---
title: "AnyMAC — paper by Wang et al. (2025) — summary and ideas"
description: "AnyMAC replaces the graph with a sequence. 95.66% accuracy. 57 references, cited by 9 papers here."
authors: ["Song Wang", "Zhen Tan", "Zihan Chen", "Shuang Zhou", "Tianlong Chen", "Jundong Li"]
year: 2025
venue: "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing"
source: "https://aclanthology.org/2025.emnlp-main.584/"
doi: "10.18653/v1/2025.emnlp-main.584"
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/wang-2025-anymac-cascading-flexible-multi-agent/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wang-2025-anymac-cascading-flexible-multi-agent/)

[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/8/) / AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction

# AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction

**Authors:** [Song Wang](https://md.research.elamur.ai/free/en/authors/song-wang/), [Zhen Tan](https://md.research.elamur.ai/free/en/authors/zhen-tan/), [Zihan Chen](https://md.research.elamur.ai/free/en/authors/zihan-chen/), Shuang Zhou, [Tianlong Chen](https://md.research.elamur.ai/free/en/authors/tianlong-chen/) and [Jundong Li](https://md.research.elamur.ai/free/en/authors/jundong-li/) · **Year:** 2025 · **Venue:** [Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing](https://md.research.elamur.ai/free/en/venues/emnlp/) ([EMNLP 2025](https://md.research.elamur.ai/free/en/venues/emnlp/2025/)) · **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/2025.emnlp-main.584/) · [PDF](https://aclanthology.org/2025.emnlp-main.584.pdf) · [DOI 10.18653/v1/2025.emnlp-main.584](https://doi.org/10.18653/v1/2025.emnlp-main.584) · [OpenAlex](https://openalex.org/W4416036612)

**Citations:** 1 citations (OpenAlex, 2026-10-14) · [9](https://md.research.elamur.ai/free/en/papers/wang-2025-anymac-cascading-flexible-multi-agent/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
LLM-based multi-agent systems usually link agents through fixed or learned graphs, often DAGs. These graphs allow each agent to be used only once per round and let agents see only their neighbours' messages. AnyMAC replaces the graph with a sequence. At each step, Next-Agent Prediction (NAP) picks which role to call next, so agents can be revisited and the chain length can change. Next-Context Selection (NCS) then decides which earlier outputs, from any previous step, go into the current prompt. A transformer encodes the query and the agents activated so far, and a referee agent combines the outputs into a final answer. The authors argue that this sequential formulation covers every topology that earlier graph-based methods can express. On reasoning and coding benchmarks, AnyMAC beats static topologies and adaptive baselines such as DyLAN and G-Designer. It also holds up when a malicious agent is added. A lighter variant, AnyMAC-Eff, greatly reduces token cost. The work matters because it lets multi-agent pipelines adapt to each query while staying cheaper and more robust.

## Key points
- **Benchmarks.** The main experiments include GSM8K, MMLU, AQuA and HumanEval. In the results table, the strongest configuration reaches an average of 90.62, with 81.50 on AQuA and 90.12 on HumanEval.
- **Ablation on GSM8K.** The full model scores 95.66% accuracy. Removing parts lowers the score:
  - without task embedding: 93.87%
  - without NAP: 94.75%
  - without NCS: 94.35%
- **Robustness on MMLU.** When a malicious agent is injected, competing methods lose up to 11.0% accuracy, while AnyMAC drops only about 1.3%.
- **Efficiency on GSM8K.** AnyMAC-Eff uses about 5× fewer prompt tokens than G-Designer, the most efficient baseline, while staying competitive in accuracy.
- **Code.** Available at https://github.com/SongW-SW/AnyMAC.

*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 (5): [🖥️ 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 · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [🌐 Computer Networks and Communications](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-networks-and-communications/) · 64 works

## Cite

Cite as: Song Wang, Zhen Tan, Zihan Chen, Shuang Zhou, Tianlong Chen and Jundong Li. 2025. AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing.

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

```bibtex
@inproceedings{wang2025anymac,
  title = {{AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction}},
  author = {Song Wang, Zhen Tan, Zihan Chen, Shuang Zhou, Tianlong Chen and Jundong Li},
  booktitle = {Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing},
  year = {2025},
  doi = {10.18653/v1/2025.emnlp-main.584},
  url = {https://doi.org/10.18653/v1/2025.emnlp-main.584}
}
```

- [← previous An Efficient and Precise Training Data Construction Framework for Process-supervised Reward Model in Mathematical Reasoning](https://md.research.elamur.ai/free/en/papers/sun-2025-efficient-precise-training-data-construction/)
- [next → Arabic Large Language Models for Medical Text Generation](https://md.research.elamur.ai/free/en/papers/allam-2025-arabic-large-language-models-medical/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/8/)

## References

57 references, 22 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, and 1 others. 2020. [Language models are few-shot learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/). Advances in neural information processing systems, 33:1877–1901.
2. Bei Chen, Fengji Zhang, Anh Nguyen, Daoguang Zan, Zeqi Lin, Jian-Guang Lou, and Weizhu Chen. 2023. Codet: Code generation with generated tests. In The Eleventh International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Bei+Chen%2C+Fengji+Zhang%2C+Anh+Nguyen%2C+Daoguang+Zan%2C+Zeqi+Lin%2C+Jian%2DGuang+Lou%2C+and+Weizhu+Chen%2E+2023%2E+Codet%3A+Code+generation+with+generated+tests%2E+In+The+Eleventh+International+Conference+on+Learning+Rep)
3. Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, Alex Ray, Raul Puri, Gretchen Krueger, Michael Petrov, Heidy Khlaaf, Girish Sastry, Pamela Mishkin, Brooke Chan, Scott Gray, and 39 others. 202… — [Evaluating Large Language Models Trained on Code](https://md.research.elamur.ai/free/en/papers/chen-2021-evaluating-large-language-models-trained/)
4. Zihan Chen, Song Wang, Cong Shen, and Jundong Li. 2024. Fastgas: Fast graph-based annotation selection for in-context learning. In Findings of the Association for Computational Linguistics ACL 2024, pages 9764–9780. [find](https://scholar.google.com/scholar?q=Zihan+Chen%2C+Song+Wang%2C+Cong+Shen%2C+and+Jundong+Li%2E+2024%2E+Fastgas%3A+Fast+graph%2Dbased+annotation+selection+for+in%2Dcontext+learning%2E+In+Findings+of+the+Association+for+Computational+Linguistics+ACL+2024%2C+p)
5. Zihan Chen, Song Wang, Zhen Tan, Jundong Li, and Cong Shen. 2025. Maple: Many-shot adaptive pseudo-labeling for in-context learning. arXiv preprint arXiv:2505.16225. — [arXiv:2505.16225](https://arxiv.org/abs/2505.16225) [find](https://scholar.google.com/scholar?q=Zihan+Chen%2C+Song+Wang%2C+Zhen+Tan%2C+Jundong+Li%2C+and+Cong+Shen%2E+2025%2E+Maple%3A+Many%2Dshot+adaptive+pseudo%2Dlabeling+for+in%2Dcontext+learning%2E+arXiv+preprint+arXiv%3A2505%2E16225%2E+%E2%80%94+%5BarXiv%3A2505%2E16225%5D%28https%3A%2F%2Farxiv)
6. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, and John Schulman. 2021. [Training verifiers to solve math word problems](https://md.research.elamur.ai/free/en/papers/cobbe-2021-training-verifiers-solve-math-word/). arXiv prepring, abs/2110.14168.
7. DeepSeek. 2025. [Deepseek r1: Towards deep reinforcement learning for language models](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/). arXiv preprint arXiv:2501.12948.
8. Yilun Du, Shuang Li, Antonio Torralba, Joshua B. Tenenbaum, and Igor Mordatch. 2023. [Improving factuality and reasoning in language models through multiagent debate](https://md.research.elamur.ai/free/en/papers/du-2023-improving-factuality-reasoning-language-models/). CoRR, abs/2305.14325.
9. Yao Fu, Hao Peng, Ashish Sabharwal, Peter Clark, and Tushar Khot. 2022. [Complexity-based prompting for multi-step reasoning](https://md.research.elamur.ai/free/en/papers/fu-2022-complexity-based-prompting-multi-step/). In The Eleventh International Conference on Learning Representations.
10. Shixiang Gu, Timothy Lillicrap, Ilya Sutskever, and Sergey Levine. 2016. Continuous deep q-learning with model-based acceleration. In International conference on machine learning, pages 2829–2838. PMLR. [find](https://scholar.google.com/scholar?q=Shixiang+Gu%2C+Timothy+Lillicrap%2C+Ilya+Sutskever%2C+and+Sergey+Levine%2E+2016%2E+Continuous+deep+q%2Dlearning+with+model%2Dbased+acceleration%2E+In+International+conference+on+machine+learning%2C+pages+2829%E2%80%932838%2E+PML)
11. Rui Hao, Linmei Hu, Weijian Qi, Qingliu Wu, Yirui Zhang, and Liqiang Nie. 2023. Chatllm network: More brains, more intelligence. [find](https://scholar.google.com/scholar?q=Rui+Hao%2C+Linmei+Hu%2C+Weijian+Qi%2C+Qingliu+Wu%2C+Yirui+Zhang%2C+and+Liqiang+Nie%2E+2023%2E+Chatllm+network%3A+More+brains%2C+more+intelligence%2E)
12. Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2021. [Measuring massive multitask language understanding](https://md.research.elamur.ai/free/en/papers/hendrycks-2020-measuring-massive-multitask-language-understanding/). Proceedings of the International Conference on Learning Representations (ICLR).
13. Niklas Muennighoff, Zitong Yang, Weijia Shi, Xiang Lisa Li, Li Fei-Fei, Hannaneh Hajishirzi, Luke Zettlemoyer, Percy Liang, Emmanuel Candès, and Tatsunori Hashimoto. 2025. [s1: Simple test-time scaling](https://md.research.elamur.ai/free/en/papers/muennighoff-2025-s1-simple-test-time-scaling/). arXiv preprint arXiv:2501.19393.
14. Samuel Holt, Max Ruiz Luyten, and Mihaela van der Schaar. 2024. L2mac: Large language model automatic computer for extensive code generation. In The Twelfth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Samuel+Holt%2C+Max+Ruiz+Luyten%2C+and+Mihaela+van+der+Schaar%2E+2024%2E+L2mac%3A+Large+language+model+automatic+computer+for+extensive+code+generation%2E+In+The+Twelfth+International+Conference+on+Learning+Repres)
15. Liangming Pan, Michael Saxon, Wenda Xu, Deepak Nathani, Xinyi Wang, and William Yang Wang. 2023. Automatically correcting large language models: Surveying the landscape of diverse self-correction strategies. Work in Progress. [find](https://scholar.google.com/scholar?q=Liangming+Pan%2C+Michael+Saxon%2C+Wenda+Xu%2C+Deepak+Nathani%2C+Xinyi+Wang%2C+and+William+Yang+Wang%2E+2023%2E+Automatically+correcting+large+language+models%3A+Surveying+the+landscape+of+diverse+self%2Dcorrection+stra)
16. Sirui Hong, Xiawu Zheng, Jonathan Chen, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, Chenyu Ran, Lingfeng Xiao, and Chenglin Wu. 2023. Metagpt: Meta programming for multi-agent collaborative framework. [find](https://scholar.google.com/scholar?q=Sirui+Hong%2C+Xiawu+Zheng%2C+Jonathan+Chen%2C+Yuheng+Cheng%2C+Jinlin+Wang%2C+Ceyao+Zhang%2C+Zili+Wang%2C+Steven+Ka+Shing+Yau%2C+Zijuan+Lin%2C+Liyang+Zhou%2C+Chenyu+Ran%2C+Lingfeng+Xiao%2C+and+Chenglin+Wu%2E+2023%2E+Metagpt%3A+Meta)
17. Arkil Patel, Satwik Bhattamishra, and Navin Goyal. 2021. [Are nlp models really able to solve simple math word problems?](https://md.research.elamur.ai/free/en/papers/patel-2021-are-nlp-models-really-able/) arXiv preprint arXiv:2103.07191.
18. Lijie Hu, Liang Liu, Shu Yang, Xin Chen, Zhen Tan, Muhammad Asif Ali, Mengdi Li, and Di Wang. 2024. Understanding reasoning in chain-of-thought from the hopfieldian view. arXiv preprint arXiv:2410.03595. — [arXiv:2410.03595](https://arxiv.org/abs/2410.03595) [find](https://scholar.google.com/scholar?q=Lijie+Hu%2C+Liang+Liu%2C+Shu+Yang%2C+Xin+Chen%2C+Zhen+Tan%2C+Muhammad+Asif+Ali%2C+Mengdi+Li%2C+and+Di+Wang%2E+2024%2E+Understanding+reasoning+in+chain%2Dof%2Dthought+from+the+hopfieldian+view%2E+arXiv+preprint+arXiv%3A2410%2E035)
19. Yoichi Ishibashi and Yoshimasa Nishimura. 2024. Self-organized agents: A llm multi-agent framework toward ultra large-scale code generation and optimization. arXiv preprint arXiv:2404.02183. — [arXiv:2404.02183](https://arxiv.org/abs/2404.02183) [find](https://scholar.google.com/scholar?q=Yoichi+Ishibashi+and+Yoshimasa+Nishimura%2E+2024%2E+Self%2Dorganized+agents%3A+A+llm+multi%2Dagent+framework+toward+ultra+large%2Dscale+code+generation+and+optimization%2E+arXiv+preprint+arXiv%3A2404%2E02183%2E+%E2%80%94+%5BarXiv%3A)
20. Eric Jang, Shixiang Gu, and Ben Poole. 2016. [Categorical reparameterization with gumbel-softmax](https://md.research.elamur.ai/free/en/papers/jang-2016-categorical-reparameterization-gumbel-softmax/). arXiv preprint arXiv:1611.01144.
21. Zhenyu Lei, Zhen Tan, Song Wang, Yaochen Zhu, Zihan Chen, Yushun Dong, and Jundong Li. 2025. [Learning from diverse reasoning paths with routing and collaboration](https://md.research.elamur.ai/free/en/papers/lei-2025-learning-diverse-reasoning-paths-routing/). arXiv preprint arXiv:2508.16861.
22. Yifan Li, Zhixin Lai, Wentao Bao, Zhen Tan, Anh Dao, Kewei Sui, Jiayi Shen, Dong Liu, Huan Liu, and Yu Kong. 2025. Visual large language models for generalized and specialized applications. arXiv preprint arXiv:2501.02765. — [arXiv:2501.02765](https://arxiv.org/abs/2501.02765) [find](https://scholar.google.com/scholar?q=Yifan+Li%2C+Zhixin+Lai%2C+Wentao+Bao%2C+Zhen+Tan%2C+Anh+Dao%2C+Kewei+Sui%2C+Jiayi+Shen%2C+Dong+Liu%2C+Huan+Liu%2C+and+Yu+Kong%2E+2025%2E+Visual+large+language+models+for+generalized+and+specialized+applications%2E+arXiv+prep)
23. Wang Ling, Dani Yogatama, Chris Dyer, and Phil Blunsom. 2017. Program induction by rationale generation: Learning to solve and explain algebraic word problems. arXiv preprint arXiv:1705.04146. [find](https://scholar.google.com/scholar?q=Wang+Ling%2C+Dani+Yogatama%2C+Chris+Dyer%2C+and+Phil+Blunsom%2E+2017%2E+Program+induction+by+rationale+generation%3A+Learning+to+solve+and+explain+algebraic+word+problems%2E+arXiv+preprint+arXiv%3A1705%2E04146%2E)
24. Haochen Liu, Song Wang, Yaochen Zhu, Yushun Dong, and Jundong Li. 2024. Knowledge graph-enhanced large language models via path selection. In Findings of the Association for Computational Linguistics ACL 2024, pages 6311–6321. [find](https://scholar.google.com/scholar?q=Haochen+Liu%2C+Song+Wang%2C+Yaochen+Zhu%2C+Yushun+Dong%2C+and+Jundong+Li%2E+2024%2E+Knowledge+graph%2Denhanced+large+language+models+via+path+selection%2E+In+Findings+of+the+Association+for+Computational+Linguistics+)
25. Chen Qian, Xin Cong, Cheng Yang, Weize Chen, Yusheng Su, Juyuan Xu, Zhiyuan Liu, and Maosong Sun. 2023. Communicative agents for software development. 25 pages, 9 figures, 2 tables. [find](https://scholar.google.com/scholar?q=Chen+Qian%2C+Xin+Cong%2C+Cheng+Yang%2C+Weize+Chen%2C+Yusheng+Su%2C+Juyuan+Xu%2C+Zhiyuan+Liu%2C+and+Maosong+Sun%2E+2023%2E+Communicative+agents+for+software+development%2E+25+pages%2C+9+figures%2C+2+tables%2E)
26. Chen Qian, Zihao Xie, Yifei Wang, Wei Liu, Yufan Dang, Zhuoyun Du, Weize Chen, Cheng Yang, Zhiyuan Liu, and Maosong Sun. 2024. Scaling large-language-model-based multi-agent collaboration. arXiv preprint arXiv:2406.07155. [find](https://scholar.google.com/scholar?q=Chen+Qian%2C+Zihao+Xie%2C+Yifei+Wang%2C+Wei+Liu%2C+Yufan+Dang%2C+Zhuoyun+Du%2C+Weize+Chen%2C+Cheng+Yang%2C+Zhiyuan+Liu%2C+and+Maosong+Sun%2E+2024%2E+Scaling+large%2Dlanguage%2Dmodel%2Dbased+multi%2Dagent+collaboration%2E+arXiv+prepr)
27. Huaizhi Qu, Inyoung Choi, Zhen Tan, Song Wang, Sukwon Yun, Qi Long, Faizan Siddiqui, Kwonjoon Lee, and Tianlong Chen. 2025. Efficient map estimation of llm judgment performance with prior transfer. arXiv preprint arXiv:2504.12589. — [arXiv:2504.12589](https://arxiv.org/abs/2504.12589) [find](https://scholar.google.com/scholar?q=Huaizhi+Qu%2C+Inyoung+Choi%2C+Zhen+Tan%2C+Song+Wang%2C+Sukwon+Yun%2C+Qi+Long%2C+Faizan+Siddiqui%2C+Kwonjoon+Lee%2C+and+Tianlong+Chen%2E+2025%2E+Efficient+map+estimation+of+llm+judgment+performance+with+prior+transfer%2E+ar)
28. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, and 1 others. 2019. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9. [find](https://scholar.google.com/scholar?q=Alec+Radford%2C+Jeffrey+Wu%2C+Rewon+Child%2C+David+Luan%2C+Dario+Amodei%2C+Ilya+Sutskever%2C+and+1+others%2E+2019%2E+Language+models+are+unsupervised+multitask+learners%2E+OpenAI+blog%2C+1%288%29%3A9%2E)
29. Subhro Roy and Dan Roth. 2016. [Solving general arithmetic word problems](https://md.research.elamur.ai/free/en/papers/roy-2015-solving-general-arithmetic-word-problems/). arXiv preprint arXiv:1608.01413.
30. John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347. [find](https://scholar.google.com/scholar?q=John+Schulman%2C+Filip+Wolski%2C+Prafulla+Dhariwal%2C+Alec+Radford%2C+and+Oleg+Klimov%2E+2017%2E+Proximal+policy+optimization+algorithms%2E+arXiv+preprint+arXiv%3A1707%2E06347%2E)
31. Noah Shinn, Beck Labash, and Ashwin Gopinath. 2023. [Reflexion: an autonomous agent with dynamic memory and self-reflection](https://md.research.elamur.ai/free/en/papers/shinn-2023-reflexion-language-agents-verbal-reinforcement/). arXiv preprint, abs/2303.11366.
32. Zijun Liu, Yanzhe Zhang, Peng Li, Yang Liu, and Diyi Yang. 2023. Dynamic llm-agent network: An llm-agent collaboration framework with agent team optimization. CoRR, abs/2310.02170. [find](https://scholar.google.com/scholar?q=Zijun+Liu%2C+Yanzhe+Zhang%2C+Peng+Li%2C+Yang+Liu%2C+and+Diyi+Yang%2E+2023%2E+Dynamic+llm%2Dagent+network%3A+An+llm%2Dagent+collaboration+framework+with+agent+team+optimization%2E+CoRR%2C+abs%2F2310%2E02170%2E)
33. Zhen Tan, Lu Cheng, Song Wang, Bo Yuan, Jundong Li, and Huan Liu. 2024a. Interpreting pretrained language models via concept bottlenecks. In Pacific-Asia Conference on Knowledge Discovery and Data Mining, pages 56–74. Springer. [find](https://scholar.google.com/scholar?q=Zhen+Tan%2C+Lu+Cheng%2C+Song+Wang%2C+Bo+Yuan%2C+Jundong+Li%2C+and+Huan+Liu%2E+2024a%2E+Interpreting+pretrained+language+models+via+concept+bottlenecks%2E+In+Pacific%2DAsia+Conference+on+Knowledge+Discovery+and+Data+Min)
34. Ramesh Manuvinakurike, Emanuel Moss, Elizabeth Anne Watkins, Saurav Sahay, Giuseppe Raffa, and Lama Nachman. 2025. Thoughts without thinking: Reconsidering the explanatory value of chain-of-thought reasoning in llms through agentic pipelines. arXiv preprint arXiv:2505.00875. — [arXiv:2505.00875](https://arxiv.org/abs/2505.00875) [find](https://scholar.google.com/scholar?q=Ramesh+Manuvinakurike%2C+Emanuel+Moss%2C+Elizabeth+Anne+Watkins%2C+Saurav+Sahay%2C+Giuseppe+Raffa%2C+and+Lama+Nachman%2E+2025%2E+Thoughts+without+thinking%3A+Reconsidering+the+explanatory+value+of+chain%2Dof%2Dthought+re)
35. Zhen Tan, Dawei Li, Song Wang, Alimohammad Beigi, Bohan Jiang, Amrita Bhattacharjee, Mansooreh Karami, Jundong Li, Lu Cheng, and Huan Liu. 2024b. [Large language models for data annotation and synthesis: A survey](https://md.research.elamur.ai/free/en/papers/tan-2024-large-language-models-data-annotation/). arXiv preprint arXiv:2402.13446.
36. Zhen Tan, Jie Peng, Song Wang, Lijie Hu, Tianlong Chen, and Huan Liu. 2025a. Tuning-free accountable intervention for llm deployment–a metacognitive approach. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 25237– 25245. [find](https://scholar.google.com/scholar?q=Zhen+Tan%2C+Jie+Peng%2C+Song+Wang%2C+Lijie+Hu%2C+Tianlong+Chen%2C+and+Huan+Liu%2E+2025a%2E+Tuning%2Dfree+accountable+intervention+for+llm+deployment%E2%80%93a+metacognitive+approach%2E+In+Proceedings+of+the+AAAI+Conference+on+)
37. Zhen Tan, Jun Yan, I Hsu, Rujun Han, Zifeng Wang, Long T Le, Yiwen Song, Yanfei Chen, Hamid Palangi, George Lee, and 1 others. 2025b. [In prospect and retrospect: Reflective memory management for long-term personalized dialogue agents](https://md.research.elamur.ai/free/en/papers/tan-2025-prospect-retrospect-reflective-memory-management/). arXiv preprint arXiv:2503.08026.
38. Zhen Tan, Chengshuai Zhao, Raha Moraffah, Yifan Li, Song Wang, Jundong Li, Tianlong Chen, and Huan Liu. 2024c. Glue pizza and eat rocks-exploiting vulnerabilities in retrieval-augmented generative models. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, page… [find](https://scholar.google.com/scholar?q=Zhen+Tan%2C+Chengshuai+Zhao%2C+Raha+Moraffah%2C+Yifan+Li%2C+Song+Wang%2C+Jundong+Li%2C+Tianlong+Chen%2C+and+Huan+Liu%2E+2024c%2E+Glue+pizza+and+eat+rocks%2Dexploiting+vulnerabilities+in+retrieval%2Daugmented+generative+mod)
39. Song Wang, Zihan Chen, Chengshuai Shi, Cong Shen, and Jundong Li. 2024. Mixture of demonstrations for in-context learning. Advances in Neural Information Processing Systems, 37:88091–88116. [find](https://scholar.google.com/scholar?q=Song+Wang%2C+Zihan+Chen%2C+Chengshuai+Shi%2C+Cong+Shen%2C+and+Jundong+Li%2E+2024%2E+Mixture+of+demonstrations+for+in%2Dcontext+learning%2E+Advances+in+Neural+Information+Processing+Systems%2C+37%3A88091%E2%80%9388116%2E)
40. Song Wang, Junhong Lin, Xiaojie Guo, Julian Shun, Jundong Li, and Yada Zhu. 2025. Reasoning of large language models over knowledge graphs with super-relations. In ICLR. [find](https://scholar.google.com/scholar?q=Song+Wang%2C+Junhong+Lin%2C+Xiaojie+Guo%2C+Julian+Shun%2C+Jundong+Li%2C+and+Yada+Zhu%2E+2025%2E+Reasoning+of+large+language+models+over+knowledge+graphs+with+super%2Drelations%2E+In+ICLR%2E)
41. Wenhui Wang, Furu Wei, Li Dong, Hangbo Bao, Nan Yang, and Ming Zhou. 2020. Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers. Advances in Neural Information Processing Systems, 33:5776–5788. [find](https://scholar.google.com/scholar?q=Wenhui+Wang%2C+Furu+Wei%2C+Li+Dong%2C+Hangbo+Bao%2C+Nan+Yang%2C+and+Ming+Zhou%2E+2020%2E+Minilm%3A+Deep+self%2Dattention+distillation+for+task%2Dagnostic+compression+of+pre%2Dtrained+transformers%2E+Advances+in+Neural+Inform)
42. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2023a. [Self-consistency improves chain of thought reasoning in language models](https://md.research.elamur.ai/free/en/papers/wang-2022-self-consistency-improves-chain-thought/). In The Eleventh International Conference on Learning Representations.
43. Zhenhailong Wang, Shaoguang Mao, Wenshan Wu, Tao Ge, Furu Wei, and Heng Ji. 2023b. Unleashing cognitive synergy in large language models: A task-solving agent through multi-persona self-collaboration. Work in progress. [find](https://scholar.google.com/scholar?q=Zhenhailong+Wang%2C+Shaoguang+Mao%2C+Wenshan+Wu%2C+Tao+Ge%2C+Furu+Wei%2C+and+Heng+Ji%2E+2023b%2E+Unleashing+cognitive+synergy+in+large+language+models%3A+A+task%2Dsolving+agent+through+multi%2Dpersona+self%2Dcollaboration%2E)
44. Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Thomas L. Griffiths, Yuan Cao, and Karthik Narasimhan. 2023a. Tree of thoughts: Deliberate problem solving with large language models. [find](https://scholar.google.com/scholar?q=Shunyu+Yao%2C+Dian+Yu%2C+Jeffrey+Zhao%2C+Izhak+Shafran%2C+Thomas+L%2E+Griffiths%2C+Yuan+Cao%2C+and+Karthik+Narasimhan%2E+2023a%2E+Tree+of+thoughts%3A+Deliberate+problem+solving+with+large+language+models%2E)
45. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R Narasimhan, and Yuan Cao. 2023b. [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.
46. Yixin Ye, Zhen Huang, Yang Xiao, Ethan Chern, Shijie Xia, and Pengfei Liu. 2025. [Limo: Less is more for reasoning](https://md.research.elamur.ai/free/en/papers/ye-2025-limo-less-more-reasoning/). arXiv preprint arXiv:2502.03387.
47. Guibin Zhang, Yanwei Yue, Zhixun Li, Sukwon Yun, Guancheng Wan, Kun Wang, Dawei Cheng, Jeffrey Xu Yu, and Tianlong Chen. 2024a. Cut the crap: An economical communication pipeline for llm-based multi-agent systems. arXiv preprint arXiv:2410.02506. — [arXiv:2410.02506](https://arxiv.org/abs/2410.02506) [find](https://scholar.google.com/scholar?q=Guibin+Zhang%2C+Yanwei+Yue%2C+Zhixun+Li%2C+Sukwon+Yun%2C+Guancheng+Wan%2C+Kun+Wang%2C+Dawei+Cheng%2C+Jeffrey+Xu+Yu%2C+and+Tianlong+Chen%2E+2024a%2E+Cut+the+crap%3A+An+economical+communication+pipeline+for+llm%2Dbased+multi%2Da)
48. Guibin Zhang, Yanwei Yue, Xiangguo Sun, Guancheng Wan, Miao Yu, Junfeng Fang, Kun Wang, Tianlong Chen, and Dawei Cheng. 2024b. G-designer: Architecting multi-agent communication topologies via graph neural networks. arXiv preprint arXiv:2410.11782. — [arXiv:2410.11782](https://arxiv.org/abs/2410.11782) [find](https://scholar.google.com/scholar?q=Guibin+Zhang%2C+Yanwei+Yue%2C+Xiangguo+Sun%2C+Guancheng+Wan%2C+Miao+Yu%2C+Junfeng+Fang%2C+Kun+Wang%2C+Tianlong+Chen%2C+and+Dawei+Cheng%2E+2024b%2E+G%2Ddesigner%3A+Architecting+multi%2Dagent+communication+topologies+via+graph+n)
49. Jintian Zhang, Xin Xu, and Shumin Deng. 2023. [Exploring collaboration mechanisms for llm agents: A social psychology view](https://md.research.elamur.ai/free/en/papers/zhang-2024-exploring-collaboration-mechanisms-llm-agents/). arXiv preprint arXiv:2310.02124.
50. Ruichen Zhang, Mufan Qiu, Zhen Tan, Mohan Zhang, Vincent Lu, Jie Peng, Kaidi Xu, Leandro Z Agudelo, Peter Qian, and Tianlong Chen. 2025. Symbiotic cooperation for web agents: Harnessing complementary strengths of large and small llms. arXiv preprint arXiv:2502.07942. — [arXiv:2502.07942](https://arxiv.org/abs/2502.07942) [find](https://scholar.google.com/scholar?q=Ruichen+Zhang%2C+Mufan+Qiu%2C+Zhen+Tan%2C+Mohan+Zhang%2C+Vincent+Lu%2C+Jie+Peng%2C+Kaidi+Xu%2C+Leandro+Z+Agudelo%2C+Peter+Qian%2C+and+Tianlong+Chen%2E+2025%2E+Symbiotic+cooperation+for+web+agents%3A+Harnessing+complementary+)
51. Zhuosheng Zhang, Aston Zhang, Mu Li, and Alex Smola. 2022. [Automatic chain of thought prompting in large language models](https://md.research.elamur.ai/free/en/papers/zhang-2022-automatic-chain-thought-prompting-large/). arXiv preprint arXiv:2210.03493.
52. Chuanyang Zheng, Zhengying Liu, Enze Xie, Zhenguo Li, and Yu Li. 2023. Progressive-hint prompting improves reasoning in large language models. Tech Report. [find](https://scholar.google.com/scholar?q=Chuanyang+Zheng%2C+Zhengying+Liu%2C+Enze+Xie%2C+Zhenguo+Li%2C+and+Yu+Li%2E+2023%2E+Progressive%2Dhint+prompting+improves+reasoning+in+large+language+models%2E+Tech+Report%2E)
53. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed Chi, Quoc Le, and Denny Zhou. 2022. [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/).
54. Zihao Zhou, Bin Hu, Chenyang Zhao, Pu Zhang, and Bin Liu. 2023. Large language model as a policy teacher for training reinforcement learning agents. arXiv preprint arXiv:2311.13373. — [arXiv:2311.13373](https://arxiv.org/abs/2311.13373) [find](https://scholar.google.com/scholar?q=Zihao+Zhou%2C+Bin+Hu%2C+Chenyang+Zhao%2C+Pu+Zhang%2C+and+Bin+Liu%2E+2023%2E+Large+language+model+as+a+policy+teacher+for+training+reinforcement+learning+agents%2E+arXiv+preprint+arXiv%3A2311%2E13373%2E+%E2%80%94+%5BarXiv%3A2311%2E1337)
55. Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Shaokun Zhang, Erkang Zhu, Beibin Li, Li Jiang, Xiaoyun Zhang, and Chi Wang. 2023. [Autogen: Enabling next-gen llm applications via multi-agent conversation](https://md.research.elamur.ai/free/en/papers/wu-2023-autogen-enabling-next-gen-llm/) framework.
56. Mingchen Zhuge, Wenyi Wang, Louis Kirsch, Francesco Faccio, Dmitrii Khizbullin, and Jürgen Schmidhuber. 2024. Gptswarm: Language agents as optimizable graphs. In Forty-first International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Mingchen+Zhuge%2C+Wenyi+Wang%2C+Louis+Kirsch%2C+Francesco+Faccio%2C+Dmitrii+Khizbullin%2C+and+J%C3%BCrgen+Schmidhuber%2E+2024%2E+Gptswarm%3A+Language+agents+as+optimizable+graphs%2E+In+Forty%2Dfirst+International+Conference+o)
57. Yikuan Yan, Yaolun Zhang, and Keman Huang. 2024. Depending on yourself when you should: Mentoring llm with rl agents to become the master in cybersecurity games. arXiv preprint arXiv:2403.17674. — [arXiv:2403.17674](https://arxiv.org/abs/2403.17674) [find](https://scholar.google.com/scholar?q=Yikuan+Yan%2C+Yaolun+Zhang%2C+and+Keman+Huang%2E+2024%2E+Depending+on+yourself+when+you+should%3A+Mentoring+llm+with+rl+agents+to+become+the+master+in+cybersecurity+games%2E+arXiv+preprint+arXiv%3A2403%2E17674%2E+%E2%80%94+%5Bar)

*Updated 30 October 2026*