---
title: "Problem Solving Through Human–AI Preference-based"
description: "The authors introduce HAI-Co², a conceptual framework that treats building a solution as stepwise… 62 references, cited by 6 papers here."
authors: ["Subhabrata Dutta", "Timo Kaufmann", "Goran Glavaš", "Ivan Habernal", "Kristian Kersting", "Frauke Kreuter", "Mira Mezini", "Iryna Gurevych", "Eyke Hüllermeier", "Hinrich Schütze"]
year: 2025
venue: "Computational Linguistics"
source: "https://aclanthology.org/2025.cl-4.8/"
doi: "10.1162/coli.a.19"
licence: "CC BY-NC-ND 4.0 (Computational Linguistics, MIT Press)"
licence_url: "https://creativecommons.org/licenses/by-nc-nd/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/dutta-2025-problem-solving-through-human-ai/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/dutta-2025-problem-solving-through-human-ai/)

[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/9/) / Problem Solving Through Human–AI Preference-based Cooperation

# Problem Solving Through Human–AI Preference-based Cooperation

**Authors:** [Subhabrata Dutta](https://md.research.elamur.ai/free/en/authors/subhabrata-dutta/), Timo Kaufmann, [Goran Glavaš](https://md.research.elamur.ai/free/en/authors/goran-glavas/), [Ivan Habernal](https://md.research.elamur.ai/free/en/authors/ivan-habernal/), [Kristian Kersting](https://md.research.elamur.ai/free/en/authors/kristian-kersting/), [Frauke Kreuter](https://md.research.elamur.ai/free/en/authors/frauke-kreuter/), Mira Mezini, [Iryna Gurevych](https://md.research.elamur.ai/free/en/authors/iryna-gurevych/), [Eyke Hüllermeier](https://md.research.elamur.ai/free/en/authors/eyke-hullermeier/) and [Hinrich Schütze](https://md.research.elamur.ai/free/en/authors/hinrich-schutze/) · **Year:** 2025 · **Venue:** [Computational Linguistics](https://md.research.elamur.ai/free/en/venues/cl/) ([Computational Linguistics 2025](https://md.research.elamur.ai/free/en/venues/cl/2025/)) · **Publisher:** [The MIT Press](https://md.research.elamur.ai/free/en/publishers/the-mit-press/) · **Licence:** [CC BY-NC-ND 4.0 (Computational Linguistics, MIT Press)](https://creativecommons.org/licenses/by-nc-nd/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2025.cl-4.8/) · [PDF](https://aclanthology.org/2025.cl-4.8.pdf) · [DOI 10.1162/coli.a.19](https://doi.org/10.1162/coli.a.19) · [OpenAlex](https://openalex.org/W4412806192)

**Citations:** 3 citations (OpenAlex, 2026-10-14) · [6](https://md.research.elamur.ai/free/en/papers/dutta-2025-problem-solving-through-human-ai/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Generative AI systems, including LLMs, vision-language models and code models, still struggle with complex expert-domain tasks. These tasks demand long-range planning, tracking many constraints at once and maintaining a large, evolving artifact such as a program. This position paper argues that full automation is the wrong goal for such work. Humans and AI should instead act as equal partners with complementary strengths. The authors introduce HAI-Co², a conceptual framework that treats building a solution as stepwise search over an explicit construction space with several abstraction levels. The goal itself is refined jointly through interactive preference learning, drawing on multi-criteria decision aiding (MCDA). Natural language is the main channel between partners. The paper releases no new dataset or benchmark. Instead, a running example of software generation with GPT-4 Turbo shows where current models fail: following preferences, reliably revising complex artifacts and supporting active human input. The authors sketch a first formalization and list open problems, including ethics and evaluation. The paper offers a research agenda for AI collaborators in expert work.

## Key points
- HAI-Co² (Human–AI Co-Construction) has four defining traits: complex expert-domain problems, joint construction of the solution, joint construction of the objective via preference learning, and natural language as the primary medium.
- Solutions and objectives are co-built differently. Solutions are artifacts found by search in a hierarchical construction space. Objectives are encoded as a utility or preference model over that space.
- Target use cases include writing software, assembling AutoML pipelines, drafting related-work sections and formalizing mathematical problems stated in natural language.
- The framework is contrasted with classic human-in-the-loop learning (e.g., active learning), where the human only serves as an oracle. HAI-Co² aims for a more symmetric partnership.
- Highlighted open challenges include learning from implicit feedback in natural language, edits and multimodal signals. Others are ethical risks such as influenceable reward functions and new evaluation methods for open-ended, non-unique solutions (Computational Linguistics, 2025; DOI 10.1162/COLI.a.19).

*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

- [Technische Universität Darmstadt](https://md.research.elamur.ai/free/en/universities/technische-universitat-darmstadt/) — University, Darmstadt, Germany · 109 works · 35,920 citations
- [Ludwig-Maximilians-Universität München](https://md.research.elamur.ai/free/en/universities/ludwig-maximilians-universitat-munchen/) — University, Munich, Germany · 107 works · 56,478 citations
- [Ruhr University Bochum](https://md.research.elamur.ai/free/en/universities/ruhr-university-bochum/) — University, Bochum, Germany · 25 works · 1,189 citations
- [University of Würzburg](https://md.research.elamur.ai/free/en/universities/university-of-wurzburg/) — University, Würzburg, Germany · 8 works · 60 citations
- [National Research Center for Applied Cybersecurity ATHENE](https://md.research.elamur.ai/free/en/labs/national-research-center-for-applied-cybersecurity-athene/) — Research institute, Darmstadt, Germany · 3 works · 17 citations

📚 Shelves (2): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works

🧭 Topics (1): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,426 works

## Cite

Cite as: Subhabrata Dutta, Timo Kaufmann, Goran Glavaš, Ivan Habernal, Kristian Kersting, Frauke Kreuter, Mira Mezini, Iryna Gurevych, Eyke Hüllermeier and Hinrich Schütze. 2025. Problem Solving Through Human–AI Preference-based Cooperation. Computational Linguistics.

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

```bibtex
@article{dutta2025problem,
  title = {{Problem Solving Through Human–AI Preference-based Cooperation}},
  author = {Subhabrata Dutta, Timo Kaufmann, Goran Glavaš, Ivan Habernal, Kristian Kersting, Frauke Kreuter, Mira Mezini, Iryna Gurevych, Eyke Hüllermeier and Hinrich Schütze},
  journal = {Computational Linguistics},
  year = {2025},
  doi = {10.1162/coli.a.19},
  url = {https://doi.org/10.1162/coli.a.19}
}
```

- [← previous Pragmatic Inference Chain (PIC) Improving LLMs' Reasoning of Authentic Implicit Toxic Language](https://md.research.elamur.ai/free/en/papers/chen-2025-pragmatic-inference-chain-pic-improving/)
- [next → Refining Input Guardrails: Enhancing LLM-as-a-Judge Efficiency Through Chain-of-Thought Fine-Tuning and Alignment](https://md.research.elamur.ai/free/en/papers/rad-2025-refining-input-guardrails-enhancing-llm/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/9/)

## References

62 references, 17 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Aithal, Sumukh K., Pratyush Maini, Zachary C. Lipton, and J. Zico Kolter. 2024. Understanding hallucinations in diffusion models through mode interpolation. CoRR, abs/2406.09358. — [arXiv:2406.09358](https://arxiv.org/abs/2406.09358) [find](https://scholar.google.com/scholar?q=Aithal%2C+Sumukh+K%2E%2C+Pratyush+Maini%2C+Zachary+C%2E+Lipton%2C+and+J%2E+Zico+Kolter%2E+2024%2E+Understanding+hallucinations+in+diffusion+models+through+mode+interpolation%2E+CoRR%2C+abs%2F2406%2E09358%2E+%E2%80%94+%5BarXiv%3A2406%2E09358%5D%28)
2. Akata, Zeynep, Dan Balliet, Maarten de Rijke, Frank Dignum, Virginia Dignum, Guszti Eiben, Antske Fokkens, Davide Grossi, Koen Hindriks, Holger Hoos, et al. 2020. A research agenda for hybrid intelligence: Augmenting human intellect with collaborative, adaptive, responsible, and explainable artifici… — [doi:10.1109/mc.2020.2996587](https://doi.org/10.1109/mc.2020.2996587) [find](https://scholar.google.com/scholar?q=Akata%2C+Zeynep%2C+Dan+Balliet%2C+Maarten+de+Rijke%2C+Frank+Dignum%2C+Virginia+Dignum%2C+Guszti+Eiben%2C+Antske+Fokkens%2C+Davide+Grossi%2C+Koen+Hindriks%2C+Holger+Hoos%2C+et+al%2E+2020%2E+A+research+agenda+for+hybrid+intellig)
3. Bird, Christian, Denae Ford, Thomas Zimmermann, Nicole Forsgren, Eirini Kalliamvakou, Travis Lowdermilk, and Idan Gazit. 2023. Taking flight with Copilot: Early insights and opportunities of AI-powered pair-programming tools. Queue, 20(6):35–57. https://doi.org/10.1145/3582083 Boutilier, Craig. 200… — [doi:10.1145/3582083](https://doi.org/10.1145/3582083) [↗](https://doi.org/10.1145/3582083)
4. Bradley, Ralph Allan and Milton E. Terry. 1952. Rank analysis of incomplete block designs: I. The method of paired comparisons. Biometrika, 39(3/4):324–345. https://doi.org/10.1093/biomet/39.3 -4.324 Branavan, S. R. K., Harr Chen, Luke Zettlemoyer, and Regina Barzilay. 2009. Reinforcement learning f… — [doi:10.1093/biomet/39.3](https://doi.org/10.1093/biomet/39.3) [↗](https://doi.org/10.1093/biomet/39.3)
5. Brown, Tom, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D. Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. [Language models are few-shot learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/). In Advances in Neural Information Processing Systems (NeurIPS), volume 33, pages 1877–1901.
6. Cao, Yihan, Siyu Li, Yixin Liu, Zhiling Yan, Yutong Dai, Philip Yu, and Lichao Sun. 2025. A survey of AI-generated content (AIGC). ACM Computing Surveys, 57(5):125:1–125:38. https://doi.org/10.1145/3704262 Carroll, Micah, Davis Foote, Anand Siththaranjan, Stuart Russell, and Anca Dragan. 2024. AI a… [↗](https://doi.org/10.1145/3704262)
7. Carroll, Micah, Rohin Shah, Mark K. Ho, Tom Griffiths, Sanjit Seshia, Pieter Abbeel, and Anca Dragan. 2019. On the utility of learning about humans for human-AI coordination. In Advances in Neural Information Processing Systems, volume 32. Casper, Stephen, Xander Davies, Claudia Shi, Thomas Krendl G… [find](https://scholar.google.com/scholar?q=Carroll%2C+Micah%2C+Rohin+Shah%2C+Mark+K%2E+Ho%2C+Tom+Griffiths%2C+Sanjit+Seshia%2C+Pieter+Abbeel%2C+and+Anca+Dragan%2E+2019%2E+On+the+utility+of+learning+about+humans+for+human%2DAI+coordination%2E+In+Advances+in+Neural+Inf)
8. Chen, Daiwei, Yi Chen, Aniket Rege, and Ramya Korlakai Vinayak. 2024. PAL: Pluralistic alignment framework for learning from heterogeneous preferences. CoRR, abs/2406.08469. — [arXiv:2406.08469](https://arxiv.org/abs/2406.08469) [find](https://scholar.google.com/scholar?q=Chen%2C+Daiwei%2C+Yi+Chen%2C+Aniket+Rege%2C+and+Ramya+Korlakai+Vinayak%2E+2024%2E+PAL%3A+Pluralistic+alignment+framework+for+learning+from+heterogeneous+preferences%2E+CoRR%2C+abs%2F2406%2E08469%2E+%E2%80%94+%5BarXiv%3A2406%2E08469%5D%28https)
9. Chen, Liang, Yichi Zhang, Shuhuai Ren, Haozhe Zhao, Zefan Cai, Yuchi Wang, Peiyi Wang, Tianyu Liu, and Baobao Chang. 2023. Towards end-to-end embodied decision making via multi-modal large language model: Explorations with GPT4-vision and beyond. CoRR, abs/2310.02071. — [arXiv:2310.02071](https://arxiv.org/abs/2310.02071) [find](https://scholar.google.com/scholar?q=Chen%2C+Liang%2C+Yichi+Zhang%2C+Shuhuai+Ren%2C+Haozhe+Zhao%2C+Zefan+Cai%2C+Yuchi+Wang%2C+Peiyi+Wang%2C+Tianyu+Liu%2C+and+Baobao+Chang%2E+2023%2E+Towards+end%2Dto%2Dend+embodied+decision+making+via+multi%2Dmodal+large+language+mo)
10. Christiano, Paul, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017. Deep reinforcement learning from human preferences. In Advances in Neural Information Processing Systems (NIPS), volume 30. [find](https://scholar.google.com/scholar?q=Christiano%2C+Paul%2C+Jan+Leike%2C+Tom+Brown%2C+Miljan+Martic%2C+Shane+Legg%2C+and+Dario+Amodei%2E+2017%2E+Deep+reinforcement+learning+from+human+preferences%2E+In+Advances+in+Neural+Information+Processing+Systems+%28NIP)
11. Co-Reyes, John D., Abhishek Gupta, Suvansh Sanjeev, Nick Altieri, John DeNero, Pieter Abbeel, and Sergey Levine. 2019. Meta-learning language-guided policy learning. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Co%2DReyes%2C+John+D%2E%2C+Abhishek+Gupta%2C+Suvansh+Sanjeev%2C+Nick+Altieri%2C+John+DeNero%2C+Pieter+Abbeel%2C+and+Sergey+Levine%2E+2019%2E+Meta%2Dlearning+language%2Dguided+policy+learning%2E+In+International+Conference+on+Lea)
12. Cobbe, Karl, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, et al. 2021. [Training verifiers to solve math word problems](https://md.research.elamur.ai/free/en/papers/cobbe-2021-training-verifiers-solve-math-word/). CoRR, abs/2110.14168.
13. De Peuter, Sebastiaan, Antti Oulasvirta, and Samuel Kaski. 2023. Toward AI assistants that let designers design. AI Magazine, 44(1):85–96. https://doi.org/10 .1002/aaai.12077 DeepSeek-AI, et al. 2025. [DeepSeek-R1: Incentivizing Reasoning capability in LLMs via reinforcement learning](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/). CoRR, abs/2501.…
14. Dejong, Gerald and Raymond Mooney. 1986. Explanation-based learning: An alternative view. Machine Learning, 1(2):145–176. https://doi.org/10.1023/A :1022898111663 Dutta, Subhabrata, Ishan Pandey, Joykirat Singh, Sunny Manchanda, Soumen Chakrabarti, and Tanmoy Chakraborty. 2024. Frugal LMs trained to… [find](https://scholar.google.com/scholar?q=Dejong%2C+Gerald+and+Raymond+Mooney%2E+1986%2E+Explanation%2Dbased+learning%3A+An+alternative+view%2E+Machine+Learning%2C+1%282%29%3A145%E2%80%93176%2E+https%3A%2F%2Fdoi%2Eorg%2F10%2E1023%2FA+%3A1022898111663+Dutta%2C+Subhabrata%2C+Ishan+Pandey%2C+Joyk)
15. Fu, Justin, Anoop Korattikara, Sergey Levine, and Sergio Guadarrama. 2019. From language to goals: Inverse reinforcement learning for vision-based instruction following. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Fu%2C+Justin%2C+Anoop+Korattikara%2C+Sergey+Levine%2C+and+Sergio+Guadarrama%2E+2019%2E+From+language+to+goals%3A+Inverse+reinforcement+learning+for+vision%2Dbased+instruction+following%2E+In+International+Conference+on)
16. Ganesh, Sumitra, Leo Ardon, Daniel Borrajo, Deepeka Garg, Udari Madhushani Sehwag, Annapoorani Lakshmi Narayanan, Giuseppe Canonaco, and Manuela M. Veloso. 2024. Generative AI agents for knowledge work augmentation in finance. Annual Review of Control, Robotics, and Autonomous Systems, 8. https://do… — [doi:10.1146/annurev](https://doi.org/10.1146/annurev) [find](https://scholar.google.com/scholar?q=Ganesh%2C+Sumitra%2C+Leo+Ardon%2C+Daniel+Borrajo%2C+Deepeka+Garg%2C+Udari+Madhushani+Sehwag%2C+Annapoorani+Lakshmi+Narayanan%2C+Giuseppe+Canonaco%2C+and+Manuela+M%2E+Veloso%2E+2024%2E+Generative+AI+agents+for+knowledge+wor)
17. Gehring, Jonas, Kunhao Zheng, Jade Copet, Vegard Mella, Taco Cohen, and Gabriel Synnaeve. 2024. [RLEF: Grounding code LLMs in execution feedback with reinforcement learning](https://md.research.elamur.ai/free/en/papers/gehring-2024-rlef-grounding-code-llms-execution/). CoRR, abs/2410.02089.
18. Grabisch, M., J. L. Marichal, R. Mesiar, and E. Pap. 2009. Aggregation Functions. Cambridge University Press. https://doi.org/10.1017/CBO9781139644150 Guo, Yangyang, Zhiyong Cheng, Liqiang Nie, Xin-Shun Xu, and Mohan Kankanhalli. 2018. Multi-modal preference modeling for product search. In Proceedi… — [doi:10.1017/cbo9781139644150](https://doi.org/10.1017/cbo9781139644150) [↗](https://doi.org/10.1017/CBO9781139644150)
19. Hager, Paul, Friederike Jungmann, Robbie Holland, Kunal Bhagat, Inga Hubrecht, Manuel Knauer, Jakob Vielhauer, Marcus Makowski, Rickmer Braren, Georgios Kaissis, and Daniel Rueckert. 2024. Evaluation and mitigation of the limitations of large language models in clinical decision-making. Nature Medic… — [doi:10.1038/s41591-024-03097-1](https://doi.org/10.1038/s41591-024-03097-1) [find](https://scholar.google.com/scholar?q=Hager%2C+Paul%2C+Friederike+Jungmann%2C+Robbie+Holland%2C+Kunal+Bhagat%2C+Inga+Hubrecht%2C+Manuel+Knauer%2C+Jakob+Vielhauer%2C+Marcus+Makowski%2C+Rickmer+Braren%2C+Georgios+Kaissis%2C+and+Daniel+Rueckert%2E+2024%2E+Evaluation+)
20. Hong, Joey, Sergey Levine, and Anca Dragan. 2023. [Learning to influence human behavior with offline reinforcement learning](https://md.research.elamur.ai/free/en/papers/hong-2023-metagpt-meta-programming-multi/). Advances in Neural Information Processing Systems, 36:36094–36105. Hong, Sirui, Mingchen Zhuge, Jonathan Chen, Xiawu Zheng, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, S…
21. Hu, Yue and Xiaojun Wan. 2014. Automatic generation of related work sections in scientific papers: An optimization approach. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1624–1633. https://doi.org/10.3115/v1/D14-1170 Hüllermeier, Eyke and… [↗](https://doi.org/10.3115/v1/D14-1170)
22. Jiang, Juyong, Fan Wang, Jiasi Shen, Sungju Kim, and Sunghun Kim. 2024. [A survey on large language models for code generation](https://md.research.elamur.ai/free/en/papers/jiang-2024-survey-large-language-models-code/). CoRR, abs/2406.00515.
23. Jin, Chi, Akshay Krishnamurthy, Max Simchowitz, and Tiancheng Yu. 2020. Reward-free exploration for reinforcement learning. In International Conference on Machine Learning, pages 4870–4879. [find](https://scholar.google.com/scholar?q=Jin%2C+Chi%2C+Akshay+Krishnamurthy%2C+Max+Simchowitz%2C+and+Tiancheng+Yu%2E+2020%2E+Reward%2Dfree+exploration+for+reinforcement+learning%2E+In+International+Conference+on+Machine+Learning%2C+pages+4870%E2%80%934879%2E)
24. Juneja, Gurusha, Subhabrata Dutta, and Tanmoy Chakraborty. 2024. LM2: A simple society of language models solves complex reasoning. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 16473–16484. https://doi.org/10.18653/v1/2024.emnlp-main.920 Kambhampa… [↗](https://doi.org/10.18653/v1/2024.emnlp-main.920)
25. Krishnamurthy, Akshay, Keegan Harris, Dylan J. Foster, Cyril Zhang, and Aleksandrs Slivkins. 2024. Can large language models explore in-context? CoRR, abs/2403.15371. — [arXiv:2403.15371](https://arxiv.org/abs/2403.15371) [find](https://scholar.google.com/scholar?q=Krishnamurthy%2C+Akshay%2C+Keegan+Harris%2C+Dylan+J%2E+Foster%2C+Cyril+Zhang%2C+and+Aleksandrs+Slivkins%2E+2024%2E+Can+large+language+models+explore+in%2Dcontext%3F+CoRR%2C+abs%2F2403%2E15371%2E+%E2%80%94+%5BarXiv%3A2403%2E15371%5D%28https%3A%2F%2Farxi)
26. Laidlaw, Cassidy, Eli Bronstein, Timothy Guo, Dylan Feng, Lukas Berglund, Justin Svegliato, Stuart Russell, and Anca Dragan. 2024. Scalably solving assistance games. In ICML 2024 Workshop on Models of Human Feedback for AI Alignment. [find](https://scholar.google.com/scholar?q=Laidlaw%2C+Cassidy%2C+Eli+Bronstein%2C+Timothy+Guo%2C+Dylan+Feng%2C+Lukas+Berglund%2C+Justin+Svegliato%2C+Stuart+Russell%2C+and+Anca+Dragan%2E+2024%2E+Scalably+solving+assistance+games%2E+In+ICML+2024+Workshop+on+Models+of)
27. Le, Hung, Hailin Chen, Amrita Saha, Akash Gokul, Doyen Sahoo, and Shafiq Joty. 2024. CodeChain: Towards modular code generation through chain of self-revisions with representative sub-modules. In the Twelfth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Le%2C+Hung%2C+Hailin+Chen%2C+Amrita+Saha%2C+Akash+Gokul%2C+Doyen+Sahoo%2C+and+Shafiq+Joty%2E+2024%2E+CodeChain%3A+Towards+modular+code+generation+through+chain+of+self%2Drevisions+with+representative+sub%2Dmodules%2E+In+the+)
28. Le, Hung, Yue Wang, Akhilesh Deepak Gotmare, Silvio Savarese, and Steven Chu-Hong Hoi. 2022. [CodeRL: Mastering code generation through pretrained models and deep reinforcement learning](https://md.research.elamur.ai/free/en/papers/le-2022-coderl-mastering-code-generation-through/). In Advances in Neural Information Processing Systems, volume 35. Lecler, Augustin, Loı̈c Duron, and Philippe Soyer…
29. Lee, Kuang-Huei, Ian Fischer, Yueh-Hua Wu, Dave Marwood, Shumeet Baluja, Dale Schuurmans, and Xinyun Chen. 2025. Evolving deeper LLM thinking. CoRR, abs/2501.09891. [find](https://scholar.google.com/scholar?q=Lee%2C+Kuang%2DHuei%2C+Ian+Fischer%2C+Yueh%2DHua+Wu%2C+Dave+Marwood%2C+Shumeet+Baluja%2C+Dale+Schuurmans%2C+and+Xinyun+Chen%2E+2025%2E+Evolving+deeper+LLM+thinking%2E+CoRR%2C+abs%2F2501%2E09891%2E)
30. Li, Ao, Yuexiang Xie, Songze Li, Fugee Tsung, Bolin Ding, and Yaliang Li. 2025. Agent-oriented planning in multi-agent systems. In the Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Li%2C+Ao%2C+Yuexiang+Xie%2C+Songze+Li%2C+Fugee+Tsung%2C+Bolin+Ding%2C+and+Yaliang+Li%2E+2025%2E+Agent%2Doriented+planning+in+multi%2Dagent+systems%2E+In+the+Thirteenth+International+Conference+on+Learning+Representations%2E)
31. Li, Belinda Z., Alex Tamkin, Noah D. Goodman, and Jacob Andreas. 2023a. Eliciting human preferences with language models. CoRR, abs/2310.11589. [find](https://scholar.google.com/scholar?q=Li%2C+Belinda+Z%2E%2C+Alex+Tamkin%2C+Noah+D%2E+Goodman%2C+and+Jacob+Andreas%2E+2023a%2E+Eliciting+human+preferences+with+language+models%2E+CoRR%2C+abs%2F2310%2E11589%2E)
32. Li, Chunyuan, Zhe Gan, Zhengyuan Yang, Jianwei Yang, Linjie Li, Lijuan Wang, and Jianfeng Gao. 2024a. [Multimodal foundation models: From specialists to general-purpose assistants](https://md.research.elamur.ai/free/en/papers/li-2023-camel-communicative-agents-mind/). Foundations and Trends in Computer Graphics and Vision, 16(1–2):1–214. https://doi.org/10.1561/0600000110 Li, Guohao, H… [↗](https://doi.org/10.1561/0600000110)
33. Li, Qintong, Leyang Cui, Xueliang Zhao, Lingpeng Kong, and Wei Bi. 2024b. [GSM-plus: A comprehensive benchmark for evaluating the robustness of LLMs as mathematical problem solvers](https://md.research.elamur.ai/free/en/papers/li-2024-gsm-plus-comprehensive-benchmark-evaluating/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pag…
34. Lin, Jessy, Daniel Fried, Dan Klein, and Anca Dragan. 2022. Inferring rewards from language in context. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8546–8560. https://doi.org/10.18653/v1/2022.acl-long.585 [↗](https://doi.org/10.18653/v1/2022.acl-long.585)
35. Liu, Jiate, Yiqin Zhu, Kaiwen Xiao, Qiang Fu, Xiao Han, Yang Wei, and Deheng Ye. 2023. RLTF: Reinforcement learning from unit test feedback. Transactions on Machine Learning Research. [find](https://scholar.google.com/scholar?q=Liu%2C+Jiate%2C+Yiqin+Zhu%2C+Kaiwen+Xiao%2C+Qiang+Fu%2C+Xiao+Han%2C+Yang+Wei%2C+and+Deheng+Ye%2E+2023%2E+RLTF%3A+Reinforcement+learning+from+unit+test+feedback%2E+Transactions+on+Machine+Learning+Research%2E)
36. Liu, Nelson F., Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, and Percy Liang. 2024. [Lost in the middle: How language models use long contexts](https://md.research.elamur.ai/free/en/papers/liu-2023-lost-middle-language-models-use/). Transactions of the Association for Computational Linguistics, 12:157–173. https://doi.org/10.1162/tacl a 00638 Maclin, Rich… [↗](https://doi.org/10.1162/tacl)
37. Magesh, Varun, Faiz Surani, Matthew Dahl, Mirac Suzgun, Christopher D. Manning, and Daniel E. Ho. 2024. [Hallucination-free? Assessing the reliability of leading AI legal research tools](https://md.research.elamur.ai/free/en/papers/magesh-2024-hallucination-free-assessing-reliability-leading/). CoRR, abs/2405.20362.
38. Maninger, Daniel, Krishna Narasimhan, and Mira Mezini. 2024. Towards trustworthy AI software development assistance. In Proceedings of the 2024 ACM/IEEE 44th International Conference on Software Engineering: New Ideas and Emerging Results, pages 112–116. https://doi.org/10.1145/3639476.3639770 Mao,… — [doi:10.1145/3639476.3639770](https://doi.org/10.1145/3639476.3639770) [↗](https://doi.org/10.1145/3639476.3639770)
39. McAleese, Nat, Rai Michael Pokorny, Juan Felipe Ceron Uribe, Evgenia Nitishinskaya, Maja Trebacz, and Jan Leike. 2024. LLM critics help catch LLM bugs. CoRR, abs/2407.00215. — [arXiv:2407.00215](https://arxiv.org/abs/2407.00215) [find](https://scholar.google.com/scholar?q=McAleese%2C+Nat%2C+Rai+Michael+Pokorny%2C+Juan+Felipe+Ceron+Uribe%2C+Evgenia+Nitishinskaya%2C+Maja+Trebacz%2C+and+Jan+Leike%2E+2024%2E+LLM+critics+help+catch+LLM+bugs%2E+CoRR%2C+abs%2F2407%2E00215%2E+%E2%80%94+%5BarXiv%3A2407%2E00215%5D%28https)
40. McCarthy, John. 1959. Programs with common sense. In Proceedings of the Teddington Conference on the Mechanization of Thought Processes, pages 75–91. [find](https://scholar.google.com/scholar?q=McCarthy%2C+John%2E+1959%2E+Programs+with+common+sense%2E+In+Proceedings+of+the+Teddington+Conference+on+the+Mechanization+of+Thought+Processes%2C+pages+75%E2%80%9391%2E)
41. Miehling, Erik, Karthikeyan Natesan Ramamurthy, Kush R. Varshney, Matthew Riemer, Djallel Bouneffouf, John T. Richards, Amit Dhurandhar, Elizabeth M. Daly, Michael Hind, Prasanna Sattigeri, et al. 2025. Agentic AI needs a systems theory. CoRR, abs/2503.00237. Modarressi, Ali, Abdullatif Köksal, Ayy… [find](https://scholar.google.com/scholar?q=Miehling%2C+Erik%2C+Karthikeyan+Natesan+Ramamurthy%2C+Kush+R%2E+Varshney%2C+Matthew+Riemer%2C+Djallel+Bouneffouf%2C+John+T%2E+Richards%2C+Amit+Dhurandhar%2C+Elizabeth+M%2E+Daly%2C+Michael+Hind%2C+Prasanna+Sattigeri%2C+et+al%2E+202)
42. OpenAI et al. 2024. [OpenAI o1 System Card](https://md.research.elamur.ai/free/en/papers/openai-2024-openai-o1-system-card/). CoRR, abs/2412.16720.
43. Ouyang, Long, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022. [Training language models to follow instructions with human feedback](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/). In Advances in Neural Information Processing Systems (NeurIPS), volume 35.
44. Peng, Andi, Andreea Bobu, Belinda Z. Li, Theodore R. Sumers, Ilia Sucholutsky, Nishanth Kumar, Thomas L. Griffiths, and Julie A. Shah. 2024. Preference-conditioned language-guided abstraction. In Proceedings of the 2024 ACM/IEEE International Conference on Human-Robot Interaction, pages 572–581. htt… — [doi:10.1145/3610977](https://doi.org/10.1145/3610977) [find](https://scholar.google.com/scholar?q=Peng%2C+Andi%2C+Andreea+Bobu%2C+Belinda+Z%2E+Li%2C+Theodore+R%2E+Sumers%2C+Ilia+Sucholutsky%2C+Nishanth+Kumar%2C+Thomas+L%2E+Griffiths%2C+and+Julie+A%2E+Shah%2E+2024%2E+Preference%2Dconditioned+language%2Dguided+abstraction%2E+In+Proc)
45. Phan, Huy Nhat, Phong X. Nguyen, and Nghi D. Q. Bui. 2024. Hyperagent: Generalist software engineering agents to solve coding tasks at scale. CoRR, abs/2409.16299. — [arXiv:2409.16299](https://arxiv.org/abs/2409.16299) [find](https://scholar.google.com/scholar?q=Phan%2C+Huy+Nhat%2C+Phong+X%2E+Nguyen%2C+and+Nghi+D%2E+Q%2E+Bui%2E+2024%2E+Hyperagent%3A+Generalist+software+engineering+agents+to+solve+coding+tasks+at+scale%2E+CoRR%2C+abs%2F2409%2E16299%2E+%E2%80%94+%5BarXiv%3A2409%2E16299%5D%28https%3A%2F%2Farxiv%2Eo)
46. Qian, Chen, Wei Liu, Hongzhang Liu, Nuo Chen, Yufan Dang, Jiahao Li, Cheng Yang, Weize Chen, Yusheng Su, Xin Cong, et al. 2024. [ChatDev: Communicative agents for software development](https://md.research.elamur.ai/free/en/papers/qian-2023-chatdev-communicative-agents-software/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers),…
47. Robertson, Jeandri, Caitlin Ferreira, Elsamari Botha, and Kim Oosthuizen. 2024. Game changers: A generative AI prompt protocol to enhance human-AI knowledge co-construction. Business Horizons, 67(5):499–510. https://doi.org/10.1016/j.bushor.2024.04.008 Ross, Andrew Slavin, Michael C. Hughes, and Fi… — [doi:10.1016/j.bushor.2024.04.008](https://doi.org/10.1016/j.bushor.2024.04.008) [↗](https://doi.org/10.1016/j.bushor.2024.04.008)
48. Shah, Nihar, Sivaraman Balakrishnan, Aditya Guntuboyina, and Martin Wainwright. 2016. Stochastically transitive models for pairwise comparisons: Statistical and computational issues. In Proceedings of the 33rd International Conference on Machine Learning, volume 48 of Proceedings of Machine Learning… [find](https://scholar.google.com/scholar?q=Shah%2C+Nihar%2C+Sivaraman+Balakrishnan%2C+Aditya+Guntuboyina%2C+and+Martin+Wainwright%2E+2016%2E+Stochastically+transitive+models+for+pairwise+comparisons%3A+Statistical+and+computational+issues%2E+In+Proceedings+of)
49. Shah, Rohin, Pedro Freire, Neel Alex, Rachel Freedman, Dmitrii Krasheninnikov, Lawrence Chan, Michael D. Dennis, Pieter Abbeel, Anca Dragan, and Stuart Russell. 2021. Benefits of assistance over reward learning. [https://api.semanticscholar.org/CorpusID:235416203](https://api.semanticscholar.org/CorpusID:235416203) Simkute, Auste, Lev Tankelevitch, Vi… — [arXiv:2402.11364](https://arxiv.org/abs/2402.11364) [↗](https://api.semanticscholar.org/CorpusID:235416203)
50. Song, Tao, Man Luo, Xiaolong Zhang, Linjiang Chen, Yan Huang, Jiaqi Cao, Qing Zhu, Daobin Liu, Baicheng Zhang, Gang Zou, et al. 2025. [A multiagent-driven robotic AI chemist enabling autonomous chemical research on demand](https://md.research.elamur.ai/free/en/papers/sprague-2024-cot-cot-chain-thought-helps/). Journal of the American Chemical Society, 147(15):12534–12545. https://doi .or…
51. Stiennon, Nisan, Long Ouyang, Jeffrey Wu, Daniel Ziegler, Ryan Lowe, Chelsea Voss, Alec Radford, Dario Amodei, and Paul F. Christiano. 2020. Learning to summarize with human feedback. In Advances in Neural Information Processing Systems (NeurIPS), volume 33. [find](https://scholar.google.com/scholar?q=Stiennon%2C+Nisan%2C+Long+Ouyang%2C+Jeffrey+Wu%2C+Daniel+Ziegler%2C+Ryan+Lowe%2C+Chelsea+Voss%2C+Alec+Radford%2C+Dario+Amodei%2C+and+Paul+F%2E+Christiano%2E+2020%2E+Learning+to+summarize+with+human+feedback%2E+In+Advances+in+N)
52. Sumers, Theodore, Robert Hawkins, Mark K. Ho, Tom Griffiths, and Dylan Hadfield-Menell. 2022. How to talk so AI will learn: Instructions, descriptions, and autonomy. In Advances in Neural Information Processing Systems, volume 35, pages 34762–34775. [find](https://scholar.google.com/scholar?q=Sumers%2C+Theodore%2C+Robert+Hawkins%2C+Mark+K%2E+Ho%2C+Tom+Griffiths%2C+and+Dylan+Hadfield%2DMenell%2E+2022%2E+How+to+talk+so+AI+will+learn%3A+Instructions%2C+descriptions%2C+and+autonomy%2E+In+Advances+in+Neural+Information+)
53. Sumers, Theodore, Shunyu Yao, Karthik Narasimhan, and Thomas Griffiths. 2024. Cognitive architectures for language agents. Transactions on Machine Learning Research. arXiv:2309.02427. [find](https://scholar.google.com/scholar?q=Sumers%2C+Theodore%2C+Shunyu+Yao%2C+Karthik+Narasimhan%2C+and+Thomas+Griffiths%2E+2024%2E+Cognitive+architectures+for+language+agents%2E+Transactions+on+Machine+Learning+Research%2E+arXiv%3A2309%2E02427%2E)
54. Sumers, Theodore R., Mark K. Ho, Robert D. Hawkins, Karthik Narasimhan, and Thomas L. Griffiths. 2021. Learning rewards from linguistic feedback. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 6002–6010. https://doi.org/10.1609/aaai.v35i7.16749 Takagi, H. 2001. I… — [doi:10.1609/aaai.v35i7.16749](https://doi.org/10.1609/aaai.v35i7.16749) [↗](https://doi.org/10.1609/aaai.v35i7.16749)
55. Towell, Geoffrey G. and Jude W. Shavlik. 1994. Knowledge-based artificial neural networks. Artificial Intelligence, 70(1):119–165. [https://doi.org](https://doi.org) /10.1016/0004-3702(94)90105-8 Vaccaro, Michelle, Abdullah Almaatouq, and Thomas Malone. 2024. When combinations of humans and AI are useful: A systematic… — [doi:10.1016/0004-3702(94)90105-8](https://doi.org/10.1016/0004-3702%2894%2990105-8) [↗](https://doi.org)
56. Wang, Lei, Chen Ma, Xueyang Feng, Zeyu Zhang, Hao Yang, Jingsen Zhang, Zhiyuan Chen, Jiakai Tang, Xu Chen, Yankai Lin, et al. 2024. [A survey on large language model based autonomous agents](https://md.research.elamur.ai/free/en/papers/wang-2023-survey-large-language-model-based/). Frontiers of Computer Science, 18(6). https://doi.org/10.1007/s11704-024-40231-1 Wang, Xuezhi, Jason Wei, Dal… [↗](https://doi.org/10.1007/s11704-024-40231-1)
57. Wang, Yanan and Yan Pei. 2024. A comprehensive survey on interactive evolutionary computation in the first two decades of the 21st century. Applied Soft Computing, page 111950. https://doi.org/10.1016/j.asoc.2024.111950 Wei, Jason, Maarten Bosma, Vincent Y. Zhao, Kelvin Guu, Adams Wei Yu, Brian Les… — [doi:10.1016/j.asoc.2024.111950](https://doi.org/10.1016/j.asoc.2024.111950) [↗](https://doi.org/10.1016/j.asoc.2024.111950)
58. Wei, Jason, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. 2022b. [Chain-of-thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). In Proceedings of the 36th International Conference on Neural Information Processing Systems.
59. Xie, Jian, Kai Zhang, Jiangjie Chen, Tinghui Zhu, Renze Lou, Yuandong Tian, Yanghua Xiao, and Yu Su. 2024. TravelPlanner: A benchmark for real-world planning with language agents. In Proceedings of the 41st International Conference on Machine Learning, volume 235 of Proceedings of Machine Learning R… [find](https://scholar.google.com/scholar?q=Xie%2C+Jian%2C+Kai+Zhang%2C+Jiangjie+Chen%2C+Tinghui+Zhu%2C+Renze+Lou%2C+Yuandong+Tian%2C+Yanghua+Xiao%2C+and+Yu+Su%2E+2024%2E+TravelPlanner%3A+A+benchmark+for+real%2Dworld+planning+with+language+agents%2E+In+Proceedings+of+th)
60. Xu, Cai, Ziyu Guan, Wei Zhao, Quanzhou Wu, Meng Yan, Long Chen, and Qiguang Miao. 2021. Recommendation by users’ multimodal preferences for smart city applications. IEEE Transactions on Industrial Informatics, 17(6):4197–4205. https://doi.org/10.1109/TII.2020.3008923 Xu, Frank F., Bogdan Vasilescu,… [↗](https://doi.org/10.1109/TII.2020.3008923)
61. Yao, Shunyu, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. 2023. Tree of thoughts: Deliberate problem solving with large language models. In Advances in Neural Information Processing Systems, volume 36. [find](https://scholar.google.com/scholar?q=Yao%2C+Shunyu%2C+Dian+Yu%2C+Jeffrey+Zhao%2C+Izhak+Shafran%2C+Tom+Griffiths%2C+Yuan+Cao%2C+and+Karthik+Narasimhan%2E+2023%2E+Tree+of+thoughts%3A+Deliberate+problem+solving+with+large+language+models%2E+In+Advances+in+Neural)
62. Zhou, Yifei, Andrea Zanette, Jiayi Pan, Sergey Levine, and Aviral Kumar. 2024. ArCHer: Training language model agents via hierarchical multi-turn RL. In Proceedings of the 41st International Conference on Machine Learning, volume 235 of Proceedings of Machine Learning Research, pages 62178–62209. [find](https://scholar.google.com/scholar?q=Zhou%2C+Yifei%2C+Andrea+Zanette%2C+Jiayi+Pan%2C+Sergey+Levine%2C+and+Aviral+Kumar%2E+2024%2E+ArCHer%3A+Training+language+model+agents+via+hierarchical+multi%2Dturn+RL%2E+In+Proceedings+of+the+41st+International+Conferenc)

*Updated 30 October 2026*