Elamur Research⌕
☰
home / papers / 2026 / Self-Evolving Multi-Agent Systems via Textual Backpropagation

Self-Evolving Multi-Agent Systems via Textual Backpropagation

Paper · 2026 · Xiaowen Ma, Yunpu Ma, Chenyang Lin et al.

Summary

Building multi-agent LLM systems usually means hand-crafting prompts, roles and topologies by trial and error. This paper proposes the Agentic Neural Network (ANN), which treats a multi-agent pipeline like a layered neural network. Each layer is a team of agents handling one subtask, and agents act as nodes. In a forward phase, a team-selector agent breaks the task into subtasks, picks a team and an aggregation strategy for each layer from candidate pools, runs the workflow and logs a trajectory. In a backward phase, used only during training, the evaluation outcome is converted into a textual "gradient." It splits into a global signal that revises workflow structure and local signals that edit prompts, nodes and edges. Momentum and validation checks keep these updates stable. At inference the learned pools are frozen and only the forward pass runs. The method is evaluated on MATH, DABench, Creative Writing, HumanEval and MMLU, and the authors report that it beats multi-agent baselines under matched settings. This matters because it automates much of the manual work of designing multi-agent systems.

Key points

  • Two-phase design. Forward team selection is followed by backward textual-gradient optimization. The textual feedback builds on TextGrad-style gradients from Yuksekgonul et al. (2024).
  • Cross-backbone results. Agent teams trained with GPT-4o-mini and evaluated with GPT-4o-mini scored 90.9 on HumanEval, 82.5 on MATH and 90.2 on DABench. Training costs were roughly $122 with GPT-3.5 and $73 with GPT-4o-mini, on about 244.6M input tokens.
  • Ablations. These ran on GPT-4o-mini for 20 epochs, with 3 runs per setting. Each component (momentum, validation filtering, backward pass) contributes to performance. Removing momentum caused the largest drop on HumanEval.
  • Transfer without re-optimization. Agent team pools optimized on MATH improved results on AIME 2024 and AIME 2025 with no further backward optimization, under both GPT-4o-mini and GPT-5.
  • Limitation. The method still needs light human initialization of team structures and prompts.

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

🎓Ludwig-Maximilians-Universität MünchenMunich · Germany107 works · 56,478 citations🎓University of Notre DameNotre Dame · United States51 works · 36,717 citations🎓Technical University of MunichMunich · Germany55 works · 48,474 citations🎓Munich Center for Machine LearningMunich · Germany57 works · 1,094 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

Cite

Cite as Xiaowen Ma, Yunpu Ma, Chenyang Lin, Sikuan Yan, Jinhe Bi, Zixuan Cao, Yijun Tian, Volker Tresp and Hinrich Schuetze. 2026. Self-Evolving Multi-Agent Systems via Textual Backpropagation. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.483

@inproceedings{ma2026self,
  title = {{Self-Evolving Multi-Agent Systems via Textual Backpropagation}},
  author = {Xiaowen Ma, Yunpu Ma, Chenyang Lin, Sikuan Yan, Jinhe Bi, Zixuan Cao, Yijun Tian, Volker Tresp and Hinrich Schuetze},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.483},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.483}
}

References

138 references, 35 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, and 1 others. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774.
  2. Maciej Besta, Nils Blach, Ales Kubicek, Robert Gerstenberger, Michal Podstawski, Lukas Gianinazzi, Joanna Gajda, Tomasz Lehmann, Hubert Niewiadomski, Piotr Nyczyk, and Torsten Hoefler. 2024. Graph of thoughts: Solving elaborate problems with large language models. Proceedings of the AAAI Conference… find
  3. Jinhe Bi, Yifan Wang, Danqi Yan, Xun Xiao, Artur Hecker, Volker Tresp, and Yunpu Ma. 2025a. Prism: Self-pruning intrinsic selection method for training-free multimodal data selection. arXiv preprint arXiv:2502.12119. — [arXiv:2502.12119](https://arxiv.org/abs/2502.12119) find
  4. Jinhe Bi, Yujun Wang, Haokun Chen, Xun Xiao, Artur Hecker, Volker Tresp, and Yunpu Ma. 2024. Visual instruction tuning with 500x fewer parameters through modality linear representation-steering. arXiv preprint arXiv:2412.12359. — [arXiv:2412.12359](https://arxiv.org/abs/2412.12359) find
  5. Jinhe Bi, Danqi Yan, Yifan Wang, Wenke Huang, Haokun Chen, Guancheng Wan, Mang Ye, Xun Xiao, Hinrich Schuetze, Volker Tresp, and 1 others. 2025b. Cot-kinetics: A theoretical modeling assessing lrm reasoning process. arXiv preprint arXiv:2505.13408. — [arXiv:2505.13408](https://arxiv.org/abs/2505.13408) find
  6. Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter,… — Language Models are Few-Shot Learners
  7. Tianle Cai, Xuezhi Wang, Tengyu Ma, Xinyun Chen, and Denny Zhou. 2023. Large language models as tool makers. ArXiv, abs/2305.17126. find
  8. Guangyao Chen, Siwei Dong, Yu Shu, Ge Zhang, Jaward Sesay, Börje F. Karlsson, Jie Fu, and Yemin Shi. 2024. Autoagents: A framework for automatic agent generation. Preprint, arXiv:2309.17288. find
  9. Haokun Chen, Hang Li, Yao Zhang, Jinhe Bi, Gengyuan Zhang, Yueqi Zhang, Philip Torr, Jindong Gu, Denis Krompass, and Volker Tresp. 2025a. Fedbip: Heterogeneous one-shot federated learning with personalized latent diffusion models. In Proceedings of the Computer Vision and Pattern Recognition Confere… find
  10. Haokun Chen, Yueqi Zhang, Yuan Bi, Yao Zhang, Tong Liu, Jinhe Bi, Jian Lan, Jindong Gu, Claudia Grosser, Denis Krompass, and 1 others. 2025b. Does machine unlearning truly remove model knowledge? a framework for auditing unlearning in llms. arXiv preprint arXiv:2505.23270. — [arXiv:2505.23270](https://arxiv.org/abs/2505.23270) find
  11. 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
  12. Weize Chen, Yusheng Su, Jingwei Zuo, Cheng Yang, Chenfei Yuan, Chi-Min Chan, Heyang Yu, Ya-Ting Lu, Yi-Hsin Hung, Cheng Qian, Yujia Qin, Xin Cong, Ruobing Xie, Zhiyuan Liu, Maosong Sun, and Jie Zhou. 2023. Agentverse: Facilitating multi-agent collaboration and exploring emergent behaviors. In Intern…
  13. Zhiwei Chen, Yupeng Hu, Zhiheng Fu, Zixu Li, Jiale Huang, Qinlei Huang, and Yinwei Wei. 2026. Intent: Invariance and discrimination-aware noise mitigation for robust composed image retrieval. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 40, pages 20463–20471. find
  14. Zhiwei Chen, Yupeng Hu, Zixu Li, Zhiheng Fu, Xuemeng Song, and Liqiang Nie. 2025c. Offset: Segmentation-based focus shift revision for composed image retrieval. In Proceedings of the ACM International Conference on Multimedia, page 6113–6122. find
  15. Zhiwei Chen, Yupeng Hu, Zixu Li, Zhiheng Fu, Haokun Wen, and Weili Guan. 2025d. Hud: Hierarchical uncertainty-aware disambiguation network for composed video retrieval. In Proceedings of the ACM International Conference on Multimedia, page 6143–6152. find
  16. Guodong Du, Zitao Fang, Jing Li, Junlin Li, Runhua Jiang, Shuyang Yu, Yifei Guo, Yangneng Chen, Sim Kuan Goh, Ho-Kin Tang, Daojing He, Honghai Liu, and Min Zhang. 2025a. Neural parameter search for slimmer fine-tuned models and better transfer. arXiv preprint arXiv:2505.18713.
  17. Guodong Du, Zitao Fang, Jing Li, Junlin Li, Runhua Jiang, Shuyang Yu, Yifei Guo, Yangneng Chen, Sim Kuan Goh, Ho-Kin Tang, Daojing He, Honghai Liu, and Min Zhang. 2025b. Neural parameter search for slimmer fine-tuned models and better transfer. In Proceedings of the 63rd Annual Meeting of the Associ…
  18. Guodong Du, Junlin Lee, Jing Li, Runhua Jiang, Yifei Guo, Shuyang Yu, Hanting Liu, Sim Kuan Goh, Ho-Kin Tang, Daojing He, and Min Zhang. 2024. Parameter competition balancing for model merging. In The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS). find
  19. Guodong Du, Xuanning Zhou, Junlin Li, Zhuo Li, Zesheng Shi, Wanyu Lin, Ho-Kin Tang, Xiucheng Li, Fangming Liu, Wenya Wang, Min Zhang, and Jing Li. 2025c. Knowledge grafting of large language models. arXiv preprint arXiv:2505.18502. — [arXiv:2505.18502](https://arxiv.org/abs/2505.18502) find
  20. Luyu Gao, Aman Madaan, Shuyan Zhou, Uri Alon, Pengfei Liu, Yiming Yang, Jamie Callan, and Graham Neubig. 2022. Pal: Program-aided language models. ArXiv, abs/2211.10435. find
  21. Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yi Dai, Jiawei Sun, Qianyu Guo, Meng Wang, and Haofen Wang. 2023. Retrieval-augmented generation for large language models: A survey. ArXiv, abs/2312.10997.
  22. Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2020. Measuring massive multitask language understanding. arXiv preprint arXiv:2009.03300.
  23. 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. Preprint, arXiv:2103.03874.
  24. Geoffrey E Hinton, Simon Osindero, and Yee-Whye Teh. 2006. A fast learning algorithm for deep belief nets. Neural computation, 18(7):1527–1554. find
  25. Sirui Hong, Yizhang Lin, Bangbang Liu, Binhao Wu, Danyang Li, Jiaqi Chen, Jiayi Zhang, Jinlin Wang, Lingyao Zhang, Mingchen Zhuge, Taicheng Guo, Tuo Zhou, Wei Tao, Wenyi Wang, Xiangru Tang, Xiangtao Lu, Xinbing Liang, Yaying Fei, Yuheng Cheng, and 6 others. 2024. Data interpreter: An llm agent for d…
  26. Sirui Hong, Xiawu Zheng, Jonathan P. Chen, Yuheng Cheng, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zi Hen Lin, Liyang Zhou, Chenyu Ran, Lingfeng Xiao, and Chenglin Wu. 2023. Metagpt: Meta programming for multi-agent collaborative framework. ArXiv, abs/2308.00352.
  27. Shengran Hu, Cong Lu, and Jeff Clune. 2025. Automated design of agentic systems. Preprint, arXiv:2408.08435. find
  28. Xueyu Hu, Ziyu Zhao, Shuang Wei, Ziwei Chai, Guoyin Wang, Xuwu Wang, Jing Su, Jingjing Xu, Ming Zhu, Yao Cheng, Jianbo Yuan, Kun Kuang, Yang Yang, Hongxia Yang, and Fei Wu. 2024. Infiagent-dabench: Evaluating agents on data analysis tasks. ArXiv, abs/2401.05507. — [arXiv:2401.05507](https://arxiv.org/abs/2401.05507) find
  29. Yupeng Hu, Zixu Li, Zhiwei Chen, Qinlei Huang, Zhiheng Fu, Mingzhu Xu, and Liqiang Nie. 2026. Refine: Composed video retrieval via shared and differential semantics enhancement. ACM Transactions on Multimedia Computing, Communications and Applications. find
  30. Xingyue Huang, Rishabh, Gregor Franke, Ziyi Yang, Jiamu Bai, Weijie Bai, Jinhe Bi, Zifeng Ding, Yiqun Duan, Chengyu Fan, Wendong Fan, Xin Gao, Ruohao Guo, Yuan He, Zhuangzhuang He, Xianglong Hu, Neil Johnson, Bowen Li, Fangru Lin, and 27 others. 2025a. Loong: Synthesize long chain-of-thoughts at sca… — [arXiv:2509.03059](https://arxiv.org/abs/2509.03059) find
  31. Ziwei Huang, Wanggui He, Quanyu Long, Yandi Wang, Haoyuan Li, Zhelun Yu, Fangxun Shu, Long Chan, Hao Jiang, Leilei Gan, and 1 others. 2024. T2i-factualbench: Benchmarking the factuality of text-to-image models with knowledge-intensive concepts. arXiv preprint arXiv:2412.04300.
  32. Ziwei Huang, Ying Shu, Hao Fang, Quanyu Long, Wenya Wang, Qiushi Guo, Tiezheng Ge, and Leilei Gan. 2025b. From competition to synergy: Unlocking reinforcement learning for subject-driven image generation. arXiv preprint arXiv:2510.18263. find
  33. Robert A Jacobs, Michael I Jordan, Steven J Nowlan, and Geoffrey E Hinton. 1991. Adaptive mixtures of local experts. Neural computation, 3(1):79–87. find
  34. Kailin Jiang, Hongbo Jiang, Ning Jiang, Zhi Gao, Jinhe Bi, Yuchen Ren, Bin Li, Yuntao Du, Lei Liu, and Qing Li. 2025a. Kore: Enhancing knowledge injection for large multimodal models via knowledge-oriented augmentations and constraints. Preprint, arXiv:2510.19316. — [arXiv:2510.19316](https://arxiv.org/abs/2510.19316) find
  35. Kailin Jiang, Ning Jiang, Yuntao Du, Yuchen Ren, Yuchen Li, Yifan Gao, Jinhe Bi, Yunpu Ma, Qingqing Liu, Xianhao Wang, Yifan Jia, Hongbo Jiang, Yao-cong Hu, Bin Li, and Lei Liu. 2025b. Mined: Probing and updating with multimodal time-sensitive knowledge for large multimodal models. Preprint, arXiv:2… find
  36. Yue Jiang, Jichu Li, Yang Liu, Dingkang Yang, Feng Zhou, and Quyu Kong. 2025c. Danmakutppbench: A multi-modal benchmark for temporal point process modeling and understanding. In NeurIPS. find
  37. Yue Jiang, Haiwei Xue, Minghao Han, Mingcheng Li, Xiaolu Hou, Dingkang Yang, Lihua Zhang, and Xu Zheng. 2026. Satiredecoder: Visual cascaded decoupling for enhancing satirical image comprehension. In AAAI. find
  38. Jinyang Li, Nan Huo, Yan Gao, Jiayi Shi, Yingxiu Zhao, Ge Qu, Yurong Wu, Chenhao Ma, Jian-Guang Lou, and Reynold Cheng. 2024a. Tapilot-crossing: Benchmarking and evolving llms towards interactive data analysis agents. arXiv preprint arXiv:2403.05307. — [arXiv:2403.05307](https://arxiv.org/abs/2403.05307) find
  39. Carlos E Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik Narasimhan. 2023. Swe-bench: Can language models resolve real-world github issues? arXiv preprint arXiv:2310.06770.
  40. 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. Preprint, arXiv:2407.12821. — [arXiv:2407.12821](https://arxiv.org/abs/2407.12821) find
  41. Zixuan Ke, Austin Xu, Yifei Ming, Xuan-Phi Nguyen, Caiming Xiong, and Shafiq Joty. 2025. Mas-zero: Designing multi-agent systems with zero supervision. Preprint, arXiv:2505.14996. — [arXiv:2505.14996](https://arxiv.org/abs/2505.14996) find
  42. Ziming Li, Xiaoming Wu, Zehong Wang, Jiazheng Li, Yijun Tian, Jinhe Bi, Yunpu Ma, Yanfang Ye, and Chuxu Zhang. 2026a. Graph is a substrate across data modalities. Preprint, arXiv:2601.22384. — [arXiv:2601.22384](https://arxiv.org/abs/2601.22384) find
  43. O. Khattab, Arnav Singhvi, Paridhi Maheshwari, Zhiyuan Zhang, Keshav Santhanam, Sri Vardhamanan, Saiful Haq, Ashutosh Sharma, Thomas T. Joshi, Hanna Moazam, Heather Miller, Matei Zaharia, and Christopher Potts. 2023a. Dspy: Compiling declarative language model calls into self-improving pipelines. Ar…
  44. Zixu Li, Zhiwei Chen, Haokun Wen, Zhiheng Fu, Yupeng Hu, and Weili Guan. 2025a. Encoder: Entity mining and modification relation binding for composed image retrieval. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 5101–5109. find
  45. O. Khattab, Arnav Singhvi, Paridhi Maheshwari, Zhiyuan Zhang, Keshav Santhanam, Sri Vardhamanan, Saiful Haq, Ashutosh Sharma, Thomas T. Joshi, Hanna Moazam, Heather Miller, Matei Zaharia, and Christopher Potts. 2024. Dspy: Compiling declarative language model calls into state-of-the-art pipelines. I… find
  46. Omar Khattab, Arnav Singhvi, Paridhi Maheshwari, Zhiyuan Zhang, Keshav Santhanam, Sri Vardhamanan, Saiful Haq, Ashutosh Sharma, Thomas T. Joshi, Hanna Moazam, Heather Miller, Matei Zaharia, and Christopher Potts. 2023b. Dspy: Compiling declarative language model calls into self-improving pipelines.…
  47. Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. Large language models are zero-shot reasoners. Advances in neural information processing systems, 35:22199– 22213.
  48. Taehyun Lee, Seokhee Hong, Jaewoo Ahn, Ilgee Hong, Hwaran Lee, Sangdoo Yun, Jamin Shin, and Gunhee Kim. 2023. Who wrote this code? watermarking for code generation. arXiv preprint arXiv:2305.15060.
  49. Yu-Ang Lee, Guan-Ting Yi, Mei-Yi Liu, Jui-Chao Lu, Guan-Bo Yang, and Yun-Nung Chen. 2025. Compound ai systems optimization: A survey of methods, challenges, and future directions. Preprint, arXiv:2506.08234. find
  50. Patrick Lewis, Ethan Perez, Aleksandara Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Kuttler, Mike Lewis, Wen tau Yih, Tim Rocktäschel, Sebastian Riedel, and Douwe Kiela. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. ArXiv, abs/2005.11401.
  51. Zixu Li, Zhiheng Fu, Yupeng Hu, Zhiwei Chen, Haokun Wen, and Liqiang Nie. 2025b. Finecir: Explicit parsing of fine-grained modification semantics for composed image retrieval. https://arxiv.org/abs/2503.21309. — [arXiv:2503.21309](https://arxiv.org/abs/2503.21309) ↗
  52. Zixu Li, Yupeng Hu, Zhiwei Chen, Qinlei Huang, Guozhi Qiu, Zhiheng Fu, and Meng Liu. 2026b. Retrack: Evidence-driven dual-stream directional anchor calibration network for composed video retrieval. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 40, pages 23373–23381. find
  53. Zixu Li, Yupeng Hu, Zhiwei Chen, Shiqi Zhang, Qinlei Huang, Zhiheng Fu, and Yinwei Wei. 2026c. Habit: Chrono-synergia robust progressive learning framework for composed image retrieval. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 40, pages 6762–6770. find
  54. Fengyuan Liu, Nouar AlDahoul, Gregory Eady, Yasir Zaki, Bedoor AlShebli, and Talal Rahwan. 2024a. Self-reflection outcome is sensitive to prompt construction. arXiv preprint arXiv:2406.10400. — [arXiv:2406.10400](https://arxiv.org/abs/2406.10400) find
  55. Fengyuan Liu, Nouar AlDahoul, Gregory Eady, Yasir Zaki, Bedoor AlShebli, and Talal Rahwan. 2024b. Self-reflection outcome is sensitive to prompt construction. arXiv preprint arXiv:2406.10400. — [arXiv:2406.10400](https://arxiv.org/abs/2406.10400) find
  56. Sibei Liu, Yuanzhe Zhang, Xiang Li, Yunbo Liu, Chengwei Feng, and Hao Yang. 2025. Gated multimodal graph learning for personalized recommendation. INNO-PRESS: Journal of Emerging Applied AI, 1(1). find
  57. Wei Liu, Haozhao Wang, Jun Wang, Ruixuan Li, Xinyang Li, Yuankai Zhang, and Yang Qiu. 2023. Mgr: Multi-generator based rationalization. Preprint, arXiv:2305.04492. find
  58. Wei Liu, Haozhao Wang, Jun Wang, Ruixuan Li, Chao Yue, and Yuankai Zhang. 2022. Fr: Folded rationalization with a unified encoder. Preprint, arXiv:2209.08285. — [arXiv:2209.08285](https://arxiv.org/abs/2209.08285) find
  59. 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
  60. Zijun Liu, Yanzhe Zhang, Peng Li, Yang Liu, and Diyi Yang. 2024c. A dynamic llm-powered agent network for task-oriented agent collaboration. In First Conference on Language Modeling. find
  61. Xuankun Rong, Wenke Huang, Jian Liang, Jinhe Bi, Xun Xiao, Yiming Li, Bo Du, and Mang Ye. 2025. Backdoor cleaning without external guidance in mllm fine-tuning. arXiv preprint arXiv:2505.16916. — [arXiv:2505.16916](https://arxiv.org/abs/2505.16916) find
  62. Shilin Lu, Yanzhu Liu, and Adams Wai-Kin Kong. 2023. Tf-icon: Diffusion-based training-free cross-domain image composition. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 2294–2305. find
  63. Shilin Lu, Zilan Wang, Leyang Li, Yanzhu Liu, and Adams Wai-Kin Kong. 2024. Mace: Mass concept erasure in diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6430–6440. find
  64. Zhengyang Lu and Ying Chen. 2019. Single image super resolution based on a modified u-net with mixed gradient loss. Preprint, arXiv:1911.09428. — [arXiv:1911.09428](https://arxiv.org/abs/1911.09428) find
  65. Zhengyang Lu and Ying Chen. 2022. Pyramid frequency network with spatial attention residual refinement module for monocular depth estimation. Journal of Electronic Imaging, 31(02). find
  66. Zhengyang Lu and Ying Chen. 2023. Joint self-supervised depth and optical flow estimation towards dynamic objects. Neural Processing Letters, 55(8):10235–10249. find
  67. Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, Sean Welleck, Bodhisattwa Prasad Majumder, Shashank Gupta, Amir Yazdanbakhsh, and Peter Clark. 2023. Self-refine: Iterative refinement with self-feedback. ArX… find
  68. 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.
  69. Tianfan Peng, Yuntao Du, Pengzhou Ji, Shijie Dong, Kailin Jiang, Mingchuan Ma, Yijun Tian, Jinhe Bi, Qian Li, Wei Du, Feng Xiao, and Lizhen Cui. 2025. Can visual input be compressed? a visual token compression benchmark for large multimodal models. Preprint, arXiv:2511.02650. — [arXiv:2511.02650](https://arxiv.org/abs/2511.02650) find
  70. Cheng 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, abs/2406.07155. find
  71. Alec Radford, Karthik Narasimhan, Tim Salimans, Ilya Sutskever, and 1 others. 2018. Improving language understanding by generative pre-training. Preprint. find
  72. Noam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz, Andy Davis, Quoc Le, Geoffrey Hinton, and Jeff Dean. 2017. Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. Preprint, arXiv:1701.06538. find
  73. Noah Shinn, Federico Cassano, Beck Labash, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. 2023. Reflexion: language agents with verbal reinforcement learning. In Neural Information Processing Systems.
  74. Linxin Song, Jiale Liu, Jieyu Zhang, Shaokun Zhang, Ao Luo, Shijian Wang, Qingyun Wu, and Chi Wang. 2024. Adaptive in-conversation team building for language model agents. Preprint, arXiv:2405.19425. — [arXiv:2405.19425](https://arxiv.org/abs/2405.19425) find
  75. Mirac Suzgun and Adam Tauman Kalai. 2024. Meta-prompting: Enhancing language models with task-agnostic scaffolding. Preprint, arXiv:2401.12954.
  76. Yijun Tian, Shaoyu Chen, Zhichao Xu, Yawei Wang, Jinhe Bi, Peng Han, and Wei Wang. 2025. Reinforcement mid-training. Preprint, arXiv:2509.24375. — [arXiv:2509.24375](https://arxiv.org/abs/2509.24375) find
  77. Yijun Tian, Kaiwen Dong, Chunhui Zhang, Chuxu Zhang, and Nitesh V Chawla. 2023a. Heterogeneous graph masked autoencoders. In Proceedings of the AAAI conference on artificial intelligence, pages 9997–10005. find
  78. Yijun Tian, Huan Song, Zichen Wang, Haozhu Wang, Ziqing Hu, Fang Wang, Nitesh V Chawla, and Panpan Xu. 2024. Graph neural prompting with large language models. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 19080–19088. find
  79. Yijun Tian, Chuxu Zhang, Zhichun Guo, Xiangliang Zhang, and Nitesh Chawla. 2023b. Learning MLPs on graphs: A unified view of effectiveness, robustness, and efficiency. In International Conference on Learning Representations. find
  80. Ashwin Verma. 2024. Advances in Multi-agent Decision Making Systems with Adaptive Algorithms. Ph.D. thesis, University of California, San Diego. find
  81. Guancheng Wan, Lucheng Fu, Haoxin Liu, Yiqiao Jin, Hui Yi Leong, Eric Hanchen Jiang, Hejia Geng, Jinhe Bi, Yunpu Ma, Xiangru Tang, B. Aditya Prakash, Yizhou Sun, and Wei Wang. 2025a. Beyond magic words: Sharpness-aware prompt evolving for robust large language models with tare. Preprint, arXiv:2509.… — [arXiv:2509.24130](https://arxiv.org/abs/2509.24130) find
  82. Guancheng Wan, Wenke Huang, and Mang Ye. 2024. Federated graph learning under domain shift with generalizable prototypes. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 15429– 15437. find
  83. Zhiyuan Wang, Tianlong Chen, Yue Zhang, Heng Tao Shen, Xiaoshuang Shi, Kaidi Xu, and 1 others. 2025g. Lec: Linear expectation constraints for false-discovery control in selective prediction and routing systems. arXiv preprint arXiv:2512.01556. — [arXiv:2512.01556](https://arxiv.org/abs/2512.01556) find
  84. Guancheng Wan, Xiaoran Shang, Yuxin Wu, Guibin Zhang, Jinhe Bi, Liangtao Zheng, Xin Lin, Yue Liu, Yanbiao Ma, Wenke Huang, and Bo Du. 2025b. HY-PERION: Fine-grained hypersphere alignment for robust federated graph learning. In The Thirty-ninth Annual Conference on Neural Information Processing Syste… find
  85. Zhiyuan Wang, Jinhao Duan, Lu Cheng, Yue Zhang, Qingni Wang, Xiaoshuang Shi, Kaidi Xu, Heng Tao Shen, and Xiaofeng Zhu. 2024d. ConU: Conformal uncertainty in large language models with correctness coverage guarantees. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 68… find
  86. Chao Wang, Chuanhao Nie, and Yunbo Liu. 2025a. Evaluating supervised learning models for fraud detection: A comparative study of classical and deep architectures on imbalanced transaction data. arXiv preprint arXiv:2505.22521. — [arXiv:2505.22521](https://arxiv.org/abs/2505.22521) find
  87. Zhiyuan Wang, Jinhao Duan, Qingni Wang, Xiaofeng Zhu, Tianlong Chen, Xiaoshuang Shi, and Kaidi Xu. 2026. Coin: Uncertainty-guarding selective question answering for foundation models with provable risk guarantees. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 40, pages 337… find
  88. Fei Wang, Xingchen Wan, Ruoxi Sun, Jiefeng Chen, and Sercan Ö Arık. 2024a. Astute rag: Overcoming imperfect retrieval augmentation and knowledge conflicts for large language models. arXiv preprint arXiv:2410.07176.
  89. Junlin Wang, Jue Wang, Ben Athiwaratkun, Ce Zhang, and James Zou. 2024b. Mixture-of-agents enhances large language model capabilities. Preprint, arXiv:2406.04692. find
  90. Yikun Wang, Zuyan Liu, Ziyi Wang, Han Hu, Pengfei Liu, and Yongming Rao. 2025b. Geovista: Web-augmented agentic visual reasoning for geolocalization. Preprint, arXiv:2511.15705. — [arXiv:2511.15705](https://arxiv.org/abs/2511.15705) find
  91. Yikun Wang, Siyin Wang, Qinyuan Cheng, Zhaoye Fei, Liang Ding, Qipeng Guo, Dacheng Tao, and Xipeng Qiu. 2025c. VisuoThink: Empowering LVLM reasoning with multimodal tree search. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages…
  92. Yikun Wang, Siyin Wang, Qinyuan Cheng, Zhaoye Fei, Liang Ding, Qipeng Guo, Dacheng Tao, and Xipeng Qiu. 2025d. Visuothink: Empowering lvlm reasoning with multimodal tree search. Preprint, arXiv:2504.09130.
  93. Yikun Wang, Yibin Wang, Dianyi Wang, Zimian Peng, Qipeng Guo, Dacheng Tao, and Jiaqi Wang. 2025e. Geometryzero: Improving geometry solving for llm with group contrastive policy optimization. Preprint, arXiv:2506.07160. — [arXiv:2506.07160](https://arxiv.org/abs/2506.07160) find
  94. Yikun Wang, Rui Zheng, Haoming Li, Qi Zhang, Tao Gui, and Fei Liu. 2024c. Rescue: Ranking llm responses with partial ordering to improve response generation. Preprint, arXiv:2311.09136. find
  95. Yujun Wang, Jinhe Bi, Yunpu Ma, and Soeren Pirk. 2025f. Ascd: Attention-steerable contrastive decoding for reducing hallucination in mllm. arXiv preprint arXiv:2506.14766. — [arXiv:2506.14766](https://arxiv.org/abs/2506.14766) find
  96. Zhiyuan Wang, Jinhao Duan, Chenxi Yuan, Qingyu Chen, Tianlong Chen, Yue Zhang, Ren Wang, Xiaoshuang Shi, and Kaidi Xu. 2025h. Word-sequence entropy: Towards uncertainty estimation in free-form medical question answering applications and beyond. Engineering Applications of Artificial Intelligence, 13… find
  97. Zhiyuan Wang, Qingni Wang, Yue Zhang, Tianlong Chen, Xiaofeng Zhu, Xiaoshuang Shi, and Kaidi Xu. 2025i. SConU: Selective conformal uncertainty in large language models. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 19052– 19… find
  98. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Ed H. Chi, F. Xia, Quoc Le, and Denny Zhou. 2022. Chain of thought prompting elicits reasoning in large language models. ArXiv, abs/2201.11903.
  99. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed Chi, Quoc Le, and Denny Zhou. 2023. Chain-of-thought prompting elicits reasoning in large language models. Preprint, arXiv:2201.11903.
  100. Jinfeng Wei and Xiaofeng Zhang. 2024. Dopra: Decoding over-accumulation penalization and re-allocation in specific weighting layer. Proceedings of the 32nd ACM International Conference on Multimedia. find
  101. Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Jiale Liu, and 1 others. 2023. Autogen: Enabling next-gen llm applications via multi-agent conversation. arXiv preprint arXiv:2308.08155.
  102. Zikai Xiao, Zihan Chen, Liyinglan Liu, YANG FENG, Joey Tianyi Zhou, Jian Wu, Wanlu Liu, Howard Hao Yang, and Zuozhu Liu. 2024. Fedloge: Joint local and generic federated learning under long-tailed data. In The Twelfth International Conference on Learning Representations. find
  103. Zikai Xiao, Zihan Chen, Songshang Liu, Hualiang Wang, YANG FENG, Jin Hao, Joey Tianyi Zhou, Jian Wu, Howard Yang, and Zuozhu Liu. 2023. Fed-grab: Federated long-tailed learning with self-adjusting gradient balancer. In Advances in Neural Information Processing Systems, volume 36, pages 77745–77757.… find
  104. Chenghao Xu, Guangtao Lyu, Jiexi Yan, Muli Yang, and Cheng Deng. 2024. LLM knows body language, too: Translating speech voices into human gestures. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5004–5013, Bangkok, Thailand.… find
  105. Rong Xuankun, Zhang Jianshu, He Kun, and Mang Ye. 2025. Can: Leveraging clients as navigators for generative replay in federated continual learning. In ICML. find
  106. Chengrun Yang, Xuezhi Wang, Yifeng Lu, Hanxiao Liu, Quoc V. Le, Denny Zhou, and Xinyun Chen. 2023. Large language models as optimizers. ArXiv, abs/2309.03409.
  107. Chengrun Yang, Xuezhi Wang, Yifeng Lu, Hanxiao Liu, Quoc V. Le, Denny Zhou, and Xinyun Chen. 2024. Large language models as optimizers. Preprint, arXiv:2309.03409.
  108. Haoyue Yang, Xuanle Zhao, Xuexin Liu, Feibang Jiang, and Yao Zhu. 2026a. Omnidiagram: Advancing unified diagram code generation via visual interrogation reward. Preprint, arXiv:2604.05514.
  109. Minglai Yang, Xinyu Guo, Zhengliang Shi, Jinhe Bi, Steven Bethard, Mihai Surdeanu, and Liangming Pan. 2026b. Alignsae: Concept-aligned sparse autoencoders. Preprint, arXiv:2512.02004. — [arXiv:2512.02004](https://arxiv.org/abs/2512.02004) find
  110. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2022. React: Synergizing reasoning and acting in language models. ArXiv, abs/2210.03629.
  111. Xinlei Yu, Ahmed Elazab, Ruiquan Ge, Jichao Zhu, Lingyan Zhang, Gangyong Jia, Qing Wu, Xiang Wan, Lihua Li, and Changmiao Wang. 2025. Ich-prnet: a cross-modal intracerebral haemorrhage prognostic prediction method using joint-attention interaction mechanism. Neural Networks, 184:107096. find
  112. Jiahao Yuan, Yike Xu, Jinyong Wen, Baokun Wang, Ziyi Gao, Xiaotong Lin, Yun Liu, Xing Fu, Yu Cheng, Yongchao Liu, and 1 others. 2026b. Query as anchor: Scenario-adaptive user representation via large language model. arXiv preprint arXiv:2602.14492. — [arXiv:2602.14492](https://arxiv.org/abs/2602.14492) find
  113. Mert Yuksekgonul, Federico Bianchi, Joseph Boen, Sheng Liu, Zhi Huang, Carlos Guestrin, and James Zou. 2024. Textgrad: Automatic "differentiation" via text. Preprint, arXiv:2406.07496.
  114. Zhi Zeng, Minnan Luo, Xiangzheng Kong, Huan Liu, Hao Guo, Hao Yang, Zihan Ma, and Xiang Zhao. 2024. Mitigating world biases: A multimodal multi-view debiasing framework for fake news video detection. In Proceedings of the 32nd ACM International Conference on Multimedia, pages 6492–6500. find
  115. Gengyuan Zhang, Jinhe Bi, Jindong Gu, Yanyu Chen, and Volker Tresp. 2023. Spot! revisiting video-language models for event understanding. arXiv preprint arXiv:2311.12919. — [arXiv:2311.12919](https://arxiv.org/abs/2311.12919) find
  116. 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. find
  117. Xiaofeng Zhang, Yihao Quan, Chaochen Gu, Chen Shen, Xiaosong Yuan, Shaotian Yan, Hao Cheng, Kaijie Wu, and Jieping Ye. 2025a. Shallow focus, deep fixes: Enhancing shallow layers vision attention sinks to alleviate hallucination in lvlms. pages 3512–3534.
  118. Xiaofeng Zhang, Chen Shen, Xiaosong Yuan, Shaotian Yan, Liang Xie, Wenxiao Wang, Chaochen Gu, Hao Tang, and Jieping Ye. 2024b. From redundancy to relevance: Enhancing explainability in multimodal large language models. NAACL. find
  119. Xiaofeng Zhang, Fanshuo Zeng, and Chaochen Gu. 2024c. Simignore: Exploring and enhancing multimodal large model complex reasoning via similarity computation. Neural Networks, page 107059. find
  120. Xiaofeng Zhang, Fanshuo Zeng, Yihao Quan, Zheng Hui, and Jiawei Yao. 2025b. Enhancing multimodal large language models complex reason via similarity computation. Proceedings of the AAAI Conference on Artificial Intelligence. find
  121. Jiahao Yuan, Zhiqing Cui, Hanqing Wang, Yuansheng Gao, Yucheng Zhou, and Usman Naseem. 2025. Kardia-r1: Unleashing llms to reason toward understanding and empathy for emotional support via rubric-as-judge reinforcement learning. arXiv preprint arXiv:2512.01282. — [arXiv:2512.01282](https://arxiv.org/abs/2512.01282) find
  122. Xiaofeng Zhang, Yuanchao Zhu, Chaochen Gu, Jiawei Cao, Hao Cheng, and Kaijie Wu. 2026a. What drives attention sinks? a study of massive activations and rotational positional encoding in large vision–language models. Information Processing & Management, 63(2):104431. find
  123. Jiahao Yuan, Yike Xu, Jinyong Wen, Baokun Wang, Yang Chen, Xiaotong Lin, Wuliang Huang, Ziyi Gao, Xing Fu, Yu Cheng, and 1 others. 2026a. How do decoder-only llms perceive users? rethinking attention masking for user representation learning. arXiv preprint arXiv:2602.10622. — [arXiv:2602.10622](https://arxiv.org/abs/2602.10622) find
  124. Xiaofeng Zhang, Yuanchao Zhu, Chaochen Gu, Xiaosong Yuan, Qiyan Zhao, Jiawei Cao, Feilong Tang, Sinan Fan, Yaomin Shen, Chen Shen, and 1 others. 2026b. Hallucination begins where saliency drops. In The Fourteenth International Conference on Learning Representations. find
  125. Yao Zhang, Chenyang Lin, Shijie Tang, Haokun Chen, Shijie Zhou, Yunpu Ma, and Volker Tresp. 2025c. Swarmagentic: Towards fully automated agentic system generation via swarm intelligence. Preprint, arXiv:2506.15672. find
  126. Jinman Zhao and Xueyan Zhang. 2024. Large language model is not a (multilingual) compositional relation reasoner. In First Conference on Language Modeling. find
  127. Qiyan Zhao, Xiaofeng Zhang, Shuochen Chang, Qianyu Chen, Xiaosong Yuan, Xuhang Chen, Luoqi Liu, Jiajun Zhang, Xu-Yao Zhang, and Da-Han Wang. 2026a. Context tokens are anchors: Understanding the repetition curse in dmllms from an information flow perspective. In The Fourteenth International Conferenc… find
  128. Qiyan Zhao, Xiaofeng Zhang, yiheng Li, Yun Xing, Yuan Xiaosong, Feilong Tang, Sinan Fan, Xuhang Chen, Xuyao Zhang, and Dahan Wang. 2025a. Mca-llava: Manhattan causal attention for reducing hallucination in large vision-language models. Proceedings of the 32nd ACM International Conference on Multimed… find
  129. Chen, Wentao Zhang, Xiangru Tang, Ningyu Zhang, Huajun Chen, Peng Cui, and Mrinmaya Sachan. 2023. Agents: An open-source framework for autonomous language agents. Preprint, arXiv:2309.07870. find
  130. Wangchunshu Zhou, Yixin Ou, Shengwei Ding, Long Li, Jialong Wu, Tiannan Wang, Jiamin Chen, Shuai Wang, Xiaohua Xu, Ningyu Zhang, Huajun Chen, and Yuchen Eleanor Jiang. 2024. Symbolic learning enables self-evolving agents. Preprint, arXiv:2406.18532.
  131. Mingchen Zhuge, Wenyi Wang, Louis Kirsch, Francesco Faccio, Dmitrii Khizbullin, and Jürgen Schmidhuber. 2024a. Gptswarm: Language agents as optimizable graphs. In Forty-first International Conference on Machine Learning. find
  132. Mingchen Zhuge, Wenyi Wang, Louis Kirsch, Francesco Faccio, Dmitrii Khizbullin, and Jürgen Schmidhuber. 2024b. Language agents as optimizable graphs. ArXiv, abs/2402.16823. find
  133. Xuanle Zhao, Deyang Jiang, Zhixiong Zeng, Lei Chen, Haibo Qiu, Jing Huang, Yufeng Zhong, Liming Zheng, Yilin Cao, and Lin Ma. 2025b. Vincicoder: Unifying multimodal code generation via coarse-to-fine visual reinforcement learning. arXiv preprint arXiv:2511.00391. — [arXiv:2511.00391](https://arxiv.org/abs/2511.00391) find
  134. Xuanle Zhao, Xianzhen Luo, Qi Shi, Chi Chen, Shuo Wang, Zhiyuan Liu, and Maosong Sun. 2025c. Chartcoder: Advancing multimodal large language model for chart-to-code generation. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7…
  135. Xuanle Zhao, Zilin Sang, Yuxuan Li, Qi Shi, Weilun Zhao, Shuo Wang, Duzhen Zhang, Xu Han, Zhiyuan Liu, and Maosong Sun. 2025d. Autoreproduce: Automatic ai experiment reproduction with paper lineage. arXiv preprint arXiv:2505.20662. find
  136. Xuanle Zhao, Shuxin Zeng, Xinyuan Cai, Xiang Cheng, Duzhen Zhang, Xiuyi Chen, and Bo Xu. 2026b. Tinychemvl: Advancing chemical vision-language models via efficient visual token reduction and complex reaction tasks. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 40, pages 15… find
  137. Huaixiu Steven Zheng, Swaroop Mishra, Hugh Zhang, Xinyun Chen, Minmin Chen, Azade Nova, Le Hou, Heng-Tze Cheng, Quoc V. Le, Ed H. Chi, and Denny Zhou. 2024. Natural plan: Benchmarking llms on natural language planning. Preprint, arXiv:2406.04520. find
  138. Wangchunshu Zhou, Yuchen Eleanor Jiang, Long Li, Jialong Wu, Tiannan Wang, Shi Qiu, Jintian Zhang, Jing Chen, Ruipu Wu, Shuai Wang, Shiding Zhu, Jiyu Contents \#\# Introduction Related Works find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/ma-2026-self-evolving-multi-agent-systems/