---
title: "IRIS — paper by Garikaparthi et al. (2025) — summary and ideas"
description: "The system then builds a research brief containing a title, a methodology and an experiment plan… 49 references, cited by 10 papers here."
authors: ["Aniketh Garikaparthi", "Manasi Patwardhan", "Lovekesh Vig", "Arman Cohan"]
year: 2025
venue: "arXiv:2504.16728"
source: "https://arxiv.org/abs/2504.16728"
doi: "10.48550/arxiv.2504.16728"
arxiv: "2504.16728"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/garikaparthi-2025-iris-interactive-research-ideation-system/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/garikaparthi-2025-iris-interactive-research-ideation-system/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/10/) / IRIS: Interactive Research Ideation System for Accelerating Scientific Discovery

# IRIS: Interactive Research Ideation System for Accelerating Scientific Discovery

**Authors:** [Aniketh Garikaparthi](https://md.research.elamur.ai/free/en/authors/aniketh-garikaparthi/), [Manasi Patwardhan](https://md.research.elamur.ai/free/en/authors/manasi-patwardhan/), [Lovekesh Vig](https://md.research.elamur.ai/free/en/authors/lovekesh-vig/) and [Arman Cohan](https://md.research.elamur.ai/free/en/authors/arman-cohan/) · **Year:** 2025 · **Venue:** [arXiv:2504.16728](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2025](https://md.research.elamur.ai/free/en/venues/acl/2025/)) · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2504.16728) · [PDF](https://arxiv.org/pdf/2504.16728) · [DOI 10.48550/arxiv.2504.16728](https://doi.org/10.48550/arxiv.2504.16728) · [arXiv 2504.16728](https://arxiv.org/abs/2504.16728) · [OpenAlex](https://openalex.org/W4412886950)

**Citations:** 1 citations (OpenAlex, 2026-10-14) · [10](https://md.research.elamur.ai/free/en/papers/garikaparthi-2025-iris-interactive-research-ideation-system/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Most LLM tools for generating research hypotheses run on their own, using multi-agent pipelines or extra inference compute. Humans or LLM judges check the results only at the end. The authors argue that this lets outputs drift away from the researcher's actual goals and lets models game judge metrics with impressive-sounding jargon. IRIS is an open-source platform that keeps the researcher involved throughout ideation. The user supplies a research goal (a problem and its motivation). The system then builds a research brief containing a title, a methodology and an experiment plan, using three agents:
- an **ideation agent** that writes and revises the brief;
- a **review agent** that scores the brief against a hierarchical critique taxonomy and gives segment-level feedback, which the user can keep or discard;
- a **retrieval agent** that writes targeted queries and assembles cited, clustered literature reports.

Monte Carlo Tree Search switches between exploring new ideas and refining promising ones, either autonomously or under user direction. In a study with eight researchers, interaction improved LLM-judged hypothesis quality, and participants rated control and feedback highly. The work offers a practical model for steerable, transparent human–AI research ideation.

## Key points
- IRIS uses MCTS to expand test-time compute. Its retrieval relies on the Ai2 Scholar QA API over Semantic Scholar's snippet search (200M+ papers), plus Grobid-based doc2json parsing for PDFs that users upload.
- The user study had N=8 researchers from AI/NLP, chemistry, physics and HCI, in 10 sessions of about 60 minutes. Mean ratings on a 1–5 scale were:
  - usability/control: 4.5
  - fine-grained feedback: 4.3
  - MCTS tree interface: 4.2
  - overall satisfaction: 3.9
  - literature summaries: 3.7
- At tree depth 3, interaction produced a 0.5-point gain in the mean absolute score from the LLM judge and a 12-point gain in ELO.
- Human rankings agreed better with LLM ELO scores (Pearson r=0.60) than with LLM absolute scores (r=0.45). The authors therefore plan to show ELO ratings in the interface instead of judge scores.
- After interaction, 2 of 8 users rated their hypothesis substantially better, 4 marginally better and 2 about the same. Retrieval quality was weaker in chemistry and physics. Frontier and reasoning models were not tested because of budget limits.

*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 University](https://md.research.elamur.ai/free/en/universities/yale-university/) — University, New Haven, United States · 112 works · 14,009 citations
- [Tata Consultancy Services](https://md.research.elamur.ai/free/en/companies/tata-consultancy-services/) — Company, Pune, India · 9 works · 46 citations

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 19,503 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 18,805 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,959 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,789 works · [🧱 Materials Science](https://md.research.elamur.ai/free/en/shelves/materials-science/) · 58 works · [🧱 Materials Chemistry](https://md.research.elamur.ai/free/en/shelves/materials-science/materials-chemistry/) · 58 works

## Cite

Cite as: Aniketh Garikaparthi, Manasi Patwardhan, Lovekesh Vig and Arman Cohan. 2025. IRIS: Interactive Research Ideation System for Accelerating Scientific Discovery. arXiv:2504.16728.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{garikaparthi2025iris,
  title = {{IRIS: Interactive Research Ideation System for Accelerating Scientific Discovery}},
  author = {Aniketh Garikaparthi, Manasi Patwardhan, Lovekesh Vig and Arman Cohan},
  year = {2025},
  doi = {10.48550/arxiv.2504.16728},
  eprint = {2504.16728},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2504.16728}
}
```

- [← previous Influences on LLM Calibration: A Study of Response Agreement, Loss Functions, and Prompt Styles](https://md.research.elamur.ai/free/en/papers/xia-2025-influences-llm-calibration-study-response/)
- [next → Is That Your Final Answer? Test-Time Scaling Improves Selective Question Answering](https://md.research.elamur.ai/free/en/papers/jurayj-2025-is-that-your-final-answer/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/10/)

## References

49 references, 21 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Nils Dycke, Ilia Kuznetsov, and Iryna Gurevych. 2023. [NLPeer: A unified resource for the computational study of peer review](https://md.research.elamur.ai/free/en/papers/dycke-2023-nlpeer-unified-resource-computational-study/). In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5049– 5073, Toronto, Canada. Association for Computat…
2. Anirudh Ajith, Mengzhou Xia, Alexis Chevalier, Tanya Goyal, Danqi Chen, and Tianyu Gao. 2024. [Litsearch: A retrieval benchmark for scientific literature search](https://md.research.elamur.ai/free/en/papers/ajith-2024-litsearch-retrieval-benchmark-scientific-literature/). Preprint, arXiv:2407.18940.
3. Saleema Amershi, Dan Weld, Mihaela Vorvoreanu, Adam Fourney, Besmira Nushi, Penny Collisson, Jina Suh, Shamsi Iqbal, Paul N. Bennett, Kori Inkpen, Jaime Teevan, Ruth Kikin-Gil, and Eric Horvitz. 2019. Guidelines for human-ai interaction. In Proceedings of the 2019 CHI Conference on Human Factors in… [find](https://scholar.google.com/scholar?q=Saleema+Amershi%2C+Dan+Weld%2C+Mihaela+Vorvoreanu%2C+Adam+Fourney%2C+Besmira+Nushi%2C+Penny+Collisson%2C+Jina+Suh%2C+Shamsi+Iqbal%2C+Paul+N%2E+Bennett%2C+Kori+Inkpen%2C+Jaime+Teevan%2C+Ruth+Kikin%2DGil%2C+and+Eric+Horvitz%2E+2019%2E)
4. Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, Dasha Metropolitansky, Robert Osazuwa Ness, and Jonathan Larson. 2025. From local to global: A graph rag approach to query-focused summarization. Preprint, arXiv:2404.16130. [find](https://scholar.google.com/scholar?q=Darren+Edge%2C+Ha+Trinh%2C+Newman+Cheng%2C+Joshua+Bradley%2C+Alex+Chao%2C+Apurva+Mody%2C+Steven+Truitt%2C+Dasha+Metropolitansky%2C+Robert+Osazuwa+Ness%2C+and+Jonathan+Larson%2E+2025%2E+From+local+to+global%3A+A+graph+rag+app)
5. Michael Fire and Carlos Guestrin. 2019. Overoptimization of academic publishing metrics: observing goodhart’s law in action. GigaScience, 8(6):giz053. [find](https://scholar.google.com/scholar?q=Michael+Fire+and+Carlos+Guestrin%2E+2019%2E+Overoptimization+of+academic+publishing+metrics%3A+observing+goodhart%E2%80%99s+law+in+action%2E+GigaScience%2C+8%286%29%3Agiz053%2E)
6. Anthropic. 2025. Claude 3.7 sonnet system card. Accessed: 2025-03-10. [find](https://scholar.google.com/scholar?q=Anthropic%2E+2025%2E+Claude+3%2E7+sonnet+system+card%2E+Accessed%3A+2025%2D03%2D10%2E)
7. Akari Asai, Jacqueline He, Rulin Shao, Weijia Shi, Amanpreet Singh, Joseph Chee Chang, Kyle Lo, Luca Soldaini, Sergey Feldman, Mike D’arcy, David Wadden, Matt Latzke, Minyang Tian, Pan Ji, Shengyan Liu, Hao Tong, Bohao Wu, Yanyu Xiong, Luke Zettlemoyer, Graham Neubig, Dan Weld, Doug Downey, Wen tau… — [OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs](https://md.research.elamur.ai/free/en/papers/asai-2024-openscholar-synthesizing-scientific-literature/)
8. Tirthankar Ghosal, Sandeep Kumar, Prabhat Kumar Bharti, and Asif Ekbal. 2022. Peer review analyze: A novel benchmark resource for computational analysis of peer reviews. PLOS ONE, 17(1):1–29. [find](https://scholar.google.com/scholar?q=Tirthankar+Ghosal%2C+Sandeep+Kumar%2C+Prabhat+Kumar+Bharti%2C+and+Asif+Ekbal%2E+2022%2E+Peer+review+analyze%3A+A+novel+benchmark+resource+for+computational+analysis+of+peer+reviews%2E+PLOS+ONE%2C+17%281%29%3A1%E2%80%9329%2E)
9. Juraj Gottweis. 2025. Towards an ai co-scientist. [find](https://scholar.google.com/scholar?q=Juraj+Gottweis%2E+2025%2E+Towards+an+ai+co%2Dscientist%2E)
10. Mourad Gridach, Jay Nanavati, Khaldoun Zine El Abidine, Lenon Mendes, and Christina Mack. 2025. Agentic ai for scientific discovery: A survey of progress, challenges, and future directions. Preprint, arXiv:2503.08979. — [arXiv:2503.08979](https://arxiv.org/abs/2503.08979) [find](https://scholar.google.com/scholar?q=Mourad+Gridach%2C+Jay+Nanavati%2C+Khaldoun+Zine+El+Abidine%2C+Lenon+Mendes%2C+and+Christina+Mack%2E+2025%2E+Agentic+ai+for+scientific+discovery%3A+A+survey+of+progress%2C+challenges%2C+and+future+directions%2E+Preprint%2C+)
11. Jinheon Baek, Sujay Kumar Jauhar, Silviu Cucerzan, and Sung Ju Hwang. 2025. [Researchagent: Iterative research idea generation over scientific literature with large language models](https://md.research.elamur.ai/free/en/papers/baek-2024-researchagent-iterative-research-idea/). Preprint, arXiv:2404.07738.
12. Xinyu Guan, Li Lyna Zhang, Yifei Liu, Ning Shang, Youran Sun, Yi Zhu, Fan Yang, and Mao Yang. 2025. [rstar-math: Small llms can master math reasoning with self-evolved deep thinking](https://md.research.elamur.ai/free/en/papers/guan-2025-rstar-math-small-llms-can/). Preprint, arXiv:2501.04519.
13. Bowen Baker, Joost Huizinga, Leo Gao, Zehao Dou, Melody Y. Guan, Aleksander Madry, Wojciech Zaremba, Jakub Pachocki, and David Farhi. 2025. [Monitoring reasoning models for misbehavior and the risks of promoting obfuscation](https://md.research.elamur.ai/free/en/papers/baker-2025-monitoring-reasoning-models-misbehavior-risks/). Accessed: 2025-03-11.
14. Tarun Gupta and Danish Pruthi. 2025. [All that glitters is not novel: Plagiarism in ai generated research](https://md.research.elamur.ai/free/en/papers/gupta-2025-all-that-glitters-novel/). Preprint, arXiv:2502.16487.
15. Xiang Hu, Hongyu Fu, Jinge Wang, Yifeng Wang, Zhikun Li, Renjun Xu, Yu Lu, Yaochu Jin, Lili Pan, and Zhenzhong Lan. 2024. [Nova: An iterative planning and search approach to enhance novelty and diversity of llm generated ideas](https://md.research.elamur.ai/free/en/papers/hu-2024-nova-iterative-planning-search-approach/). Preprint, arXiv:2410.14255.
16. Esther Landhuis. 2016. Scientific literature: Information overload. Nature, 535:457 – 458. [find](https://scholar.google.com/scholar?q=Esther+Landhuis%2E+2016%2E+Scientific+literature%3A+Information+overload%2E+Nature%2C+535%3A457+%E2%80%93+458%2E)
17. Long Li, Weiwen Xu, Jiayan Guo, Ruochen Zhao, Xingxuan Li, Yuqian Yuan, Boqiang Zhang, Yuming Jiang, Yifei Xin, Ronghao Dang, Deli Zhao, Yu Rong, Tian Feng, and Lidong Bing. 2024. [Chain of ideas: Revolutionizing research via novel idea development with llm agents](https://md.research.elamur.ai/free/en/papers/li-2024-chain-ideas-revolutionizing-research/). Preprint, arXiv:2410.13185.
18. Qian Huang, Jian Vora, Percy Liang, and Jure Leskovec. 2024. [Mlagentbench: Evaluating language agents on machine learning experimentation](https://md.research.elamur.ai/free/en/papers/huang-2023-mlagentbench-evaluating-language-agents/). Preprint, arXiv:2310.03302.
19. Yiren Liu, Si Chen, Haocong Cheng, Mengxia Yu, Xiao Ran, Andrew Mo, Yiliu Tang, and Yun Huang. 2024. How ai processing delays foster creativity: Exploring research question co-creation with an llm-based agent. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems, CHI ’24,… [find](https://scholar.google.com/scholar?q=Yiren+Liu%2C+Si+Chen%2C+Haocong+Cheng%2C+Mengxia+Yu%2C+Xiao+Ran%2C+Andrew+Mo%2C+Yiliu+Tang%2C+and+Yun+Huang%2E+2024%2E+How+ai+processing+delays+foster+creativity%3A+Exploring+research+question+co%2Dcreation+with+an+llm%2Dbas)
20. Anna Kantosalo and Anna Jordanous. 2021. Role-based perceptions of computer participants in human-computer co-creativity. In 7th Computational Creativity Symposium at AISB 2021, pages 20–26, London, UK. AISB. [find](https://scholar.google.com/scholar?q=Anna+Kantosalo+and+Anna+Jordanous%2E+2021%2E+Role%2Dbased+perceptions+of+computer+participants+in+human%2Dcomputer+co%2Dcreativity%2E+In+7th+Computational+Creativity+Symposium+at+AISB+2021%2C+pages+20%E2%80%9326%2C+London%2C+U)
21. Neha Nayak Kennard, Tim O’Gorman, Rajarshi Das, Akshay Sharma, Chhandak Bagchi, Matthew Clinton, Pranay Kumar Yelugam, Hamed Zamani, and Andrew McCallum. 2022. DISAPERE: A dataset for discourse structure in peer review discussions. In Proceedings of the 2022 Conference of the North American Chapter… [find](https://scholar.google.com/scholar?q=Neha+Nayak+Kennard%2C+Tim+O%E2%80%99Gorman%2C+Rajarshi+Das%2C+Akshay+Sharma%2C+Chhandak+Bagchi%2C+Matthew+Clinton%2C+Pranay+Kumar+Yelugam%2C+Hamed+Zamani%2C+and+Andrew+McCallum%2E+2022%2E+DISAPERE%3A+A+dataset+for+discourse+struct)
22. 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](https://md.research.elamur.ai/free/en/papers/lu-2024-ai-scientist-fully-automated/). Preprint, arXiv:2408.06292.
23. Martin Májovský, Martin Černý, Matěj Kasal, Martin Komarc, and David Netuka. 2023. Artificial intelligence can generate fraudulent but authentic-looking scientific medical articles: Pandora’s box has been opened. J Med Internet Res, 25:e46924. [find](https://scholar.google.com/scholar?q=Martin+M%C3%A1jovsk%C3%BD%2C+Martin+C%CC%8Cern%C3%BD%2C+Mate%CC%8Cj+Kasal%2C+Martin+Komarc%2C+and+David+Netuka%2E+2023%2E+Artificial+intelligence+can+generate+fraudulent+but+authentic%2Dlooking+scientific+medical+articles%3A+Pandora%E2%80%99s+box+ha)
24. Yoonsu Kim, Jueon Lee, Seoyoung Kim, Jaehyuk Park, and Juho Kim. 2024. Understanding users’ dissatisfaction with chatgpt responses: Types, resolving tactics, and the effect of knowledge level. In Proceedings of the 29th International Conference on Intelligent User Interfaces, IUI ’24, page 385–404,… [find](https://scholar.google.com/scholar?q=Yoonsu+Kim%2C+Jueon+Lee%2C+Seoyoung+Kim%2C+Jaehyuk+Park%2C+and+Juho+Kim%2E+2024%2E+Understanding+users%E2%80%99+dissatisfaction+with+chatgpt+responses%3A+Types%2C+resolving+tactics%2C+and+the+effect+of+knowledge+level%2E+In+Proc)
25. Michael Muller, Justin D Weisz, and Werner Geyer. 2020. Mixed initiative generative ai interfaces: An analytic framework for generative ai applications. In Proceedings of the Workshop The Future of Co-Creative Systems-A Workshop on Human-Computer Co-Creativity of the 11th International Conference on… [find](https://scholar.google.com/scholar?q=Michael+Muller%2C+Justin+D+Weisz%2C+and+Werner+Geyer%2E+2020%2E+Mixed+initiative+generative+ai+interfaces%3A+An+analytic+framework+for+generative+ai+applications%2E+In+Proceedings+of+the+Workshop+The+Future+of+Co)
26. Rodney Kinney, Chloe Anastasiades, Russell Authur, Iz Beltagy, Jonathan Bragg, Alexandra Buraczynski, Isabel Cachola, Stefan Candra, Yoganand Chandrasekhar, Arman Cohan, Miles Crawford, Doug Downey, Jason Dunkelberger, Oren Etzioni, Rob Evans, Sergey Feldman, Joseph Gorney, David Graham, Fangzhou Hu… [find](https://scholar.google.com/scholar?q=Rodney+Kinney%2C+Chloe+Anastasiades%2C+Russell+Authur%2C+Iz+Beltagy%2C+Jonathan+Bragg%2C+Alexandra+Buraczynski%2C+Isabel+Cachola%2C+Stefan+Candra%2C+Yoganand+Chandrasekhar%2C+Arman+Cohan%2C+Miles+Crawford%2C+Doug+Downey%2C+J)
27. Rahul Nadkarni, David Wadden, Iz Beltagy, Noah A. Smith, Hannaneh Hajishirzi, and Tom Hope. 2021. Scientific language models for biomedical knowledge base completion: An empirical study. Preprint, arXiv:2106.09700. — [arXiv:2106.09700](https://arxiv.org/abs/2106.09700) [find](https://scholar.google.com/scholar?q=Rahul+Nadkarni%2C+David+Wadden%2C+Iz+Beltagy%2C+Noah+A%2E+Smith%2C+Hannaneh+Hajishirzi%2C+and+Tom+Hope%2E+2021%2E+Scientific+language+models+for+biomedical+knowledge+base+completion%3A+An+empirical+study%2E+Preprint%2C+arX)
28. Harshit Nigam, Manasi Patwardhan, Lovekesh Vig, and Gautam Shroff. 2024. An interactive co-pilot for accelerated research ideation. In Proceedings of the Third Workshop on Bridging Human–Computer Interaction and Natural Language Processing, pages 60–73, Mexico City, Mexico. Association for Computati… [find](https://scholar.google.com/scholar?q=Harshit+Nigam%2C+Manasi+Patwardhan%2C+Lovekesh+Vig%2C+and+Gautam+Shroff%2E+2024%2E+An+interactive+co%2Dpilot+for+accelerated+research+ideation%2E+In+Proceedings+of+the+Third+Workshop+on+Bridging+Human%E2%80%93Computer+Inte)
29. Changkun Ou, Daniel Buschek, Sven Mayer, and Andreas Butz. 2022. The human in the infinite loop: A case study on revealing and explaining human-ai interaction loop failures. In Proceedings of Mensch Und Computer 2022, MuC ’22, page 158–168, New York, NY, USA. Association for Computing Machinery. [find](https://scholar.google.com/scholar?q=Changkun+Ou%2C+Daniel+Buschek%2C+Sven+Mayer%2C+and+Andreas+Butz%2E+2022%2E+The+human+in+the+infinite+loop%3A+A+case+study+on+revealing+and+explaining+human%2Dai+interaction+loop+failures%2E+In+Proceedings+of+Mensch+U)
30. Levente Kocsis and Csaba Szepesvári. 2006. Bandit based monte-carlo planning. In Machine Learning: ECML 2006, pages 282–293, Berlin, Heidelberg. Springer Berlin Heidelberg. [find](https://scholar.google.com/scholar?q=Levente+Kocsis+and+Csaba+Szepesv%C3%A1ri%2E+2006%2E+Bandit+based+monte%2Dcarlo+planning%2E+In+Machine+Learning%3A+ECML+2006%2C+pages+282%E2%80%93293%2C+Berlin%2C+Heidelberg%2E+Springer+Berlin+Heidelberg%2E)
31. Reshma S Pillai and Deepthi L R. 2022. A survey on citation recommendation system. In 2022 Third International Conference on Intelligent Computing Instrumentation and Control Technologies (ICICICT), pages 423–429. [find](https://scholar.google.com/scholar?q=Reshma+S+Pillai+and+Deepthi+L+R%2E+2022%2E+A+survey+on+citation+recommendation+system%2E+In+2022+Third+International+Conference+on+Intelligent+Computing+Instrumentation+and+Control+Technologies+%28ICICICT%29%2C+p)
32. Sandeep Kumar, Tirthankar Ghosal, Vinayak Goyal, and Asif Ekbal. 2024. [Can large language models unlock novel scientific research ideas?](https://md.research.elamur.ai/free/en/papers/kumar-2025-can-large-language-models-unlock/) Preprint, arXiv:2409.06185.
33. Ori Press, Andreas Hochlehnert, Ameya Prabhu, Vishaal Udandarao, Ofir Press, and Matthias Bethge. 2024. [Citeme: Can language models accurately cite scientific claims?](https://md.research.elamur.ai/free/en/papers/press-2024-citeme-language-models-accurately/) Preprint, arXiv:2407.12861.
34. Justin Sybrandt, Ilya Tyagin, Michael Shtutman, and Ilya Safro. 2020. Agatha: Automatic graph mining and transformer based hypothesis generation approach. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management, CIKM ’20, page 2757–2764, New York, NY, USA. Assoc… [find](https://scholar.google.com/scholar?q=Justin+Sybrandt%2C+Ilya+Tyagin%2C+Michael+Shtutman%2C+and+Ilya+Safro%2E+2020%2E+Agatha%3A+Automatic+graph+mining+and+transformer+based+hypothesis+generation+approach%2E+In+Proceedings+of+the+29th+ACM+International+)
35. Kevin Pu, K. J. Kevin Feng, Tovi Grossman, Tom Hope, Bhavana Dalvi Mishra, Matt Latzke, Jonathan Bragg, Joseph Chee Chang, and Pao Siangliulue. 2024. Ideasynth: Iterative research idea development through evolving and composing idea facets with literature-grounded feedback. Preprint, arXiv:2410.0402… — [arXiv:2410.04025](https://arxiv.org/abs/2410.04025) [find](https://scholar.google.com/scholar?q=Kevin+Pu%2C+K%2E+J%2E+Kevin+Feng%2C+Tovi+Grossman%2C+Tom+Hope%2C+Bhavana+Dalvi+Mishra%2C+Matt+Latzke%2C+Jonathan+Bragg%2C+Joseph+Chee+Chang%2C+and+Pao+Siangliulue%2E+2024%2E+Ideasynth%3A+Iterative+research+idea+development+thr)
36. Qingyun Wang, Doug Downey, Heng Ji, and Tom Hope. 2024. [SciMON: Scientific inspiration machines optimized for novelty](https://md.research.elamur.ai/free/en/papers/wang-2023-scimon-scientific-inspiration-machines/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 279–299, Bangkok, Thailand. Association for Computational L…
37. Zhenting Qi, Mingyuan Ma, Jiahang Xu, Li Lyna Zhang, Fan Yang, and Mao Yang. 2024. [Mutual reasoning makes smaller llms stronger problem-solvers](https://md.research.elamur.ai/free/en/papers/qi-2024-mutual-reasoning-makes-smaller-llms/). Preprint, arXiv:2408.06195.
38. Justin D. Weisz, Jessica He, Michael Muller, Gabriela Hoefer, Rachel Miles, and Werner Geyer. 2024. Design principles for generative ai applications. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems, CHI ’24, New York, NY, USA. Association for Computing Machinery. et.a… [find](https://scholar.google.com/scholar?q=Justin+D%2E+Weisz%2C+Jessica+He%2C+Michael+Muller%2C+Gabriela+Hoefer%2C+Rachel+Miles%2C+and+Werner+Geyer%2E+2024%2E+Design+principles+for+generative+ai+applications%2E+In+Proceedings+of+the+2024+CHI+Conference+on+Human)
39. Samuel Schmidgall, Yusheng Su, Ze Wang, Ximeng Sun, Jialian Wu, Xiaodong Yu, Jiang Liu, Zicheng Liu, and Emad Barsoum. 2025. [Agent laboratory: Using llm agents as research assistants](https://md.research.elamur.ai/free/en/papers/schmidgall-2025-agent-laboratory-using-llm/). Preprint, arXiv:2501.04227.
40. Yixuan Weng, Minjun Zhu, Guangsheng Bao, Hongbo Zhang, Jindong Wang, Yue Zhang, and Linyi Yang. 2025. [Cycleresearcher: Improving automated research via automated review](https://md.research.elamur.ai/free/en/papers/weng-2024-cycleresearcher-improving-automated-research/). Preprint, arXiv:2411.00816.
41. Ben Shneiderman. 2020. Bridging the gap between ethics and practice: Guidelines for reliable, safe, and trustworthy human-centered ai systems. ACM Trans. Interact. Intell. Syst., 10(4). [find](https://scholar.google.com/scholar?q=Ben+Shneiderman%2E+2020%2E+Bridging+the+gap+between+ethics+and+practice%3A+Guidelines+for+reliable%2C+safe%2C+and+trustworthy+human%2Dcentered+ai+systems%2E+ACM+Trans%2E+Interact%2E+Intell%2E+Syst%2E%2C+10%284%29%2E)
42. Jinzhu Zhang and Lipeng Zhu. 2022. Citation recommendation using semantic representation of cited papers’ relations and content. Expert Systems with Applications, 187:115826. [find](https://scholar.google.com/scholar?q=Jinzhu+Zhang+and+Lipeng+Zhu%2E+2022%2E+Citation+recommendation+using+semantic+representation+of+cited+papers%E2%80%99+relations+and+content%2E+Expert+Systems+with+Applications%2C+187%3A115826%2E)
43. Chenglei Si, Diyi Yang, and Tatsunori Hashimoto. 2024. [Can llms generate novel research ideas? a large-scale human study with 100+ nlp researchers](https://md.research.elamur.ai/free/en/papers/si-2024-llms-generate-novel-research/). Preprint, arXiv:2409.04109.
44. Yuxiang Zheng, Shichao Sun, Lin Qiu, Dongyu Ru, Cheng Jiayang, Xuefeng Li, Jifan Lin, Binjie Wang, Yun Luo, Renjie Pan, Yang Xu, Qingkai Min, Zizhao Zhang, Yiwen Wang, Wenjie Li, and Pengfei Liu. 2024. Openresearcher: Unleashing ai for accelerated scientific research. Preprint, arXiv:2408.06941. [find](https://scholar.google.com/scholar?q=Yuxiang+Zheng%2C+Shichao+Sun%2C+Lin+Qiu%2C+Dongyu+Ru%2C+Cheng+Jiayang%2C+Xuefeng+Li%2C+Jifan+Lin%2C+Binjie+Wang%2C+Yun+Luo%2C+Renjie+Pan%2C+Yang+Xu%2C+Qingkai+Min%2C+Zizhao+Zhang%2C+Yiwen+Wang%2C+Wenjie+Li%2C+and+Pengfei+Liu%2E+2024)
45. Michael D. Skarlinski, Sam Cox, Jon M. Laurent, James D. Braza, Michaela Hinks, Michael J. Hammerling, Manvitha Ponnapati, Samuel G. Rodriques, and Andrew D. White. 2024. [Language agents achieve superhuman synthesis of scientific knowledge](https://md.research.elamur.ai/free/en/papers/skarlinski-2024-language-agents-achieve-superhuman/). Preprint, arXiv:2409.13740.
46. Ruiyang Zhou, Lu Chen, and Kai Yu. 2024. [Is LLM a reliable reviewer? a comprehensive evaluation of LLM on automatic paper reviewing tasks](https://md.research.elamur.ai/free/en/papers/zhou-2024-is-llm-reliable-reviewer-comprehensive/). In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 9340– 9351, T…
47. Peiyang Song, Kaiyu Yang, and Anima Anandkumar. 2025. [Lean copilot: Large language models as copilots for theorem proving in lean](https://md.research.elamur.ai/free/en/papers/song-2024-lean-copilot-large-language-models/). Preprint, arXiv:2404.12534.
48. Scott Spangler, Angela D. Wilkins, Benjamin J. Bachman, Meena Nagarajan, Tajhal Dayaram, Peter Haas, Sam Regenbogen, Curtis R. Pickering, Austin Comer, Jeffrey N. Myers, Ioana Stanoi, Linda Kato, Ana Lelescu, Jacques J. Labrie, Neha Parikh, Andreas Martin Lisewski, Lawrence Donehower, Ying Chen, and… [find](https://scholar.google.com/scholar?q=Scott+Spangler%2C+Angela+D%2E+Wilkins%2C+Benjamin+J%2E+Bachman%2C+Meena+Nagarajan%2C+Tajhal+Dayaram%2C+Peter+Haas%2C+Sam+Regenbogen%2C+Curtis+R%2E+Pickering%2C+Austin+Comer%2C+Jeffrey+N%2E+Myers%2C+Ioana+Stanoi%2C+Linda+Kato%2C+Ana+)
49. Don R. Swanson. 1986. Undiscovered public knowledge. The Library Quarterly: Information, Community, Policy, 56(2):103–118. [find](https://scholar.google.com/scholar?q=Don+R%2E+Swanson%2E+1986%2E+Undiscovered+public+knowledge%2E+The+Library+Quarterly%3A+Information%2C+Community%2C+Policy%2C+56%282%29%3A103%E2%80%93118%2E)

*Updated 3 November 2026*