568) find
  6. Kevin C. Elliott. 2012. Epistemic and methodological iteration in scientific research. Studies in History and Philosophy of Science Part A, 43(2):376–382. find
  7. Mohamed Amine Ferrag, Norbert Tihanyi, and Merouane Debbah. 2025. Reasoning beyond limits: Advances and open problems for llms. Preprint, arXiv:2503.22732. — [arXiv:2503.22732](https://arxiv.org/abs/2503.22732) find
  8. Alireza Ghafarollahi and Markus J Buehler. 2025. Sciagents: automating scientific discovery through bioinspired multi-agent intelligent graph reasoning. Advanced Materials, 37(22):2413523. find
  9. Longzhen Han, Awes Mubarak, Almas Baimagambetov, Nikolaos Polatidis, and Thar Baker. 2025. A survey of generative categories and techniques in multimodal large language models. Preprint, arXiv:2506.10016. — [arXiv:2506.10016](https://arxiv.org/abs/2506.10016) find
  10. Xinyi He, Jiaru Zou, Yun Lin, Mengyu Zhou, Shi Han, Zejian Yuan, and Dongmei Zhang. 2024. Co-CoST: Automatic complex code generation with online searching and correctness testing. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 19433–19451, Miami, Flo… find
  11. Dimitar Hristovski, Borut Peterlin, Joyce A. Mitchell, and Susanne M. Humphrey. 2005. Using literature-based discovery to identify disease candidate genes. International Journal of Medical Informatics, 74(2):289–298. find
  12. Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, and 1 others. 2025. A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions. ACM Transactions on Information Systems,…
  13. Peter Jansen, Oyvind Tafjord, Marissa Radensky, Pao Siangliulue, Tom Hope, Bhavana Dalvi Mishra, Bodhisattwa Prasad Majumder, Daniel S Weld, and Peter Clark. 2025. Codescientist: End-to-end semi-automated scientific discovery with code-based experimentation. arXiv preprint arXiv:2503.22708. find
  14. Zixuan Ke, Fangkai Jiao, Yifei Ming, Xuan-Phi Nguyen, Austin Xu, Do Xuan Long, Minzhi Li, Chengwei Qin, Peifeng Wang, Silvio Savarese, and 1 others. 2025. A survey of frontiers in llm reasoning: Inference scaling, learning to reason, and agentic systems. arXiv preprint arXiv:2504.09037. find
  15. Ross D. King, Jem Rowland, Stephen G. Oliver, Michael Young, Wayne Aubrey, Emma Byrne, Maria Liakata, Magdalena Markham, Pinar Pir, Larisa N. Soldatova, Andrew Sparkes, Kenneth E. Whelan, and Amanda Clare. 2009. The automation of science. Science, 324(5923):85–89. find
  16. Adithya Kulkarni, Fatimah Alotaibi, Xinyue Zeng, Longfeng Wu, Tong Zeng, Barry Menglong Yao, Minqian Liu, Shuaicheng Zhang, Lifu Huang, and Dawei Zhou. 2025. Scientific hypothesis generation and validation: Methods, datasets, and future directions. Preprint, arXiv:2505.04651. find
  17. Jia Li, Yongmin Li, Ge Li, Zhi Jin, Yiyang Hao, and Xing Hu. 2023. Skcoder: A sketch-based approach for automatic code generation. In 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE), pages 2124–2135. IEEE. find
  18. Zhigen Li, Jianxiang Peng, Yanmeng Wang, Yong Cao, Tianhao Shen, Minghui Zhang, Linxi Su, Shang Wu, Yihang Wu, YuQian Wang, Ye Wang, Wei Hu, Jianfeng Li, Shaojun Wang, Jing Xiao, and Deyi Xiong. 2025. ChatSOP: An SOP-guided MCTS planning framework for controllable LLM dialogue agents. In Proceedings… find
  19. Yan Liu, Minghui Zhang, Bojian Xiong, Yifan Xiao, Yinong Sun, Yating Mei, Longyu Zeng, Jingchao Yang, Yang Wang, and Deyi Xiong. 2025. HighMATH: Evaluating math reasoning of large language models in breadth and depth. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 10… find
  20. Chris Lu, Cong Lu, Robert Tjarko Lange, Jakob Foerster, Jeff Clune, and David Ha. 2024. The ai scientist: Towards fully automated open-ended scientific discovery. arXiv preprint arXiv:2408.06292.
  21. Staša Milojević. 2014. Principles of scientific research team formation and evolution. Proceedings of the National Academy of Sciences, 111(11):3984–3989. find
  22. Juran Noh, Hieu A Doan, Heather Job, Lily A Robertson, Lu Zhang, Rajeev S Assary, Karl Mueller, Vijayakumar Murugesan, and Yangang Liang. 2024. An integrated high-throughput robotic platform and active learning approach for accelerated discovery of optimal electrolyte formulations. Nature Communicat… find
  23. Shirui Pan, Linhao Luo, Yufei Wang, Chen Chen, Jiapu Wang, and Xindong Wu. 2024. Unifying large language models and knowledge graphs: A roadmap. IEEE Transactions on Knowledge and Data Engineering, 36(7):3580–3599.
  24. Xiaoxue Ren, Xinyuan Ye, Dehai Zhao, Zhenchang Xing, and Xiaohu Yang. 2023. From misuse to mastery: Enhancing code generation with knowledge-driven ai chaining. In 2023 38th IEEE/ACM International Conference on Automated Software Engineering (ASE), pages 976–987. IEEE. find
  25. Neil R Smalheiser and Don R Swanson. 1998. Using arrowsmith: a computer-assisted approach to formulating and assessing scientific hypotheses. Computer Methods and Programs in Biomedicine, 57(3):149– 153. find
  26. Haoyang Su, Renqi Chen, Shixiang Tang, Zhenfei Yin, Xinzhe Zheng, Jinzhe Li, Biqing Qi, Qi Wu, Hui Li, Wanli Ouyang, Philip Torr, Bowen Zhou, and Nanqing Dong. 2025. Many heads are better than one: Improved scientific idea generation by a LLM-based multi-agent system. In Proceedings of the 63rd Annu…
  27. Yuan Sui, Mengyu Zhou, Mingjie Zhou, Shi Han, and Dongmei Zhang. 2024. Table meets llm: Can large language models understand structured table data? a benchmark and empirical study. In Proceedings of the 17th ACM International Conference on Web Search and Data Mining, pages 645–654.
  28. Yunsheng Tian, Mina Konaković Luković, Timothy Erps, Michael Foshey, and Wojciech Matusik. 2021. Autooed: Automated optimal experiment design platform. Preprint, arXiv:2104.05959. — [arXiv:2104.05959](https://arxiv.org/abs/2104.05959) find
  29. Gary Tom, Stefan P Schmid, Sterling G Baird, Yang Cao, Kourosh Darvish, Han Hao, Stanley Lo, Sergio Pablo-García, Ella M Rajaonson, Marta Skreta, and 1 others. 2024. Self-driving laboratories for chemistry and materials science. Chemical Reviews, 124(16):9633– 9732. find
  30. Trieu H Trinh, Yuhuai Wu, Quoc V Le, He He, and Thang Luong. 2024. Solving olympiad geometry without human demonstrations. Nature, 625(7995):476–482.
  31. Qingyun Wang, Doug Downey, Heng Ji, and Tom Hope. 2024a. Scimon: Scientific inspiration machines optimized for novelty. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), page 279–299. Association for Computational Linguistics.
  32. Wenxiao Wang, Lihui Gu, Liye Zhang, Yunxiang Luo, Yi Dai, Chen Shen, Liang Xie, Binbin Lin, Xiaofei He, and Jieping Ye. 2024b. Scipip: An llm-based scientific paper idea proposer. arXiv preprint arXiv:2410.23166. — [arXiv:2410.23166](https://arxiv.org/abs/2410.23166) find
  33. Yixuan Weng, Minjun Zhu, Guangsheng Bao, Hongbo Zhang, Jindong Wang, Yue Zhang, and Linyi Yang. 2024. Cycleresearcher: Improving automated research via automated review. arXiv preprint arXiv:2411.00816.
  34. Xiaoyu Xiong, Hao Wang, Keming Wu, Zhenfei Yang, Hanjie Zhao, Hongxiang Wang, Hao Liu, and Deyi Xiong. 2026. Collaborative and autonomous ai for science and innovation: Practices, challenges, and future directions. TechRxiv, 2026(0220). find
  35. Fengli Xu, Qianyue Hao, Zefang Zong, Jingwei Wang, Yunke Zhang, Jingyi Wang, Xiaochong Lan, Jiahui Gong, Tianjian Ouyang, Fanjin Meng, and 1 others. 2025. Towards large reasoning models: A survey of reinforced reasoning with large language models. arXiv preprint arXiv:2501.09686.
  36. Yutaro Yamada, Robert Tjarko Lange, Cong Lu, Shengran Hu, Chris Lu, Jakob Foerster, Jeff Clune, and David Ha. 2025. The ai scientist-v2: Workshop-level automated scientific discovery via agentic tree search. arXiv preprint arXiv:2504.08066.
  37. Lei Yang, Renren Jin, Ling Shi, Jianxiang Peng, Yue Chen, and Deyi Xiong. 2025. Probench: Benchmarking large language models in competitive programming. ArXiv, abs/2502.20868. — [arXiv:2502.20868](https://arxiv.org/abs/2502.20868) find
  38. Zonglin Yang, Xinya Du, Junxian Li, Jie Zheng, Soujanya Poria, and Erik Cambria. 2024. Large language models for automated open-domain scientific hypotheses discovery. In Findings of the Association for Computational Linguistics ACL 2024, pages 13545–13565.
  39. Shaowei Zhang and Deyi Xiong. 2025. Debate4MATH: Multi-agent debate for fine-grained reasoning in math. In Findings of the Association for Computational Linguistics: ACL 2025, pages 16810–16824, Vienna, Austria. Association for Computational Linguistics. find
  40. Zihan Zhang, Meng Fang, Ling Chen, Mohammad-Reza Namazi-Rad, and Jun Wang. 2023. How do large language models capture the ever-changing world knowledge? a review of recent advances. arXiv preprint arXiv:2310.07343. find
  41. Tianshi Zheng, Zheye Deng, Hong Ting Tsang, Weiqi Wang, Jiaxin Bai, Zihao Wang, and Yangqiu Song. 2025. From automation to autonomy: A survey on large language models in scientific discovery. arXiv preprint arXiv:2505.13259. find
  42. Yizhen Zheng, Huan Yee Koh, Jiaxin Ju, Anh TN Nguyen, Lauren T May, Geoffrey I Webb, and Shirui Pan. 2023. Large language models for scientific synthesis, inference and explanation. arXiv preprint arXiv:2310.07984. — [arXiv:2310.07984](https://arxiv.org/abs/2310.07984) find
  43. Hang Zhou, Yehui Tang, Haochen Qin, Yujie Yang, Renren Jin, Deyi Xiong, Kai Han, and Yunhe Wang. 2024a. Star-agents: Automatic data optimization with llm agents for instruction tuning. In Advances in Neural Information Processing Systems, volume 37, pages 4575–4597. Curran Associates, Inc. find
  44. Yangqiaoyu Zhou, Haokun Liu, Tejes Srivastava, Hongyuan Mei, and Chenhao Tan. 2024b. Hypothesis generation with large language models. In Proceedings of the 1st Workshop on NLP for Science (NLP4Science), pages 117–139, Miami, FL, USA. Association for Computational Linguistics. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/xiong-2026-evosci-bio-inspired-multi-agent/