Elamur Research⌕
☰
home / papers / 2026 / BayesFlow: A Probability Inference Framework for Meta-Agent Assisted Workflow Generation

BayesFlow: A Probability Inference Framework for Meta-Agent Assisted Workflow Generation

Paper · 2026 · Bo Yuan, Yun Zhou, Zhichao Xu et al.

Summary

This paper addresses automatic agentic workflow generation: composing LLM calls, tool use and post-processing into executable pipelines without manual design. Earlier systems such as AFlow and ADAS treat this as heuristic optimization. They have weak theoretical backing and usually return one top workflow. The authors instead frame the task as sampling from a posterior over code-represented workflows. The meta-optimizer LLM acts as the prior, and validation accuracy enters as an energy-based reward.

Their framework, Bayesian Workflow Generation (BWG), builds workflows step by step. It uses two mechanisms:

  • Parallel look-ahead rollouts, in the style of Sequential Monte Carlo, assign importance weights to partial workflows. This avoids a trained process reward model or a stronger proprietary scorer.
  • A sequential in-loop refiner improves the candidate pool. It also covers earlier search methods as special cases.

Without the refiner, the weighted samples provably converge to the target posterior. The training-free instantiation, BayesFlow, beats strong baselines on six benchmarks with both Claude and Qwen executors. It also yields a more diverse set of good workflows, which helps when outputs from several workflows are combined.

Key points

  • Benchmarks: GSM8K, MATH, HotpotQA, DROP, MMLU-Pro and GPQA. The abstract reports six datasets, while the conclusion mentions seven.
  • Main gains:
    • Up to 9 percentage points over SOTA workflow-generation baselines, on math reasoning.
    • Up to 65 points over zero-shot prompting.
    • Average margin over the strongest baseline of 4.6 points with a Claude-3.7-Sonnet executor and 3.5 points with Qwen-2.5-7B.
  • Efficiency: BayesFlow often uses far fewer optimizer tokens than AFlow. On DROP with Claude Haiku 4.5 as optimizer and Qwen2.5-7B-Instruct as executor, it used about 14.5M input tokens versus about 79M, while F1 rose from 0.735 to 0.780. Its rollouts can also run fully in parallel.
  • Robustness: Performance stays stable when the per-round budget of 20 proposals is split differently between look-ahead rollouts N ∈ {5, 10, 15} and refinements M.
  • Workflow-level scaling: On a 100-example MATH subset, BayesFlow beats AFlow for L ∈ {1, 2, 4, 8}. The gap is largest on Best@L, for example Best@8 of 86% versus 81%. This suggests the generated workflows are more diverse.

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

🎓Georgia Institute of TechnologyAtlanta · United States152 works · 27,763 citations🏢AmazonSeattle · United States128 works · 41,700 citations

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksArts and Humanities · 17,450 worksLanguage and Linguistics · 17,296 worksDecision Sciences · 249 worksInformation Systems and Management · 52 works

Cite

Cite as Bo Yuan, Yun Zhou, Zhichao Xu, Kiran Ramnath, Aosong Feng and Balasubramaniam Srinivasan. 2026. BayesFlow: A Probability Inference Framework for Meta-Agent Assisted Workflow Generation. Findings of the Association for Computational Linguistics: EACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-eacl.165

@inproceedings{yuan2026bayesflow,
  title = {{BayesFlow: A Probability Inference Framework for Meta-Agent Assisted Workflow Generation}},
  author = {Bo Yuan, Yun Zhou, Zhichao Xu, Kiran Ramnath, Aosong Feng and Balasubramaniam Srinivasan},
  booktitle = {Findings of the Association for Computational Linguistics: EACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-eacl.165},
  url = {https://doi.org/10.18653/v1/2026.findings-eacl.165}
}

References

73 references, 34 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Anthropic. 2024. Introducing Claude 3.5 Sonnet. Accessed 8 Aug 2025. find
  2. Anthropic. 2025. Claude 3.7 sonnet and claude code. Accessed 8 Aug 2025. find
  3. Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2024. Self-rag: Learning to retrieve, generate, and critique through self-reflection. In The Twelfth International Conference on Learning Representations.
  4. Jacob Austin, Augustus Odena, Maxwell Nye, Maarten Bosma, Henryk Michalewski, David Dohan, Ellen Jiang, Carrie Cai, Michael Terry, Quoc Le, and 1 others. 2021. Program synthesis with large language models. arXiv preprint arXiv:2108.07732.
  5. Mert Cemri, Melissa Z Pan, Shuyi Yang, Lakshya A Agrawal, Bhavya Chopra, Rishabh Tiwari, Kurt Keutzer, Aditya Parameswaran, Dan Klein, Kannan Ramchandran, and 1 others. 2025. Why do multi-agent llm systems fail? arXiv preprint arXiv:2503.13657.
  6. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, and 1 others. 2021. Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168.
  7. Arnaud Doucet, Nando De Freitas, and Neil Gordon. 2001. An introduction to sequential monte carlo methods. In Sequential Monte Carlo methods in practice, pages 3–14. Springer. find
  8. Arnaud Doucet, Simon Godsill, and Christophe Andrieu. 2000. On sequential monte carlo sampling methods for bayesian filtering. Statistics and computing, 10(3):197–208. find
  9. Yilun Du, Shuang Li, Antonio Torralba, Joshua B Tenenbaum, and Igor Mordatch. 2023. Improving factuality and reasoning in language models through multiagent debate. In Forty-first International Conference on Machine Learning.
  10. Yilun Du and Igor Mordatch. 2019. Implicit generation and modeling with energy based models. Advances in neural information processing systems, 32. find
  11. Dheeru Dua, Yizhong Wang, Pradeep Dasigi, Gabriel Stanovsky, Sameer Singh, and Matt Gardner. 2019. Drop: A reading comprehension benchmark requiring discrete reasoning over paragraphs. arXiv preprint arXiv:1903.00161.
  12. Gonçalo Faria, Sweta Agrawal, António Farinhas, Ricardo Rei, José de Souza, and André Martins. 2024. QUEST: Quality-aware metropolis-hastings sampling for machine translation. Advances in Neural Information Processing Systems, 37:89042–89068. find
  13. Chrisantha Fernando, Dylan Banarse, Henryk Michalewski, Simon Osindero, and Tim Rocktäschel. 2023. Promptbreeder: Self-referential self-improvement via prompt evolution. arXiv preprint arXiv:2309.16797.
  14. Xingang Guo, Fangxu Yu, Huan Zhang, Lianhui Qin, and Bin Hu. 2024. Cold-attack: Jailbreaking llms with stealthiness and controllability. arXiv preprint arXiv:2402.08679. — [arXiv:2402.08679](https://arxiv.org/abs/2402.08679) find
  15. Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt. 2021. Measuring mathematical problem solving with the math dataset. arXiv preprint arXiv:2103.03874.
  16. Sirui Hong, Yizhang Lin, Bang Liu, Bangbang Liu, Binhao Wu, Danyang Li, Jiaqi Chen, Jiayi Zhang, Jinlin Wang, Li Zhang, Lingyao Zhang, Min Yang, Mingchen Zhuge, Taicheng Guo, Tuo Zhou, Wei Tao, Wenyi Wang, Xiangru Tang, Xiangtao Lu, and 6 others. 2024a. Data interpreter: An LLM agent for data scienc…
  17. Sirui Hong, Mingchen Zhuge, Jonathan Chen, Xiawu Zheng, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, Chenyu Ran, Lingfeng Xiao, Chenglin Wu, and Jürgen Schmidhuber. 2024b. Metagpt: Meta programming for A multi-agent collaborative framework. In ICLR…
  18. Sirui Hong, Mingchen Zhuge, Jonathan Chen, Xiawu Zheng, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, and 1 others. 2023. Metagpt: Meta programming for a multi-agent collaborative framework. In The Twelfth International Conference on Learning Representations.
  19. Shengran Hu, Cong Lu, and Jeff Clune. 2024. Automated design of agentic systems. arXiv preprint arXiv:2408.08435.
  20. Dong Huang, Qingwen Bu, Jie M. Zhang, Michael Luck, and Heming Cui. 2023. Agentcoder: Multi-agent-based code generation with iterative testing and optimisation. CoRR, abs/2312.13010.
  21. Dongfu Jiang, Xiang Ren, and Bill Yuchen Lin. 2023. Llm-blender: Ensembling large language models with pairwise ranking and generative fusion. arXiv preprint arXiv:2306.02561.
  22. Adam Johansen. 2009. A tutorial on particle filtering and smoothing: Fifteen years later. find
  23. Omar Khattab, Arnav Singhvi, Paridhi Maheshwari, Zhiyuan Zhang, Keshav Santhanam, Sri Vardhamanan, Saiful Haq, Ashutosh Sharma, Thomas T Joshi, Hanna Moazam, and 1 others. 2023. Dspy: Compiling declarative language model calls into self-improving pipelines. arXiv preprint arXiv:2310.03714.
  24. Will LeVine, Benjamin Pikus, Anthony Chen, and Sean Hendryx. 2023. A Baseline Analysis of Reward Models’ Ability To Accurately Analyze Foundation Models Under Distribution Shift. arXiv preprint arXiv:2311.14743. — [arXiv:2311.14743](https://arxiv.org/abs/2311.14743) find
  25. Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, and 1 others. 2023. Self-refine: Iterative refinement with self-feedback. Advances in Neural Information Processing Systems, 36:46534–46594. find
  26. Skander Moalla, Andrea Miele, Daniil Pyatko, Razvan Pascanu, and Caglar Gulcehre. 2024. No representation, no trust: connecting representation, collapse, and trust issues in ppo. Advances in Neural Information Processing Systems, 37:69652–69699. find
  27. Fan Nie, Lan Feng, Haotian Ye, Weixin Liang, Pan Lu, Huaxiu Yao, Alexandre Alahi, and James Zou. 2025. Weak-for-strong: Training weak meta-agent to harness strong executors. arXiv preprint arXiv:2504.04785. find
  28. Harsha Nori, Yin Tat Lee, Sheng Zhang, Dean Carignan, Richard Edgar, Nicolò Fusi, Nicholas King, Jonathan Larson, Yuanzhi Li, Weishung Liu, Renqian Luo, Scott Mayer McKinney, Robert Osazuwa Ness, Hoifung Poon, Tao Qin, Naoto Usuyama, Chris White, and Eric Horvitz. 2023. Can generalist foundation mod… find
  29. Boyan Li, Yuyu Luo, Chengliang Chai, Guoliang Li, and Nan Tang. 2024a. The dawn of natural language to SQL: are we fully ready? Proc. VLDB Endow., 17(11):3318–3331. find
  30. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, and 1 others. 2022. Training language models to follow instructions with human feedback. Advances in neural information processing systems, 35:27730–27744.
  31. Guohao Li, Hasan Hammoud, Hani Itani, Dmitrii Khizbullin, and Bernard Ghanem. 2023. Camel: Communicative agents for" mind" exploration of large language model society. Advances in Neural Information Processing Systems, 36:51991–52008.
  32. Shuofei Qiao, Runnan Fang, Zhisong Qiu, Xiaobin Wang, Ningyu Zhang, Yong Jiang, Pengjun Xie, Fei Huang, and Huajun Chen. 2024. Benchmarking agentic workflow generation. arXiv preprint arXiv:2410.07869. — [arXiv:2410.07869](https://arxiv.org/abs/2410.07869) find
  33. Yu Li, Lehui Li, Zhihao Wu, Qingmin Liao, Jianye Hao, Kun Shao, Fengli Xu, and Yong Li. 2025. Agentswift: Efficient llm agent design via value-guided hierarchical search. arXiv preprint arXiv:2506.06017. — [arXiv:2506.06017](https://arxiv.org/abs/2506.06017) find
  34. Lianhui Qin, Sean Welleck, Daniel Khashabi, and Yejin Choi. 2022. Cold decoding: Energy-based constrained text generation with langevin dynamics. Advances in Neural Information Processing Systems, 35:9538–9551. find
  35. Zelong Li, Shuyuan Xu, Kai Mei, Wenyue Hua, Balaji Rama, Om Raheja, Hao Wang, He Zhu, and Yongfeng Zhang. 2024b. Autoflow: Automated workflow generation for large language model agents. arXiv preprint arXiv:2407.12821. — [arXiv:2407.12821](https://arxiv.org/abs/2407.12821) find
  36. David Rein, Betty Li Hou, Asa Cooper Stickland, Jackson Petty, Richard Yuanzhe Pang, Julien Dirani, Julian Michael, and Samuel R Bowman. 2024. Gpqa: A graduate-level google-proof q&a benchmark. In First Conference on Language Modeling.
  37. Tian Liang, Zhiwei He, Wenxiang Jiao, Xing Wang, Yan Wang, Rui Wang, Yujiu Yang, Shuming Shi, and Zhaopeng Tu. 2023. Encouraging divergent thinking in large language models through multi-agent debate. arXiv preprint arXiv:2305.19118.
  38. Matthew Renze and Erhan Guven. 2024. Self-reflection in llm agents: Effects on problem-solving performance. arXiv preprint arXiv:2405.06682.
  39. João Loula, Benjamin LeBrun, Li Du, Ben Lipkin, Clemente Pasti, Gabriel Grand, Tianyu Liu, Yahya Emara, Marjorie Freedman, Jason Eisner, and 1 others. 2025. Syntactic and semantic control of large language models via sequential monte carlo. arXiv preprint arXiv:2504.13139. — [arXiv:2504.13139](https://arxiv.org/abs/2504.13139) find
  40. Tal Ridnik, Dedy Kredo, and Itamar Friedman. 2024. Code generation with alphacodium: From prompt engineering to flow engineering. CoRR, abs/2401.08500. find
  41. Paul B Rohrbach and Robert L Jack. 2022. Convergence of random-weight sequential Monte Carlo methods. arXiv preprint arXiv:2208.12108. — [arXiv:2208.12108](https://arxiv.org/abs/2208.12108) find
  42. Jon Saad-Falcon, Adrian Gamarra Lafuente, Shlok Natarajan, Nahum Maru, Hristo Todorov, Etash Guha, E Kelly Buchanan, Mayee Chen, Neel Guha, Christopher Ré, and 1 others. 2024. Archon: An architecture search framework for inference-time techniques. arXiv preprint arXiv:2409.15254. — [arXiv:2409.15254](https://arxiv.org/abs/2409.15254) find
  43. John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347. find
  44. Yu Shang, Yu Li, Keyu Zhao, Likai Ma, Jiahe Liu, Fengli Xu, and Yong Li. 2024. Agentsquare: Automatic llm agent search in modular design space. arXiv preprint arXiv:2410.06153. — [arXiv:2410.06153](https://arxiv.org/abs/2410.06153) find
  45. Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. 2023. Reflexion: Language agents with verbal reinforcement learning. Advances in Neural Information Processing Systems, 36:8634–8652.
  46. Joar Skalse, Nikolaus Howe, Dmitrii Krasheninnikov, and David Krueger. 2022. Defining and characterizing reward gaming. Advances in Neural Information Processing Systems, 35:9460–9471. find
  47. Nan Tang, Chenyu Yang, Ju Fan, Lei Cao, Yuyu Luo, and Alon Halevy. 2023. Verifai: verified generative ai. arXiv preprint arXiv:2307.02796. — [arXiv:2307.02796](https://arxiv.org/abs/2307.02796) find
  48. Qwen Team. 2024. Qwen2 technical report. arXiv preprint arXiv:2407.10671. find
  49. Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, and Anima Anandkumar. 2023a. Voyager: An open-ended embodied agent with large language models. arXiv preprint arXiv:2305.16291. find
  50. Xinyuan Wang, Chenxi Li, Zhen Wang, Fan Bai, Haotian Luo, Jiayou Zhang, Nebojsa Jojic, Eric P Xing, and Zhiting Hu. 2023b. Promptagent: Strategic planning with language models enables expert-level prompt optimization. arXiv preprint arXiv:2310.16427.
  51. Yubo Wang, Xueguang Ma, Ge Zhang, Yuansheng Ni, Abhranil Chandra, Shiguang Guo, Weiming Ren, Aaran Arulraj, Xuan He, Ziyan Jiang, and 1 others. 2024a. Mmlu-pro: A more robust and challenging multi-task language understanding benchmark. Advances in Neural Information Processing Systems, 37:95266–9529…
  52. Zhenhailong Wang, Shaoguang Mao, Wenshan Wu, Tao Ge, Furu Wei, and Heng Ji. 2024b. Unleashing the emergent cognitive synergy in large language models: A task-solving agent through multi-persona self-collaboration. In Proceedings of the 2024 Conference of the North American Chapter of the Association…
  53. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, and 1 others. 2022a. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, 35:24824– 24837.
  54. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, and 1 others. 2022b. Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35:24824– 24837.
  55. Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Jiale Liu, and 1 others. 2024a. Autogen: Enabling next-gen llm applications via multi-agent conversations. In First Conference on Language Modeling. find
  56. Yangzhen Wu, Zhiqing Sun, Shanda Li, Sean Welleck, and Yiming Yang. 2024b. Inference scaling laws: An empirical analysis of compute-optimal inference for problem-solving with language models. arXiv preprint arXiv:2408.00724.
  57. Yupeng Xie, Yuyu Luo, Guoliang Li, and Nan Tang. 2024. Haichart: Human and AI paired visualization system. Proc. VLDB Endow., 17(11):3178–3191. find
  58. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2022a. Self-consistency improves chain of thought reasoning in language models. arXiv preprint arXiv:2203.11171.
  59. Peiran Xu, Zhuohao Li, Xiaoying Xing, Guannan Zhang, Debiao Li, and Kunyu Shi. 2025. Hybrid Reward Normalization for Process-supervised Non-verifiable Agentic Tasks. arXiv preprint arXiv:2509.25598. — [arXiv:2509.25598](https://arxiv.org/abs/2509.25598) find
  60. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V Le, Ed H Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2022b. Self-consistency improves chain of thought reasoning in language models. In The Eleventh International Conference on Learning Representations.
  61. Chengrun Yang, Xuezhi Wang, Yifeng Lu, Hanxiao Liu, Quoc V Le, Denny Zhou, and Xinyun Chen. 2023. Large language models as optimizers. In The Twelfth International Conference on Learning Representations.
  62. Yinjie Wang, Ling Yang, Guohao Li, Mengdi Wang, and Bryon Aragam. 2025. Scoreflow: Mastering llm agent workflows via score-based preference optimization. arXiv preprint arXiv:2502.04306. — [arXiv:2502.04306](https://arxiv.org/abs/2502.04306) find
  63. Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William W Cohen, Ruslan Salakhutdinov, and Christopher D Manning. 2018. Hotpotqa: A dataset for diverse, explainable multi-hop question answering. arXiv preprint arXiv:1809.09600.
  64. Yilin Ye, Jianing Hao, Yihan Hou, Zhan Wang, Shishi Xiao, Yuyu Luo, and Wei Zeng. 2024. Generative AI for visualization: State of the art and future directions. Vis. Informatics, 8(1):43–66. find
  65. Mert Yuksekgonul, Federico Bianchi, Joseph Boen, Sheng Liu, Zhi Huang, Carlos Guestrin, and James Zou. 2024. Textgrad: Automatic" differentiation" via text. arXiv preprint arXiv:2406.07496.
  66. Guibin Zhang, Luyang Niu, Junfeng Fang, Kun Wang, Lei Bai, and Xiang Wang. 2025. Multi-agent architecture search via agentic supernet. arXiv preprint arXiv:2502.04180. — [arXiv:2502.04180](https://arxiv.org/abs/2502.04180) find
  67. Jiayi Zhang, Jinyu Xiang, Zhaoyang Yu, Fengwei Teng, Xionghui Chen, Jiaqi Chen, Mingchen Zhuge, Xin Cheng, Sirui Hong, Jinlin Wang, and 1 others. 2024a. Aflow: Automating agentic workflow generation. arXiv preprint arXiv:2410.10762.
  68. Jiayi Zhang, Chuang Zhao, Yihan Zhao, Zhaoyang Yu, Ming He, and Jianping Fan. 2024b. Mobileexperts: A dynamic tool-enabled agent team in mobile devices. CoRR, abs/2407.03913. — [arXiv:2407.03913](https://arxiv.org/abs/2407.03913) find
  69. Qinlin Zhao, Jindong Wang, Yixuan Zhang, Yiqiao Jin, Kaijie Zhu, Hao Chen, and Xing Xie. 2023. Competeai: Understanding the competition behaviors in large language model-based agents. CoRR. find
  70. Qihuang Zhong, Kang Wang, Ziyang Xu, Juhua Liu, Liang Ding, Bo Du, and Dacheng Tao. 2024. Achieving\> 97% on gsm8k: Deeply understanding the problems makes llms perfect reasoners. arXiv preprint arXiv:2404.14963. — [arXiv:2404.14963](https://arxiv.org/abs/2404.14963) find
  71. Andy Zhou, Kai Yan, Michal Shlapentokh-Rothman, Haohan Wang, and Yu-Xiong Wang. 2024. Language agent tree search unifies reasoning, acting, and planning in language models. In Forty-first International Conference on Machine Learning. find
  72. Mingchen Zhuge, Haozhe Liu, Francesco Faccio, Dylan R Ashley, Róbert Csordás, Anand Gopalakrishnan, Abdullah Hamdi, Hasan Abed Al Kader Hammoud, Vincent Herrmann, Kazuki Irie, and 1 others. 2023. Mindstorms in natural language-based societies of mind. arXiv preprint arXiv:2305.17066. — [arXiv:2305.17066](https://arxiv.org/abs/2305.17066) find
  73. 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.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/yuan-2026-bayesflow-probability-inference-framework-meta/