Elamur Research⌕
☰
home / papers / 2026 / ReCreate: Reasoning and Creating Domain Agents Driven by Experience

ReCreate: Reasoning and Creating Domain Agents Driven by Experience

Paper · 2026 · Zhezheng Hao, Hong Wang, Jian Luo et al.

Summary

Most practical LLM agents still depend on scaffolds that people write by hand: prompts, workflows, tools, and memory. This is costly and hard to scale across many domains. Earlier automated agent generators, such as ADAS, optimize scaffolds as a black box guided only by final scores. That approach reveals little about why an agent failed and requires expensive repeated evaluation.

ReCreate takes a white-box approach. A strong LLM acts as the optimizer and inspects interaction experience (trajectories, execution and evaluation logs, environment state) to decide concrete scaffold edits, such as new rules, new tools, or reordered workflows. The design has three parts:

  • a store that lets the optimizer retrieve experience on demand,
  • a pipeline that turns reasoning over that evidence into scaffold changes,
  • hierarchical updates that generalize fixes for single tasks into domain-level patterns.

Across thirteen benchmarks in four domains, ReCreate beats both human-designed agents and automated baselines, even when it starts from minimal seed scaffolds, and it costs less to run. This suggests that frontier models can increasingly take over expert scaffold engineering.

Key points

  • The scaffold is split into four editable modules: Role & Object, Process & Strategy, Action & Tool, and Memory & Retrieval. The evaluation domains are software engineering (SWE-bench), data science (DA-Code, DS-1000), math, and digital tasks, with gpt-5-mini as the task agent.
  • In the ablations, the full system scores 60.19 on SWE, 39.77 on DA-Code, and 77.74 on DS. Removing the creation router or the domain-level update lowers all three scores, for example SWE drops to 58.00 or 57.09.
  • With Claude-opus as the optimizer, the generated scaffolds consistently outperform human-designed ones. A gpt-5-mini optimizer mostly does not, so the optimizer's reasoning strength is crucial.
  • Scaffold optimization costs roughly 36–82% less than ADAS. For comparison, ADAS needs about $500 for a single ARC run on 20 samples.
  • One experience-derived fix illustrates the approach: on SWE-bench, adding a pre-submission git diff --cached check alone raised the pass rate by over 2%. Code is available at github.com/zz-haooo/ReCreate.

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

🏢TencentShenzhen · China134 works · 19,743 citations🎓Shanghai Jiao Tong UniversityShanghai · China149 works · 16,161 citations🎓Zhejiang UniversityHangzhou · China172 works · 12,988 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

🧭 Topics 1Research subjects and languages the work is about.Reasoning · 1,426 works

Cite

Cite as Zhezheng Hao, Hong Wang, Jian Luo, Jianqing Zhang, Yuyan Zhou, Qiang Lin, Can Wang, Hande Dong and Jiawei Chen. 2026. ReCreate: Reasoning and Creating Domain Agents Driven by Experience. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.acl-long.1432

@inproceedings{hao2026recreate,
  title = {{ReCreate: Reasoning and Creating Domain Agents Driven by Experience}},
  author = {Zhezheng Hao, Hong Wang, Jian Luo, Jianqing Zhang, Yuyan Zhou, Qiang Lin, Can Wang, Hande Dong and Jiawei Chen},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.1432},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1432}
}

References

88 references, 29 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Anthropic. 2025a. Introducing claude opus 4.5. https://www.anthropic.com/news/claude-opus-4-5. ↗
  2. Anthropic. 2025b. Raising the bar on swe-bench verified with claude 3.5 sonnet. https://www.anthropic.com/engineering/ swe-bench-sonnet. ↗
  3. Sikai Bai, Haoxi Li, Jie Zhang, Yongjiang Liu, and Song Guo. 2026. Ttvs: Boosting self-exploring reinforcement learning via test-time variational synthesis. Preprint, arXiv:2604.08468. find
  4. Yupeng Chang, Xu Wang, Jindong Wang, Yuan Wu, Linyi Yang, Kaijie Zhu, Hao Chen, Xiaoyuan Yi, Cunxiang Wang, Yidong Wang, and 1 others. 2024. A survey on evaluation of large language models. ACM transactions on intelligent systems and technology, 15(3):1–45.
  5. Jiawei Chen, Hande Dong, Xiang Wang, Fuli Feng, Meng Wang, and Xiangnan He. 2023. Bias and debias in recommender system: A survey and future directions. ACM Transactions on Information Systems, 41(3):1–39. find
  6. Zihao Cheng, Zeming Liu, Yingyu Shan, Xinyi Wang, Xiangrong Zhu, Yunpu Ma, Hongru Wang, Yuhang Guo, Wei Lin, and Yunhong Wang. 2026. Mem 2 evolve: Towards self-evolving agents via co-evolutionary capability expansion and experience distillation. Preprint, arXiv:2604.10923.
  7. Prateek Chhikara, Dev Khant, Saket Aryan, Taranjeet Singh, and Deshraj Yadav. 2025. Mem0: Building production-ready ai agents with scalable long-term memory. arXiv preprint arXiv:2504.19413.
  8. François Chollet. 2019. On the measure of intelligence. arXiv preprint arXiv:1911.01547. find
  9. Yu Cui, Feng Liu, Jiawei Chen, Canghong Jin, Xingyu Lou, Changwang Zhang, Jun Wang, Yuegang Sun, and Can Wang. 2025. Hatllm: Hierarchical attention masking for enhanced collaborative modeling in llm-based recommendation. arXiv preprint arXiv:2510.10955. — [arXiv:2510.10955](https://arxiv.org/abs/2510.10955) find
  10. 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.
  11. Chongming Gao, Kexin Huang, Jiawei Chen, Yuan Zhang, Biao Li, Peng Jiang, Shiqi Wang, Zhong Zhang, and Xiangnan He. 2023a. Alleviating matthew effect of offline reinforcement learning in interactive recommendation. In Proceedings of the 46th international ACM SIGIR conference on research and develop… find
  12. Chongming Gao, Shiqi Wang, Shijun Li, Jiawei Chen, Xiangnan He, Wenqiang Lei, Biao Li, Yuan Zhang, and Peng Jiang. 2023b. Cirs: Bursting filter bubbles by counterfactual interactive recommender system. ACM Transactions on Information Systems, 42(1):1– 27. find
  13. Hongcheng Gao, Yue Liu, Yufei He, Longxu Dou, Chao Du, Zhijie Deng, Bryan Hooi, Min Lin, and Tianyu Pang. 2025. Flowreasoner: Reinforcing query-level meta-agents. arXiv preprint arXiv:2504.15257. — [arXiv:2504.15257](https://arxiv.org/abs/2504.15257) find
  14. Google. 2025. A new era of intelligence with gemini 3. https://blog.google/products/gemini/ gemini-3/. ↗
  15. Han Lee. 2025. Claude agent skills: A first principles deep dive. https://leehanchung.github.io/blogs/2025/10/ 26/claude-skills-deep-dive/. ↗
  16. Mohd Ariful Haque, Justin Williams, Sunzida Siddique, Md Hujaifa Islam, Hasmot Ali, Kishor Datta Gupta, and Roy George. 2025. Advanced tool learning and selection system (atlass): A closed-loop framework using llm. arXiv preprint arXiv:2503.10071. — [arXiv:2503.10071](https://arxiv.org/abs/2503.10071) find
  17. Hongliang He, Wenlin Yao, Kaixin Ma, Wenhao Yu, Yong Dai, Hongming Zhang, Zhenzhong Lan, and Dong Yu. 2024. Webvoyager: Building an end-to-end web agent with large multimodal models. arXiv preprint arXiv:2401.13919.
  18. 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.
  19. Shengran Hu, Cong Lu, and Jeff Clune. 2024. Automated design of agentic systems. arXiv preprint arXiv:2408.08435. find
  20. Yiming Huang, Jianwen Luo, Yan Yu, Yitong Zhang, Fangyu Lei, Yifan Wei, Shizhu He, Lifu Huang, Xiao Liu, Jun Zhao, and 1 others. 2024. Da-code: Agent data science code generation benchmark for large language models. arXiv preprint arXiv:2410.07331. find
  21. 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.
  22. Zong Ke, Yuqing Cao, Zhenrui Chen, Yuchen Yin, Shouchao He, and Yu Cheng. 2025. Early warning of cryptocurrency reversal risks via multi-source data. Finance Research Letters, page 107890. 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. Yuhang Lai, Chengxi Li, Yiming Wang, Tianyi Zhang, Ruiqi Zhong, Luke Zettlemoyer, Wen-tau Yih, Daniel Fried, Sida Wang, and Tao Yu. 2023. Ds-1000: A natural and reliable benchmark for data science code generation. In International Conference on Machine Learning, pages 18319–18345. PMLR. find
  25. Jia Li, Edward Beeching, Lewis Tunstall, Ben Lipkin, Roman Soletskyi, Shengyi Huang, Kashif Rasul, Longhui Yu, Albert Q Jiang, Ziju Shen, and 1 others. 2024. Numinamath: The largest public dataset in ai4maths with 860k pairs of competition math problems and solutions. Hugging Face repository, 13(9):… find
  26. Shanda Li, Tanya Marwah, Junhong Shen, Weiwei Sun, Andrej Risteski, Yiming Yang, and Ameet Talwalkar. 2025a. Codepde: An inference framework for llm-driven pde solver generation. arXiv preprint arXiv:2505.08783. — [arXiv:2505.08783](https://arxiv.org/abs/2505.08783) find
  27. Songze Li, Xiaoke Guo, Tianqi Liu, Biao Yi, Zhaoyan Gong, Zhiqiang Liu, Huajun Chen, and Wen Zhang. 2026. What’s missing in screen-to-action? towards a ui-in-the-loop paradigm for multimodal gui reasoning. Preprint, arXiv:2604.06995. find
  28. Xiaoxi Li, Guanting Dong, Jiajie Jin, Yuyao Zhang, Yujia Zhou, Yutao Zhu, Peitian Zhang, and Zhicheng Dou. 2025b. Search-o1: Agentic search-enhanced large reasoning models. arXiv preprint arXiv:2501.05366.
  29. Xiaoxi Li, Wenxiang Jiao, Jiarui Jin, Guanting Dong, Jiajie Jin, Yinuo Wang, Hao Wang, Yutao Zhu, Ji-Rong Wen, Yuan Lu, and 1 others. 2025c. Deepagent: A general reasoning agent with scalable toolsets. arXiv preprint arXiv:2510.21618. — [arXiv:2510.21618](https://arxiv.org/abs/2510.21618) find
  30. Yu Li, Lehui Li, Zhihao Wu, Qingmin Liao, Jianye Hao, Kun Shao, Fengli Xu, and Yong Li. 2025d. 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
  31. Xinbin Liang, Jinyu Xiang, Zhaoyang Yu, Jiayi Zhang, Sirui Hong, Sheng Fan, and Xiao Tang. 2025. Openmanus: An open-source framework for building general ai agents. find
  32. Xuechen Liang, Yangfan He, Yinghui Xia, Xinyuan Song, Jianhui Wang, Meiling Tao, Li Sun, Xinhang Yuan, Jiayi Su, Keqin Li, and 1 others. 2024. Self-evolving agents with reflective and memory-augmented abilities. arXiv preprint arXiv:2409.00872. 2025b. How do recommendation models amplify popularity… — [arXiv:2409.00872](https://arxiv.org/abs/2409.00872) find
  33. Aixin Liu, Aoxue Mei, Bangcai Lin, Bing Xue, Bingxuan Wang, Bingzheng Xu, Bochao Wu, Bowei Zhang, Chaofan Lin, Chen Dong, and 1 others. 2025a. Deepseek-v3. 2: Pushing the frontier of open large language models. arXiv preprint arXiv:2512.02556.
  34. Ziyu Liu, Yuhang Zang, Shengyuan Ding, Yuhang Cao, Xiaoyi Dong, Haodong Duan, Dahua Lin, and Jiaqi Wang. 2025b. Spark: Synergistic policy and reward co-evolving framework. arXiv preprint arXiv:2509.22624. — [arXiv:2509.22624](https://arxiv.org/abs/2509.22624) find
  35. Yunbo Long, Yuhan Liu, and Liming Xu. 2026. Emo-mas: Emotion-aware multi-agent system for high-stakes edge-deployable negotiation with bayesian orchestration. Preprint, arXiv:2604.07003. — [arXiv:2604.07003](https://arxiv.org/abs/2604.07003) find
  36. Junyu Luo, Weizhi Zhang, Ye Yuan, Yusheng Zhao, Junwei Yang, Yiyang Gu, Bohan Wu, Binqi Chen, Ziyue Qiao, Qingqing Long, and 1 others. 2025. Large language model agent: A survey on methodology, applications and challenges. arXiv preprint arXiv:2503.21460.
  37. Shichao Ma, Yunhe Guo, Jiahao Su, Qihe Huang, Zhengyang Zhou, and Yang Wang. 2026. Talk2image: A multi-agent system for multi-turn image generation and editing. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 40, pages 32437–32445. find
  38. Yubo Ma, Zhibin Gou, Junheng Hao, Ruochen Xu, Shuohang Wang, Liangming Pan, Yujiu Yang, Yixin Cao, Aixin Sun, Hany Awadalla, and 1 others. 2024. Sciagent: Tool-augmented language models for scientific reasoning. arXiv preprint arXiv:2402.11451.
  39. 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
  40. Mariana Meireles, Rupali Bhati, Niklas Lauffer, and Cameron Allen. 2025. The influence of scaffolds on coordination scaling laws in llm agents. In Workshop on Scaling Environments for Agents. find
  41. Jiaye Lin, Yifu Guo, Yuzhen Han, Sen Hu, Ziyi Ni, Licheng Wang, Mingguang Chen, Hongzhang Liu, Ronghao Chen, Yangfan He, and 1 others. 2025a. Se-agent: Self-evolution trajectory optimization in multi-step reasoning with llm-based agents. arXiv preprint arXiv:2508.02085. — [arXiv:2508.02085](https://arxiv.org/abs/2508.02085) find
  42. Sewon Min, Mike Lewis, Luke Zettlemoyer, and Hannaneh Hajishirzi. 2022. Metaicl: Learning to learn in context. In Proceedings of the 2022 conference of the North American chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2791–2809. find
  43. Siyi Lin, Chongming Gao, Jiawei Chen, Sheng Zhou, Binbin Hu, Yan Feng, Chun Chen, and Can Wang. find
  44. OpenAI. 2025. Introducing gpt-5.2. https://openai.com/index/introducing-gpt-5-2. ↗
  45. Kaichen Ouyang, Zong Ke, Shengwei Fu, Lingjie Liu, Puning Zhao, and Dayu Hu. 2024. Learn from global correlations: Enhancing evolutionary algorithm via spectral gnn. arXiv preprint arXiv:2412.17629. — [arXiv:2412.17629](https://arxiv.org/abs/2412.17629) find
  46. Zehua Pei, Hui-Ling Zhen, Shixiong Kai, Sinno Jialin Pan, Yunhe Wang, Mingxuan Yuan, and Bei Yu. 2025. Scope: Prompt evolution for enhancing agent effectiveness. arXiv preprint arXiv:2512.15374. — [arXiv:2512.15374](https://arxiv.org/abs/2512.15374) find
  47. Cheng Qian, Chi Han, Yi Fung, Yujia Qin, Zhiyuan Liu, and Heng Ji. 2023. Creator: Tool creation for disentangling abstract and concrete reasoning of large language models. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 6922–6939.
  48. Yujia Qin, Shihao Liang, Yining Ye, Kunlun Zhu, Lan Yan, Yaxi Lu, Yankai Lin, Xin Cong, Xiangru Tang, Bill Qian, and 1 others. 2023. Toolllm: Facilitating large language models to master 16000+ real-world apis. arXiv preprint arXiv:2307.16789.
  49. Jiahao Qiu, Xuan Qi, Tongcheng Zhang, Xinzhe Juan, Jiacheng Guo, Yifu Lu, Yimin Wang, Zixin Yao, Qihan Ren, Xun Jiang, and 1 others. 2025. Alita: Generalist agent enabling scalable agentic reasoning with minimal predefinition and maximal self-evolution. arXiv preprint arXiv:2505.20286. — [arXiv:2505.20286](https://arxiv.org/abs/2505.20286) find
  50. Rana Salama, Jason Cai, Michelle Yuan, Anna Currey, Monica Sunkara, Yi Zhang, and Yassine Benajiba. 2025. Meminsight: Autonomous memory augmentation for llm agents. arXiv preprint arXiv:2503.21760.
  51. Timo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu, Maria Lomeli, Eric Hambro, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. 2023. Toolformer: Language models can teach themselves to use tools. Advances in Neural Information Processing Systems, 36:68539–68551.
  52. 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
  53. Zhengliang Shi, Yuhan Wang, Lingyong Yan, Pengjie Ren, Shuaiqiang Wang, Dawei Yin, and Zhaochun Ren. 2025. Retrieval models aren’t tool-savvy: Benchmarking tool retrieval for large language models. arXiv preprint arXiv:2503.01763. find
  54. Mirac Suzgun and Adam Tauman Kalai. 2024. Meta-prompting: Enhancing language models with task-agnostic scaffolding. arXiv preprint arXiv:2401.12954.
  55. Jiabin Tang, Lianghao Xia, Zhonghang Li, and Chao Huang. 2025. Ai-researcher: Autonomous scientific innovation. arXiv preprint arXiv:2505.18705. find
  56. Tongyi DeepResearch Team, Baixuan Li, Bo Zhang, Dingchu Zhang, Fei Huang, Guangyu Li, Guoxin Chen, Huifeng Yin, Jialong Wu, Jingren Zhou, and 1 others. 2025. Tongyi deepresearch technical report. arXiv preprint arXiv:2510.24701. — [arXiv:2510.24701](https://arxiv.org/abs/2510.24701) find
  57. Harsh Trivedi, Tushar Khot, Mareike Hartmann, Ruskin Manku, Vinty Dong, Edward Li, Shashank Gupta, Ashish Sabharwal, and Niranjan Balasubramanian. 2024. Appworld: A controllable world of apps and people for benchmarking interactive coding agents. arXiv preprint arXiv:2407.18901.
  58. 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
  59. Hongru Wang, Yujia Qin, Yankai Lin, Jeff Z Pan, and Kam-Fai Wong. 2024a. Empowering large language models: Tool learning for real-world interaction. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 2983–2986. find
  60. Renxi Wang, Xudong Han, Lei Ji, Shu Wang, Timothy Baldwin, and Haonan Li. 2024b. Toolgen: Unified tool retrieval and calling via generation. arXiv preprint arXiv:2410.03439. — [arXiv:2410.03439](https://arxiv.org/abs/2410.03439) find
  61. Xingyao Wang, Boxuan Li, Yufan Song, Frank F Xu, Xiangru Tang, Mingchen Zhuge, Jiayi Pan, Yueqi Song, Bowen Li, Jaskirat Singh, and 1 others. 2024c. Openhands: An open platform for ai software developers as generalist agents. arXiv preprint arXiv:2407.16741.
  62. 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. find
  63. 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
  64. Zora Zhiruo Wang, Jiayuan Mao, Daniel Fried, and Graham Neubig. 2024d. Agent workflow memory. arXiv preprint arXiv:2409.07429.
  65. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, and 1 others. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, 35:24824– 24837.
  66. Yixuan Weng, Minjun Zhu, Guangsheng Bao, Hongbo Zhang, Jindong Wang, Yue Zhang, and Linyi Yang. 2024. Cycleresearcher: Improving automated research via automated review. arXiv preprint arXiv:2411.00816. find
  67. Zhiheng Xi, Wenxiang Chen, Xin Guo, Wei He, Yiwen Ding, Boyang Hong, Ming Zhang, Junzhe Wang, Senjie Jin, Enyu Zhou, and 1 others. 2025. The rise and potential of large language model based agents: A survey. Science China Information Sciences, 68(2):121101.
  68. Chunqiu Steven Xia, Yinlin Deng, Soren Dunn, and Lingming Zhang. 2024. Agentless: Demystifying llm-based software engineering agents. arXiv preprint arXiv:2407.01489. find
  69. Chunqiu Steven Xia, Zhe Wang, Yan Yang, Yuxiang Wei, and Lingming Zhang. 2025. Live-swe-agent: Can software engineering agents self-evolve on the fly? arXiv preprint arXiv:2511.13646. — [arXiv:2511.13646](https://arxiv.org/abs/2511.13646) find
  70. Shengxiang Xu, Jiayi Zhang, Shimin Di, Yuyu Luo, Liang Yao, Hanmo Liu, Jia Zhu, Fan Liu, and Min-Ling Zhang. 2025. Robustflow: Towards robust agentic workflow generation. arXiv preprint arXiv:2509.21834. — [arXiv:2509.21834](https://arxiv.org/abs/2509.21834) find
  71. 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.
  72. Jian Yang, Wei Zhang, Shark Liu, Jiajun Wu, Shawn Guo, and Yizhi Li. 2025. From code foundation models to agents and applications: A practical guide to code intelligence. arXiv preprint arXiv:2511.18538. — [arXiv:2511.18538](https://arxiv.org/abs/2511.18538) find
  73. John Yang, Carlos E Jimenez, Alexander Wettig, Kilian Lieret, Shunyu Yao, Karthik Narasimhan, and Ofir Press. 2024. Swe-agent: Agent-computer interfaces enable automated software engineering. Advances in Neural Information Processing Systems, 37:50528– 50652.
  74. Seungyoun Yi, Minsoo Khang, and Sungrae Park. 2025. Zera: Zero-init instruction evolving refinement agent– from zero instructions to structured prompts via principle-based optimization. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 23334–23348.
  75. Li Yin and Zhangyang Wang. 2025. Llm-autodiff: Auto-differentiate any llm workflow. arXiv preprint arXiv:2501.16673. — [arXiv:2501.16673](https://arxiv.org/abs/2501.16673) find
  76. Lifan Yuan, Yangyi Chen, Xingyao Wang, Yi R Fung, Hao Peng, and Heng Ji. 2023. Craft: Customizing llms by creating and retrieving from specialized toolsets. arXiv preprint arXiv:2309.17428. — [arXiv:2309.17428](https://arxiv.org/abs/2309.17428) find
  77. 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.
  78. 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
  79. Wenyuan Zhang, Xinghua Zhang, Haiyang Yu, Shuaiyi Nie, Bingli Wu, Juwei Yue, Tingwen Liu, and Yongbin Li. 2026a. Expseek: Self-triggered experience seeking for web agents. arXiv preprint arXiv:2601.08605.
  80. Yunyao Zhang, Yihao Ai, Zuocheng Ying, Qirui Mi, Junqing Yu, Wei Yang, and Zikai Song. 2026b. Coupling macro dynamics and micro states for long-horizon social simulation. Preprint, arXiv:2604.05516. — [arXiv:2604.05516](https://arxiv.org/abs/2604.05516) find
  81. Yunyao Zhang, Zikai Song, Hang Zhou, Wenfeng Ren, Yi-Ping Phoebe Chen, Junqing Yu, and Wei Yang. 2025. ga − s 3 : Comprehensive social network simulation with group agents. In Findings of the Association for Computational Linguistics: ACL 2025, pages 8950–8970, Vienna, Austria. Association for Compu… find
  82. Yuzhe Zhang, Xianwei Xue, Xingyong Wu, Mengke Chen, Chen Liu, Xinran He, Run Shao, Feiran Liu, Huanmin Xu, Qiutong Pan, and Haiwei Wang. 2026c. Don’t act blindly: Robust gui automation via action-effect verification and self-correction. Preprint, arXiv:2604.05477.
  83. Andrew Zhao, Daniel Huang, Quentin Xu, Matthieu Lin, Yong-Jin Liu, and Gao Huang. 2024. Expel: Llm agents are experiential learners. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 19632–19642. find
  84. Boyuan Zheng, Michael Y Fatemi, Xiaolong Jin, Zora Zhiruo Wang, Apurva Gandhi, Yueqi Song, Yu Gu, Jayanth Srinivasa, Gaowen Liu, Graham Neubig, and 1 others. 2025. Skillweaver: Web agents can self-improve by discovering and honing skills. arXiv preprint arXiv:2504.07079. find
  85. Huaixiu Steven Zheng, Swaroop Mishra, Xinyun Chen, Heng-Tze Cheng, Ed H Chi, Quoc V Le, and Denny Zhou. 2023. Take a step back: Evoking reasoning via abstraction in large language models. arXiv preprint arXiv:2310.06117. find
  86. Yuanhang Zheng, Peng Li, Wei Liu, Yang Liu, Jian Luan, and Bin Wang. 2024. Toolrerank: Adaptive and hierarchy-aware reranking for tool retrieval. arXiv preprint arXiv:2403.06551. find
  87. Yongchao Zhou, Andrei Ioan Muresanu, Ziwen Han, Keiran Paster, Silviu Pitis, Harris Chan, and Jimmy Ba. 2022. Large language models are human-level prompt engineers. In The eleventh international conference on learning representations.
  88. Peiyan Zhang, Haibo Jin, Leyang Hu, Xinnuo Li, Liying Kang, Man Luo, Yangqiu Song, and Haohan Wang. 2024b. Revolve: Optimizing ai systems by tracking response evolution in textual optimization. arXiv preprint arXiv:2412.03092. — [arXiv:2412.03092](https://arxiv.org/abs/2412.03092) find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/hao-2026-recreate-reasoning-creating-domain-agents/