---
title: "CAMO — paper by Yu et al. (2026) — summary and ideas"
description: "Simulations driven by LLM agents often display emergent social phenomena such as coordination or polarization. 57 references."
authors: ["Xiangning Yu", "Yuwei Guo", "Yuqi Hou", "Xiao Xue", "Qun Ma"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.1224/"
doi: "10.18653/v1/2026.findings-acl.1224"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/yu-2026-camo-agentic-framework-automated-causal/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yu-2026-camo-agentic-framework-automated-causal/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/26/) / CAMO: An Agentic Framework for Automated Causal Discovery from Micro Behaviors to Macro Emergence in LLM Agent Simulations

# CAMO: An Agentic Framework for Automated Causal Discovery from Micro Behaviors to Macro Emergence in LLM Agent Simulations

**Authors:** Xiangning Yu, Yuwei Guo, Yuqi Hou, Xiao Xue and Qun Ma · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.1224/) · [PDF](https://aclanthology.org/2026.findings-acl.1224.pdf) · [DOI 10.18653/v1/2026.findings-acl.1224](https://doi.org/10.18653/v1/2026.findings-acl.1224) · [OpenAlex](https://openalex.org/W7166834594)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Simulations driven by LLM agents often display emergent social phenomena such as coordination or polarization. They rarely reveal *why* these outcomes arise, so interventions remain guesswork. CAMO addresses this with an agentic framework that recovers micro-to-macro causal mechanisms behind a chosen emergent target Y. It does not attempt the full causal graph. Instead, it learns two things:

- a computable Markov boundary of Y over a factor space derived from simulation logs (ratios, rolling statistics, graph metrics);
- a minimal upstream explanatory subgraph linking micro- and meso-level causes to Y.

Five workflow LLM agents turn domain texts into competing causal hypotheses, add and prune factors by information gain, and run constrained causal discovery. Ambiguous edge directions are resolved through counterfactual runs inside the simulator. A fast loop refines the local graph, and a slow loop revises hypotheses when the evidence contradicts them.

The framework was tested on four emergent settings, with and without ground-truth graphs. It recovered structure more accurately than the baselines and ranked effective interventions better. This makes simulation-based studies of emergence more explainable and more useful for steering outcomes.

## Key points
- **Five agents:** Worldview Parser, Worldview Integrator, Causal Cartographer, Simulation Scriptwright and Counterfactual Adjudicator, coordinated by a fast–slow self-evolving loop.
- **Evaluation settings:** an O2O delivery simulation calibrated on real aggregate statistics, Smallville (coordination), and AgentSociety (opinion polarization and inflammatory message spread).
- **Intervention ranking without ground truth** (Random Walk with Restart from Y, DeepSeek-V3.2, averaged over 3 runs):
  - CAMO achieves the best Precision@5 and MAP@5 on all three tasks, e.g., MAP@5 of 0.84 on polarization.
  - Baselines include PC, MMHC, PAIRWISE, SCD (PC)+LLM and LLM-KBCI.
- **Ablation on O2O** (GPT-5 mini): full CAMO reaches MB-F1 0.80 and Anc-F1 0.90. Removing the worldview agents (A1 and A2) collapses Markov boundary recovery, with MB-F1 falling to 0.00.
- **Limitations:** results depend on LLM-derived priors and may suffer residual confounding from unlogged variables. Findings are scoped to the simulator, and repeated simulator queries create a budget–accuracy trade-off. Code is available at GitHub, RisingDate/CAMO.

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

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎯 Decision Sciences](https://md.research.elamur.ai/free/en/shelves/decision-sciences/) · 249 works · [🎯 Management Science and Operations Research](https://md.research.elamur.ai/free/en/shelves/decision-sciences/management-science-and-operations-research/) · 134 works

## Cite

Cite as: Xiangning Yu, Yuwei Guo, Yuqi Hou, Xiao Xue and Qun Ma. 2026. CAMO: An Agentic Framework for Automated Causal Discovery from Micro Behaviors to Macro Emergence in LLM Agent Simulations. Findings of the Association for Computational Linguistics: ACL 2026.

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

```bibtex
@inproceedings{yu2026camo,
  title = {{CAMO: An Agentic Framework for Automated Causal Discovery from Micro Behaviors to Macro Emergence in LLM Agent Simulations}},
  author = {Xiangning Yu, Yuwei Guo, Yuqi Hou, Xiao Xue and Qun Ma},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1224},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1224}
}
```

- [← previous CAMMAR: Culture-Aware Matryoshka for Metaphorical Arabic Representations](https://md.research.elamur.ai/free/en/papers/awinat-2026-cammar-culture-aware-matryoshka-metaphorical/)
- [next → Can a Remedy Find a Researcher? Exploring the Development of Semantic Knowledge in Italian BabyLMs](https://md.research.elamur.ai/free/en/papers/suozzi-2026-can-remedy-find-researcher-exploring/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/26/)

## References

57 references, 9 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Carlo Adornetto, Adrian Mora, Kai Hu, Leticia Izquierdo Garcia, Parfait Atchade-Adelomou, Gianluigi Greco, Luis Alberto Alonso Pastor, and Kent Larson. 2025. Generative agents in agent-based modeling: Overview, validation, and emerging challenges. IEEE Transactions on Artificial Intelligence. [find](https://scholar.google.com/scholar?q=Carlo+Adornetto%2C+Adrian+Mora%2C+Kai+Hu%2C+Leticia+Izquierdo+Garcia%2C+Parfait+Atchade%2DAdelomou%2C+Gianluigi+Greco%2C+Luis+Alberto+Alonso+Pastor%2C+and+Kent+Larson%2E+2025%2E+Generative+agents+in+agent%2Dbased+modeling%3A)
2. Amey Agrawal, Nitin Kedia, Jayashree Mohan, Ashish Panwar, Nipun Kwatra, Bhargav S Gulavani, Ramachandran Ramjee, and Alexey Tumanov. 2024. [Vidur: A large-scale simulation framework for llm inference](https://md.research.elamur.ai/free/en/papers/agrawal-2024-vidur-large-scale-simulation-framework/). Proceedings of Machine Learning and Systems, 6:351–366.
3. Jacy Reese Anthis, Ryan Liu, Sean M Richardson, Austin C Kozlowski, Bernard Koch, James Evans, Erik Brynjolfsson, and Michael Bernstein. 2025. Llm social simulations are a promising research method. arXiv preprint arXiv:2504.02234. — [arXiv:2504.02234](https://arxiv.org/abs/2504.02234) [find](https://scholar.google.com/scholar?q=Jacy+Reese+Anthis%2C+Ryan+Liu%2C+Sean+M+Richardson%2C+Austin+C+Kozlowski%2C+Bernard+Koch%2C+James+Evans%2C+Erik+Brynjolfsson%2C+and+Michael+Bernstein%2E+2025%2E+Llm+social+simulations+are+a+promising+research+method%2E+a)
4. Ariel Flint Ashery, Luca Maria Aiello, and Andrea Baronchelli. 2025. Emergent social conventions and collective bias in llm populations. Science Advances, 11(20):eadu9368. [find](https://scholar.google.com/scholar?q=Ariel+Flint+Ashery%2C+Luca+Maria+Aiello%2C+and+Andrea+Baronchelli%2E+2025%2E+Emergent+social+conventions+and+collective+bias+in+llm+populations%2E+Science+Advances%2C+11%2820%29%3Aeadu9368%2E)
5. Weize Chen, Yusheng Su, Jingwei Zuo, Cheng Yang, Chenfei Yuan, Chi-Min Chan, Heyang Yu, Yaxi Lu, Yi-Hsin Hung, Chen Qian, and 1 others. 2024. [Agentverse: Facilitating multi-agent collaboration and exploring emergent behaviors](https://md.research.elamur.ai/free/en/papers/chen-2023-agentverse-facilitating-multi-agent/). In ICLR.
6. Haoang Chi, He Li, Wenjing Yang, Feng Liu, Long Lan, Xiaoguang Ren, Tongliang Liu, and Bo Han. 2024. Unveiling causal reasoning in large language models: Reality or mirage? Advances in Neural Information Processing Systems, 37:96640–96670. [find](https://scholar.google.com/scholar?q=Haoang+Chi%2C+He+Li%2C+Wenjing+Yang%2C+Feng+Liu%2C+Long+Lan%2C+Xiaoguang+Ren%2C+Tongliang+Liu%2C+and+Bo+Han%2E+2024%2E+Unveiling+causal+reasoning+in+large+language+models%3A+Reality+or+mirage%3F+Advances+in+Neural+Informat)
7. David Maxwell Chickering. 2002. Optimal structure identification with greedy search. Journal of machine learning research, 3(Nov):507–554. [find](https://scholar.google.com/scholar?q=David+Maxwell+Chickering%2E+2002%2E+Optimal+structure+identification+with+greedy+search%2E+Journal+of+machine+learning+research%2C+3%28Nov%29%3A507%E2%80%93554%2E)
8. Yun-Shiuan Chuang, Agam Goyal, Nikunj Harlalka, Siddharth Suresh, Robert Hawkins, Sijia Yang, Dhavan Shah, Junjie Hu, and Timothy Rogers. 2024. Simulating opinion dynamics with networks of llm-based agents. In Findings of the association for computational linguistics: NAACL 2024, pages 3326–3346. [find](https://scholar.google.com/scholar?q=Yun%2DShiuan+Chuang%2C+Agam+Goyal%2C+Nikunj+Harlalka%2C+Siddharth+Suresh%2C+Robert+Hawkins%2C+Sijia+Yang%2C+Dhavan+Shah%2C+Junjie+Hu%2C+and+Timothy+Rogers%2E+2024%2E+Simulating+opinion+dynamics+with+networks+of+llm%2Dbased+a)
9. Gordon Dai, Weijia Zhang, Jinhan Li, Siqi Yang, Srihas Rao, Arthur Caetano, Misha Sra, and 1 others. 2024. Artificial leviathan: Exploring social evolution of llm agents through the lens of hobbesian social contract theory. arXiv preprint arXiv:2406.14373. — [arXiv:2406.14373](https://arxiv.org/abs/2406.14373) [find](https://scholar.google.com/scholar?q=Gordon+Dai%2C+Weijia+Zhang%2C+Jinhan+Li%2C+Siqi+Yang%2C+Srihas+Rao%2C+Arthur+Caetano%2C+Misha+Sra%2C+and+1+others%2E+2024%2E+Artificial+leviathan%3A+Exploring+social+evolution+of+llm+agents+through+the+lens+of+hobbesian+)
10. DeepSeek-AI. 2025a. [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/). Preprint, arXiv:2501.12948.
11. DeepSeek-AI. 2025b. [Deepseek-v3.2: Pushing the frontier of open large language models](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-v3-2-pushing/).
12. Mugariya Farooq, Shahad Hardan, Aigerim Zhumb-hayeva, Yujia Zheng, Preslav Nakov, and Kun Zhang. 2023. Understanding breast cancer survival: Using causality and language models on multi-omics data. arXiv preprint arXiv:2305.18410. — [arXiv:2305.18410](https://arxiv.org/abs/2305.18410) [find](https://scholar.google.com/scholar?q=Mugariya+Farooq%2C+Shahad+Hardan%2C+Aigerim+Zhumb%2Dhayeva%2C+Yujia+Zheng%2C+Preslav+Nakov%2C+and+Kun+Zhang%2E+2023%2E+Understanding+breast+cancer+survival%3A+Using+causality+and+language+models+on+multi%2Domics+data%2E+ar)
13. Tao Feng, Lizhen Qu, Niket Tandon, Zhuang Li, Xiaoxi Kang, and Gholamreza Haffari. 2024. On the reliability of large language models for causal discovery. arXiv preprint arXiv:2407.19638. [find](https://scholar.google.com/scholar?q=Tao+Feng%2C+Lizhen+Qu%2C+Niket+Tandon%2C+Zhuang+Li%2C+Xiaoxi+Kang%2C+and+Gholamreza+Haffari%2E+2024%2E+On+the+reliability+of+large+language+models+for+causal+discovery%2E+arXiv+preprint+arXiv%3A2407%2E19638%2E)
14. Chen Gao, Xiaochong Lan, Nian Li, Yuan Yuan, Jingtao Ding, Zhilun Zhou, Fengli Xu, and Yong Li. 2024. [Large language models empowered agent-based modeling and simulation: A survey and perspectives](https://md.research.elamur.ai/free/en/papers/gao-2023-large-language-models-empowered-agent/). Humanities and Social Sciences Communications, 11(1):1–24.
15. Taicheng Guo, Xiuying Chen, Yaqi Wang, Ruidi Chang, Shichao Pei, Nitesh V Chawla, Olaf Wiest, and Xiangliang Zhang. 2024. [Large language model based multi-agents: A survey of progress and challenges](https://md.research.elamur.ai/free/en/papers/guo-2024-large-language-model-based/). arXiv preprint arXiv:2402.01680.
16. Prateek Gupta, Qiankun Zhong, Hiromu Yakura, Thomas Eisenmann, and Iyad Rahwan. 2025. The role of social learning and collective norm formation in fostering cooperation in llm multi-agent systems. arXiv preprint arXiv:2510.14401. — [arXiv:2510.14401](https://arxiv.org/abs/2510.14401) [find](https://scholar.google.com/scholar?q=Prateek+Gupta%2C+Qiankun+Zhong%2C+Hiromu+Yakura%2C+Thomas+Eisenmann%2C+and+Iyad+Rahwan%2E+2025%2E+The+role+of+social+learning+and+collective+norm+formation+in+fostering+cooperation+in+llm+multi%2Dagent+systems%2E+arX)
17. Elahe Khatibi, Mahyar Abbasian, Zhongqi Yang, Iman Azimi, and Amir M. Rahmani. 2025. Alcm: Autonomous llm-augmented causal discovery framework. Preprint, arXiv:2405.01744. — [arXiv:2405.01744](https://arxiv.org/abs/2405.01744) [find](https://scholar.google.com/scholar?q=Elahe+Khatibi%2C+Mahyar+Abbasian%2C+Zhongqi+Yang%2C+Iman+Azimi%2C+and+Amir+M%2E+Rahmani%2E+2025%2E+Alcm%3A+Autonomous+llm%2Daugmented+causal+discovery+framework%2E+Preprint%2C+arXiv%3A2405%2E01744%2E+%E2%80%94+%5BarXiv%3A2405%2E01744%5D%28https%3A%2F)
18. Emre Kiciman, Robert Ness, Amit Sharma, and Chenhao Tan. 2023. Causal reasoning and large language models: Opening a new frontier for causality. Transactions on Machine Learning Research. [find](https://scholar.google.com/scholar?q=Emre+Kiciman%2C+Robert+Ness%2C+Amit+Sharma%2C+and+Chenhao+Tan%2E+2023%2E+Causal+reasoning+and+large+language+models%3A+Opening+a+new+frontier+for+causality%2E+Transactions+on+Machine+Learning+Research%2E)
19. Daphne Koller and Nir Friedman. 2009. Probabilistic graphical models: principles and techniques. MIT press. [find](https://scholar.google.com/scholar?q=Daphne+Koller+and+Nir+Friedman%2E+2009%2E+Probabilistic+graphical+models%3A+principles+and+techniques%2E+MIT+press%2E)
20. Hao Duong Le, Xin Xia, and Zhang Chen. 2024. Multi-agent causal discovery using large language models. arXiv preprint arXiv:2407.15073. — [arXiv:2407.15073](https://arxiv.org/abs/2407.15073) [find](https://scholar.google.com/scholar?q=Hao+Duong+Le%2C+Xin+Xia%2C+and+Zhang+Chen%2E+2024%2E+Multi%2Dagent+causal+discovery+using+large+language+models%2E+arXiv+preprint+arXiv%3A2407%2E15073%2E+%E2%80%94+%5BarXiv%3A2407%2E15073%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2407%2E15073%29)
21. Chenxi Liu, Yongqiang Chen, Tongliang Liu, Mingming Gong, James Cheng, Bo Han, and Kun Zhang. 2024. Discovery of the hidden world with large language models. Advances in Neural Information Processing Systems, 37:102307–102365. [find](https://scholar.google.com/scholar?q=Chenxi+Liu%2C+Yongqiang+Chen%2C+Tongliang+Liu%2C+Mingming+Gong%2C+James+Cheng%2C+Bo+Han%2C+and+Kun+Zhang%2E+2024%2E+Discovery+of+the+hidden+world+with+large+language+models%2E+Advances+in+Neural+Information+Processing+)
22. Xiaoyu Liu, Paiheng Xu, Junda Wu, Jiaxin Yuan, Yifan Yang, Yuhang Zhou, Fuxiao Liu, Tianrui Guan, Haoliang Wang, Tong Yu, and 1 others. 2025. Large language models and causal inference in collaboration: A comprehensive survey. Findings of the Association for Computational Linguistics: NAACL 2025, pa… [find](https://scholar.google.com/scholar?q=Xiaoyu+Liu%2C+Paiheng+Xu%2C+Junda+Wu%2C+Jiaxin+Yuan%2C+Yifan+Yang%2C+Yuhang+Zhou%2C+Fuxiao+Liu%2C+Tianrui+Guan%2C+Haoliang+Wang%2C+Tong+Yu%2C+and+1+others%2E+2025%2E+Large+language+models+and+causal+inference+in+collaboratio)
23. Yuren Mao, Peigen Liu, Xinjian Wang, Rui Ding, Jing Miao, Hui Zou, Mingjie Qi, Wanxiang Luo, Longbin Lai, Kai Wang, Zhengping Qian, Peilun Yang, Yunjun Gao, and Ying Zhang. 2025. Agent-kernel: A microkernel multi-agent system framework for adaptive social simulation powered by llms. Preprint, arXiv:… — [arXiv:2512.01610](https://arxiv.org/abs/2512.01610) [find](https://scholar.google.com/scholar?q=Yuren+Mao%2C+Peigen+Liu%2C+Xinjian+Wang%2C+Rui+Ding%2C+Jing+Miao%2C+Hui+Zou%2C+Mingjie+Qi%2C+Wanxiang+Luo%2C+Longbin+Lai%2C+Kai+Wang%2C+Zhengping+Qian%2C+Peilun+Yang%2C+Yunjun+Gao%2C+and+Ying+Zhang%2E+2025%2E+Agent%2Dkernel%3A+A+micro)
24. Onder Gurcan. 2024. Llm-augmented agent-based modelling for social simulations: Challenges and opportunities. arXiv preprint arXiv:2405.06700. — [arXiv:2405.06700](https://arxiv.org/abs/2405.06700) [find](https://scholar.google.com/scholar?q=Onder+Gurcan%2E+2024%2E+Llm%2Daugmented+agent%2Dbased+modelling+for+social+simulations%3A+Challenges+and+opportunities%2E+arXiv+preprint+arXiv%3A2405%2E06700%2E+%E2%80%94+%5BarXiv%3A2405%2E06700%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2405%2E06700%29)
25. Xinyi Mou, Xuanwen Ding, Qi He, Liang Wang, Jingcong Liang, Xinnong Zhang, Libo Sun, Jiayu Lin, Jie Zhou, Xuanjing Huang, and 1 others. 2024. From individual to society: A survey on social simulation driven by large language model-based agents. arXiv preprint arXiv:2412.03563. — [arXiv:2412.03563](https://arxiv.org/abs/2412.03563) [find](https://scholar.google.com/scholar?q=Xinyi+Mou%2C+Xuanwen+Ding%2C+Qi+He%2C+Liang+Wang%2C+Jingcong+Liang%2C+Xinnong+Zhang%2C+Libo+Sun%2C+Jiayu+Lin%2C+Jie+Zhou%2C+Xuanjing+Huang%2C+and+1+others%2E+2024%2E+From+individual+to+society%3A+A+survey+on+social+simulation+)
26. Kairong Han, Kun Kuang, Ziyu Zhao, Junjian Ye, and Fei Wu. 2024. Causal agent based on large language model. arXiv preprint arXiv:2408.06849. — [arXiv:2408.06849](https://arxiv.org/abs/2408.06849) [find](https://scholar.google.com/scholar?q=Kairong+Han%2C+Kun+Kuang%2C+Ziyu+Zhao%2C+Junjian+Ye%2C+and+Fei+Wu%2E+2024%2E+Causal+agent+based+on+large+language+model%2E+arXiv+preprint+arXiv%3A2408%2E06849%2E+%E2%80%94+%5BarXiv%3A2408%2E06849%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2408%2E06849%29)
27. OpenAI. 2025. GPT-5 mini (openai api model specs). [https://platform.openai.com/docs/](https://platform.openai.com/docs/) models/gpt-5-mini. Accessed: 2025-12-31. [↗](https://platform.openai.com/docs/)
28. Zhijing Jin, Yuen Chen, Felix Leeb, Luigi Gresele, Ojasv Kamal, Zhiheng Lyu, Kevin Blin, Fernando Gonzalez Adauto, Max Kleiman-Weiner, Mrinmaya Sachan, and 1 others. 2023. Cladder: Assessing causal reasoning in language models. Advances in Neural Information Processing Systems, 36:31038– 31065. [find](https://scholar.google.com/scholar?q=Zhijing+Jin%2C+Yuen+Chen%2C+Felix+Leeb%2C+Luigi+Gresele%2C+Ojasv+Kamal%2C+Zhiheng+Lyu%2C+Kevin+Blin%2C+Fernando+Gonzalez+Adauto%2C+Max+Kleiman%2DWeiner%2C+Mrinmaya+Sachan%2C+and+1+others%2E+2023%2E+Cladder%3A+Assessing+causal+re)
29. Joon Sung Park, Joseph O’Brien, Carrie Jun Cai, Meredith Ringel Morris, Percy Liang, and Michael S Bernstein. 2023. Generative agents: Interactive simulacra of human behavior. In Proceedings of the 36th annual acm symposium on user interface software and technology, pages 1–22. [find](https://scholar.google.com/scholar?q=Joon+Sung+Park%2C+Joseph+O%E2%80%99Brien%2C+Carrie+Jun+Cai%2C+Meredith+Ringel+Morris%2C+Percy+Liang%2C+and+Michael+S+Bernstein%2E+2023%2E+Generative+agents%3A+Interactive+simulacra+of+human+behavior%2E+In+Proceedings+of+the+36)
30. Thomas Jiralerspong, Xiaoyin Chen, Yash More, Vedant Shah, and Yoshua Bengio. 2024. Efficient causal graph discovery using large language models. arXiv preprint arXiv:2402.01207. — [arXiv:2402.01207](https://arxiv.org/abs/2402.01207) [find](https://scholar.google.com/scholar?q=Thomas+Jiralerspong%2C+Xiaoyin+Chen%2C+Yash+More%2C+Vedant+Shah%2C+and+Yoshua+Bengio%2E+2024%2E+Efficient+causal+graph+discovery+using+large+language+models%2E+arXiv+preprint+arXiv%3A2402%2E01207%2E+%E2%80%94+%5BarXiv%3A2402%2E01207%5D%28)
31. Jinghua Piao, Zhihong Lu, Chen Gao, Fengli Xu, Qinghua Hu, Fernando P Santos, Yong Li, and James Evans. 2025a. Emergence of human-like polarization among large language model agents. arXiv preprint arXiv:2501.05171. — [arXiv:2501.05171](https://arxiv.org/abs/2501.05171) [find](https://scholar.google.com/scholar?q=Jinghua+Piao%2C+Zhihong+Lu%2C+Chen+Gao%2C+Fengli+Xu%2C+Qinghua+Hu%2C+Fernando+P+Santos%2C+Yong+Li%2C+and+James+Evans%2E+2025a%2E+Emergence+of+human%2Dlike+polarization+among+large+language+model+agents%2E+arXiv+preprint+ar)
32. Jinghua Piao, Yuwei Yan, Jun Zhang, Nian Li, Junbo Yan, Xiaochong Lan, Zhihong Lu, Zhiheng Zheng, Jing Yi Wang, Di Zhou, and 1 others. 2025b. Agentsociety: Large-scale simulation of llm-driven generative agents advances understanding of human behaviors and society. arXiv preprint arXiv:2502.08691. — [arXiv:2502.08691](https://arxiv.org/abs/2502.08691) [find](https://scholar.google.com/scholar?q=Jinghua+Piao%2C+Yuwei+Yan%2C+Jun+Zhang%2C+Nian+Li%2C+Junbo+Yan%2C+Xiaochong+Lan%2C+Zhihong+Lu%2C+Zhiheng+Zheng%2C+Jing+Yi+Wang%2C+Di+Zhou%2C+and+1+others%2E+2025b%2E+Agentsociety%3A+Large%2Dscale+simulation+of+llm%2Ddriven+generat)
33. Giorgio Piatti, Zhijing Jin, Max Kleiman-Weiner, Bernhard Schölkopf, Mrinmaya Sachan, and Rada Mihalcea. 2024. Cooperate or collapse: Emergence of sustainable cooperation in a society of llm agents. Advances in Neural Information Processing Systems, 37:111715–111759. [find](https://scholar.google.com/scholar?q=Giorgio+Piatti%2C+Zhijing+Jin%2C+Max+Kleiman%2DWeiner%2C+Bernhard+Sch%C3%B6lkopf%2C+Mrinmaya+Sachan%2C+and+Rada+Mihalcea%2E+2024%2E+Cooperate+or+collapse%3A+Emergence+of+sustainable+cooperation+in+a+society+of+llm+agents%2E+A)
34. Siyue Ren, Zhiyao Cui, Ruiqi Song, Zhen Wang, and Shuyue Hu. 2024. Emergence of social norms in generative agent societies: principles and architecture. arXiv preprint arXiv:2403.08251. — [arXiv:2403.08251](https://arxiv.org/abs/2403.08251) [find](https://scholar.google.com/scholar?q=Siyue+Ren%2C+Zhiyao+Cui%2C+Ruiqi+Song%2C+Zhen+Wang%2C+and+Shuyue+Hu%2E+2024%2E+Emergence+of+social+norms+in+generative+agent+societies%3A+principles+and+architecture%2E+arXiv+preprint+arXiv%3A2403%2E08251%2E+%E2%80%94+%5BarXiv%3A2403%2E)
35. Jonathan Richens and Tom Everitt. 2024. Robust agents learn causal world models. arXiv preprint arXiv:2402.10877. — [arXiv:2402.10877](https://arxiv.org/abs/2402.10877) [find](https://scholar.google.com/scholar?q=Jonathan+Richens+and+Tom+Everitt%2E+2024%2E+Robust+agents+learn+causal+world+models%2E+arXiv+preprint+arXiv%3A2402%2E10877%2E+%E2%80%94+%5BarXiv%3A2402%2E10877%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2402%2E10877%29)
36. Christoph Riedl. 2025. Emergent coordination in multi-agent language models. arXiv preprint arXiv:2510.05174. — [arXiv:2510.05174](https://arxiv.org/abs/2510.05174) [find](https://scholar.google.com/scholar?q=Christoph+Riedl%2E+2025%2E+Emergent+coordination+in+multi%2Dagent+language+models%2E+arXiv+preprint+arXiv%3A2510%2E05174%2E+%E2%80%94+%5BarXiv%3A2510%2E05174%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2510%2E05174%29)
37. ChengAo Shen, Zhengzhang Chen, Dongsheng Luo, Dongkuan Xu, Haifeng Chen, and Jingchao Ni. 2024. Exploring multi-modal integration with tool-augmented llm agents for precise causal discovery. arXiv preprint arXiv:2412.13667, 1(3). — [arXiv:2412.13667](https://arxiv.org/abs/2412.13667) [find](https://scholar.google.com/scholar?q=ChengAo+Shen%2C+Zhengzhang+Chen%2C+Dongsheng+Luo%2C+Dongkuan+Xu%2C+Haifeng+Chen%2C+and+Jingchao+Ni%2E+2024%2E+Exploring+multi%2Dmodal+integration+with+tool%2Daugmented+llm+agents+for+precise+causal+discovery%2E+arXiv+pre)
38. Peter Spirtes and Clark Glymour. 1991. An algorithm for fast recovery of sparse causal graphs. Social science computer review, 9(1):62–72. [find](https://scholar.google.com/scholar?q=Peter+Spirtes+and+Clark+Glymour%2E+1991%2E+An+algorithm+for+fast+recovery+of+sparse+causal+graphs%2E+Social+science+computer+review%2C+9%281%29%3A62%E2%80%9372%2E)
39. Peter Spirtes, Clark N Glymour, and Richard Scheines. 2000. Causation, prediction, and search. MIT press. [find](https://scholar.google.com/scholar?q=Peter+Spirtes%2C+Clark+N+Glymour%2C+and+Richard+Scheines%2E+2000%2E+Causation%2C+prediction%2C+and+search%2E+MIT+press%2E)
40. Ryosuke Takata, Atsushi Masumori, and Takashi Ikegami. 2024. Spontaneous emergence of agent individuality through social interactions in llm-based communities. arXiv preprint arXiv:2411.03252. — [arXiv:2411.03252](https://arxiv.org/abs/2411.03252) [find](https://scholar.google.com/scholar?q=Ryosuke+Takata%2C+Atsushi+Masumori%2C+and+Takashi+Ikegami%2E+2024%2E+Spontaneous+emergence+of+agent+individuality+through+social+interactions+in+llm%2Dbased+communities%2E+arXiv+preprint+arXiv%3A2411%2E03252%2E+%E2%80%94+%5BarXi)
41. Masayuki Takayama, Tadahisa Okuda, Thong Pham, Tatsuyoshi Ikenoue, Shingo Fukuma, Shohei Shimizu, and Akiyoshi Sannai. 2024. Integrating large language models in causal discovery: A statistical causal approach. arXiv preprint arXiv:2402.01454. — [arXiv:2402.01454](https://arxiv.org/abs/2402.01454) [find](https://scholar.google.com/scholar?q=Masayuki+Takayama%2C+Tadahisa+Okuda%2C+Thong+Pham%2C+Tatsuyoshi+Ikenoue%2C+Shingo+Fukuma%2C+Shohei+Shimizu%2C+and+Akiyoshi+Sannai%2E+2024%2E+Integrating+large+language+models+in+causal+discovery%3A+A+statistical+causal)
42. Gemma Team, Aishwarya Kamath, Johan Ferret, Shreya Pathak, Nino Vieillard, Ramona Merhej, Sarah Perrin, Tatiana Matejovicova, Alexandre Ramé, Morgane Rivière, and 1 others. 2025. Gemma 3 technical report. arXiv preprint arXiv:2503.19786. [find](https://scholar.google.com/scholar?q=Gemma+Team%2C+Aishwarya+Kamath%2C+Johan+Ferret%2C+Shreya+Pathak%2C+Nino+Vieillard%2C+Ramona+Merhej%2C+Sarah+Perrin%2C+Tatiana+Matejovicova%2C+Alexandre+Ram%C3%A9%2C+Morgane+Rivi%C3%A8re%2C+and+1+others%2E+2025%2E+Gemma+3+technical+rep)
43. Ioannis Tsamardinos, Laura E Brown, and Constantin F Aliferis. 2006. The max-min hill-climbing bayesian network structure learning algorithm. Machine learning, 65(1):31–78. [find](https://scholar.google.com/scholar?q=Ioannis+Tsamardinos%2C+Laura+E+Brown%2C+and+Constantin+F+Aliferis%2E+2006%2E+The+max%2Dmin+hill%2Dclimbing+bayesian+network+structure+learning+algorithm%2E+Machine+learning%2C+65%281%29%3A31%E2%80%9378%2E)
44. Hai Wang, Lei Zhao, Kaile Yan, Xiaoyi Wang, Yile Liang, and Jinghua Hao. 2025a. Meituan: Operational-level on-demand food delivery data for the 2025 informs tsl data-driven research challenge. Available at SSRN 5696423. [find](https://scholar.google.com/scholar?q=Hai+Wang%2C+Lei+Zhao%2C+Kaile+Yan%2C+Xiaoyi+Wang%2C+Yile+Liang%2C+and+Jinghua+Hao%2E+2025a%2E+Meituan%3A+Operational%2Dlevel+on%2Ddemand+food+delivery+data+for+the+2025+informs+tsl+data%2Ddriven+research+challenge%2E+Availab)
45. Qian Wang, Jiaying Wu, Zhenheng Tang, Bingqiao Luo, Nuo Chen, Wei Chen, and Bingsheng He. 2025b. What limits llm-based human simulation: Llms or our design? arXiv preprint arXiv:2501.08579. — [arXiv:2501.08579](https://arxiv.org/abs/2501.08579) [find](https://scholar.google.com/scholar?q=Qian+Wang%2C+Jiaying+Wu%2C+Zhenheng+Tang%2C+Bingqiao+Luo%2C+Nuo+Chen%2C+Wei+Chen%2C+and+Bingsheng+He%2E+2025b%2E+What+limits+llm%2Dbased+human+simulation%3A+Llms+or+our+design%3F+arXiv+preprint+arXiv%3A2501%2E08579%2E+%E2%80%94+%5BarXiv%3A2)
46. Anpeng Wu, Kun Kuang, Minqin Zhu, Yingrong Wang, Yujia Zheng, Kairong Han, Baohong Li, Guangyi Chen, Fei Wu, and Kun Zhang. 2024. Causality for large language models. arXiv preprint arXiv:2410.15319. — [arXiv:2410.15319](https://arxiv.org/abs/2410.15319) [find](https://scholar.google.com/scholar?q=Anpeng+Wu%2C+Kun+Kuang%2C+Minqin+Zhu%2C+Yingrong+Wang%2C+Yujia+Zheng%2C+Kairong+Han%2C+Baohong+Li%2C+Guangyi+Chen%2C+Fei+Wu%2C+and+Kun+Zhang%2E+2024%2E+Causality+for+large+language+models%2E+arXiv+preprint+arXiv%3A2410%2E15319%2E+)
47. Yuchen Xia, Daniel Dittler, Nasser Jazdi, Haonan Chen, and Michael Weyrich. 2024. Llm experiments with simulation: Large language model multi-agent system for simulation model parametrization in digital twins. In 2024 IEEE 29th International Conference on Emerging Technologies and Factory Automation… [find](https://scholar.google.com/scholar?q=Yuchen+Xia%2C+Daniel+Dittler%2C+Nasser+Jazdi%2C+Haonan+Chen%2C+and+Michael+Weyrich%2E+2024%2E+Llm+experiments+with+simulation%3A+Large+language+model+multi%2Dagent+system+for+simulation+model+parametrization+in+digit)
48. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, and 1 others. 2025. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). arXiv preprint arXiv:2505.09388.
49. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R Narasimhan, and Yuan Cao. 2022. [React: Synergizing reasoning and acting in language models](https://md.research.elamur.ai/free/en/papers/yao-2022-react-synergizing-reasoning-acting-language/). In The eleventh international conference on learning representations.
50. Kui Yu, Lin Liu, Jiuyong Li, and Huanhuan Chen. 2018. Mining markov blankets without causal sufficiency. IEEE transactions on neural networks and learning systems, 29(12):6333–6347. [find](https://scholar.google.com/scholar?q=Kui+Yu%2C+Lin+Liu%2C+Jiuyong+Li%2C+and+Huanhuan+Chen%2E+2018%2E+Mining+markov+blankets+without+causal+sufficiency%2E+IEEE+transactions+on+neural+networks+and+learning+systems%2C+29%2812%29%3A6333%E2%80%936347%2E)
51. Xiangning Yu, Zhuohan Wang, Linyi Yang, Haoxuan Li, Anjie Liu, Xiao Xue, Jun Wang, and Mengyue Yang. 2025a. Causal sufficiency and necessity improves chain-of-thought reasoning. arXiv preprint arXiv:2506.09853. — [arXiv:2506.09853](https://arxiv.org/abs/2506.09853) [find](https://scholar.google.com/scholar?q=Xiangning+Yu%2C+Zhuohan+Wang%2C+Linyi+Yang%2C+Haoxuan+Li%2C+Anjie+Liu%2C+Xiao+Xue%2C+Jun+Wang%2C+and+Mengyue+Yang%2E+2025a%2E+Causal+sufficiency+and+necessity+improves+chain%2Dof%2Dthought+reasoning%2E+arXiv+preprint+arXiv%3A2)
52. Xiangning Yu, Xiao Xue, Deyu Zhou, Gang Wang, and Zhiyong Feng. 2025b. Unlocking complexity: Harnessing value entropy for advanced multidimensional utility evaluation in service ecosystems. IEEE Transactions on Services Computing. [find](https://scholar.google.com/scholar?q=Xiangning+Yu%2C+Xiao+Xue%2C+Deyu+Zhou%2C+Gang+Wang%2C+and+Zhiyong+Feng%2E+2025b%2E+Unlocking+complexity%3A+Harnessing+value+entropy+for+advanced+multidimensional+utility+evaluation+in+service+ecosystems%2E+IEEE+Trans)
53. Matej Zečević, Moritz Willig, Devendra Singh Dhami, and Kristian Kersting. 2023. Causal parrots: Large language models may talk causality but are not causal. arXiv preprint arXiv:2308.13067. [find](https://scholar.google.com/scholar?q=Matej+Zec%CC%8Cevic%CC%81%2C+Moritz+Willig%2C+Devendra+Singh+Dhami%2C+and+Kristian+Kersting%2E+2023%2E+Causal+parrots%3A+Large+language+models+may+talk+causality+but+are+not+causal%2E+arXiv+preprint+arXiv%3A2308%2E13067%2E)
54. Jiji Zhang. 2008. Causal reasoning with ancestral graphs. Journal of Machine Learning Research, 9(7). [find](https://scholar.google.com/scholar?q=Jiji+Zhang%2E+2008%2E+Causal+reasoning+with+ancestral+graphs%2E+Journal+of+Machine+Learning+Research%2C+9%287%29%2E)
55. Xinnong Zhang, Jiayu Lin, Xinyi Mou, Shiyue Yang, Xiawei Liu, Libo Sun, Hanjia Lyu, Yihang Yang, Weihong Qi, Yue Chen, Guanying Li, Ling Yan, Yao Hu, Siming Chen, Yu Wang, Xuanjing Huang, Jiebo Luo, Shiping Tang, Libo Wu, and 2 others. 2025. Socioverse: A world model for social simulation powered by… — [arXiv:2504.10157](https://arxiv.org/abs/2504.10157) [find](https://scholar.google.com/scholar?q=Xinnong+Zhang%2C+Jiayu+Lin%2C+Xinyi+Mou%2C+Shiyue+Yang%2C+Xiawei+Liu%2C+Libo+Sun%2C+Hanjia+Lyu%2C+Yihang+Yang%2C+Weihong+Qi%2C+Yue+Chen%2C+Guanying+Li%2C+Ling+Yan%2C+Yao+Hu%2C+Siming+Chen%2C+Yu+Wang%2C+Xuanjing+Huang%2C+Jiebo+Luo%2C+S)
56. Lecheng Zheng, Zhengzhang Chen, Dongjie Wang, Chengyuan Deng, Reon Matsuoka, and Haifeng Chen. 2024. Lemma-rca: A large multi-modal multi-domain dataset for root cause analysis. arXiv preprint arXiv:2406.05375. — [arXiv:2406.05375](https://arxiv.org/abs/2406.05375) [find](https://scholar.google.com/scholar?q=Lecheng+Zheng%2C+Zhengzhang+Chen%2C+Dongjie+Wang%2C+Chengyuan+Deng%2C+Reon+Matsuoka%2C+and+Haifeng+Chen%2E+2024%2E+Lemma%2Drca%3A+A+large+multi%2Dmodal+multi%2Ddomain+dataset+for+root+cause+analysis%2E+arXiv+preprint+arXiv%3A2)
57. Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric Xing, and 1 others. 2023. [Judging llm-as-a-judge with mt-bench and chatbot arena](https://md.research.elamur.ai/free/en/papers/zheng-2023-judging-llm-judge-mt-bench/). Advances in neural information processing systems, 36:46595–46623.

*Updated 2 November 2026*