---
title: "AutoAgent — paper by Tang et al. (2026) — summary and ideas"
description: "Users build and run LLM agents, tools and multi-agent workflows through natural-language… 42 references, cited by 10 papers here."
authors: ["Jiabin Tang", "Tianyu Fan", "Chao Huang"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.2129/"
doi: "10.18653/v1/2026.findings-acl.2129"
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/tang-2026-autoagent-fully-automated-zero-code/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/tang-2026-autoagent-fully-automated-zero-code/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/) / AutoAgent: A Fully-Automated and Zero-Code Framework for LLM Agents

# AutoAgent: A Fully-Automated and Zero-Code Framework for LLM Agents

**Authors:** Jiabin Tang, Tianyu Fan and [Chao Huang](https://md.research.elamur.ai/free/en/authors/chao-huang/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.2129/) · [PDF](https://aclanthology.org/2026.findings-acl.2129.pdf) · [DOI 10.18653/v1/2026.findings-acl.2129](https://doi.org/10.18653/v1/2026.findings-acl.2129) · [OpenAlex](https://openalex.org/W7166831912)

**Citations:** 3 citations (OpenAlex, 2026-10-14) · [10](https://md.research.elamur.ai/free/en/papers/tang-2026-autoagent-fully-automated-zero-code/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Frameworks for building LLM agents, such as LangChain and AutoGen, assume programming skills, which the authors estimate only about 0.03% of people have. AutoAgent aims to remove this barrier. Users build and run LLM agents, tools and multi-agent workflows through natural-language conversation alone. The system works as an agent operating system with four parts:
- **Agentic System Utilities:** web, coding and local-file agents that cooperate under an orchestrator.
- **LLM-powered Actionable Engine:** connects to any LLM provider through direct or transformed tool use.
- **Self-Managing File System:** converts heterogeneous files into searchable vector databases.
- **Self-Play Agent Customization:** turns user requests into XML specifications and then into executable code, repairing its own errors when generation fails.

AutoAgent can also act directly as a generalist assistant. The authors report strong GAIA results and better RAG performance than competing LLM-based methods. The work matters because it brings agent development within reach of non-programmers. However, the natural-language programming paradigm itself has not yet been evaluated systematically.

## Key points
- **GAIA results are reported inconsistently.** The abstract and Figure 1 claim AutoAgent ranks first among open-source systems and beats prior state of the art. The introduction instead mentions second place. Exact scores are not in the excerpt provided.
- **Financial Agent case study.** The system generated:
  - a Document Manager Agent and a Market Research Agent;
  - the tools get_balance_sheet, get_cash_flow, get_income_statement and analyze_financial_data;
  - a Financial Analysis Orchestrator to coordinate them.

  It also recovered on its own from a SyntaxError.
- **Auto-generated Majority Voting workflow on MATH-500 (pass@1).** The workflow scored 75.6. The individual models scored 66.4 (gpt-4o), 66.4 (claude-3.5-sonnet) and 74.2 (deepseek-v3).
- **Stated limitations.** There is no dedicated benchmark for natural-language agent programming. There is no GUI/visual agent support; web interaction is DOM-level only.
- **Code:** https://github.com/HKUDS/AutoAgent

*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

- [University of Hong Kong](https://md.research.elamur.ai/free/en/universities/university-of-hong-kong/) — University, Pok Fu Lam, China · 89 works · 11,774 citations

📚 Shelves (4): [🖥️ 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

## Cite

Cite as: Jiabin Tang, Tianyu Fan and Chao Huang. 2026. AutoAgent: A Fully-Automated and Zero-Code Framework for LLM Agents. Findings of the Association for Computational Linguistics: ACL 2026.

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

```bibtex
@inproceedings{tang2026autoagent,
  title = {{AutoAgent: A Fully-Automated and Zero-Code Framework for LLM Agents}},
  author = {Jiabin Tang, Tianyu Fan and Chao Huang},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.2129},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.2129}
}
```

- [← previous When One LLM Drools, Multi-LLM Collaboration Rules](https://md.research.elamur.ai/free/en/papers/feng-2026-when-one-llm-drools-multi/)
- [next → CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks](https://md.research.elamur.ai/free/en/papers/jiang-2026-codejudgebench-benchmarking-llm-as-judge/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/)

## References

42 references, 17 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Anthropic. 2024. Building effective agents. [https://www.anthropic.com/research/](https://www.anthropic.com/research/) building-effective-agents. [↗](https://www.anthropic.com/research/)
2. Wenyi Hong, Weihan Wang, Qingsong Lv, Jiazheng Xu, Wenmeng Yu, Junhui Ji, Yan Wang, Zihan Wang, Yuxiao Dong, Ming Ding, and Jie Tang. 2024b. [Cogagent: A visual language model for GUI agents](https://md.research.elamur.ai/free/en/papers/hong-2023-cogagent-visual-language-model/). In CVPR, pages 14281–14290. IEEE.
3. BerriAI. 2024. Litellm: Proxy server (llm gateway) to call 100+ llm apis in openai format. [https://github.com/BerriAI/litellm](https://github.com/BerriAI/litellm). [↗](https://github.com/BerriAI/litellm)
4. Shengran Hu, Cong Lu, and Jeff Clune. 2024. Automated design of agentic systems. CoRR, abs/2408.08435. [find](https://scholar.google.com/scholar?q=Shengran+Hu%2C+Cong+Lu%2C+and+Jeff+Clune%2E+2024%2E+Automated+design+of+agentic+systems%2E+CoRR%2C+abs%2F2408%2E08435%2E)
5. Composio. 2024. Composio: Production ready toolset for ai agents. [https://github.com/ComposioHQ/](https://github.com/ComposioHQ/) composio. [↗](https://github.com/ComposioHQ/)
6. HuggingFace. 2024. Transformers documentation: Agents and toos. [https://huggingface.co/docs/](https://huggingface.co/docs/) transformers/agents. [↗](https://huggingface.co/docs/)
7. Alexandre Drouin, Maxime Gasse, Massimo Caccia, Issam H. Laradji, Manuel Del Verme, Tom Marty, David Vazquez, Nicolas Chapados, and Alexandre Lacoste. 2024. WorkArena: How capable are web agents at solving common knowledge work tasks? In Proceedings of the 41st International Conference on Machine Le… [find](https://scholar.google.com/scholar?q=Alexandre+Drouin%2C+Maxime+Gasse%2C+Massimo+Caccia%2C+Issam+H%2E+Laradji%2C+Manuel+Del+Verme%2C+Tom+Marty%2C+David+Vazquez%2C+Nicolas+Chapados%2C+and+Alexandre+Lacoste%2E+2024%2E+WorkArena%3A+How+capable+are+web+agents+at+so)
8. LangChain. 2023. Langchain: Build context-aware reasoning applications. [https://github.com/](https://github.com/) langchain-ai/langchain. [↗](https://github.com/)
9. E2B. 2024. Secure open source cloud runtime for ai apps & ai agents. [https://github.com/e2b-dev/](https://github.com/e2b-dev/) e2b. [↗](https://github.com/e2b-dev/)
10. Tianyu Fan, Jingyuan Wang, Xubin Ren, and Chao Huang. 2025. Minirag: Towards extremely simple retrieval-augmented generation. arXiv preprint arXiv:2501.06713. — [arXiv:2501.06713](https://arxiv.org/abs/2501.06713) [find](https://scholar.google.com/scholar?q=Tianyu+Fan%2C+Jingyuan+Wang%2C+Xubin+Ren%2C+and+Chao+Huang%2E+2025%2E+Minirag%3A+Towards+extremely+simple+retrieval%2Daugmented+generation%2E+arXiv+preprint+arXiv%3A2501%2E06713%2E+%E2%80%94+%5BarXiv%3A2501%2E06713%5D%28https%3A%2F%2Farxiv%2Eorg%2Fab)
11. Adam Fourney, Gagan Bansal, Hussein Mozannar, Cheng Tan, Eduardo Salinas, Erkang Zhu, Friederike Niedtner, Grace Proebsting, Griffin Bassman, Jack Gerrits, Jacob Alber, Peter Chang, Ricky Loynd, Robert West, Victor Dibia, Ahmed Awadallah, Ece Kamar, Rafah Hosn, and Saleema Amershi. 2024. Magentic-on… [find](https://scholar.google.com/scholar?q=Adam+Fourney%2C+Gagan+Bansal%2C+Hussein+Mozannar%2C+Cheng+Tan%2C+Eduardo+Salinas%2C+Erkang+Zhu%2C+Friederike+Niedtner%2C+Grace+Proebsting%2C+Griffin+Bassman%2C+Jack+Gerrits%2C+Jacob+Alber%2C+Peter+Chang%2C+Ricky+Loynd%2C+Rober)
12. Luyu Gao, Xueguang Ma, Jimmy Lin, and Jamie Callan. 2022. [Precise zero-shot dense retrieval without relevance labels](https://md.research.elamur.ai/free/en/papers/gao-2022-precise-zero-shot-dense-retrieval/). arXiv preprint arXiv:2212.10496.
13. Google. 2024. Langfun: Oo for llms. github.com/google/langfun. https:// [find](https://scholar.google.com/scholar?q=Google%2E+2024%2E+Langfun%3A+Oo+for+llms%2E+github%2Ecom%2Fgoogle%2Flangfun%2E+https%3A%2F%2F)
14. LangChain. 2024. Langgraph: sbuild resilient language agents as graphs. [https://github.com/](https://github.com/) langchain-ai/langgraph. [↗](https://github.com/)
15. Guohao Li, Hasan Hammoud, Hani Itani, Dmitrii Khizbullin, and Bernard Ghanem. 2023. [CAMEL: communicative agents for "mind" exploration of large language model society](https://md.research.elamur.ai/free/en/papers/li-2023-camel-communicative-agents-mind/). In NeurIPS.
16. Manling Li, Shiyu Zhao, Qineng Wang, Kangrui Wang, Yu Zhou, Sanjana Srivastava, Cem Gokmen, Tony Lee, Li Erran Li, Ruohan Zhang, and 1 others. 2024. Embodied agent interface: Benchmarking llms for embodied decision making. In NeurIPS 2024. [find](https://scholar.google.com/scholar?q=Manling+Li%2C+Shiyu+Zhao%2C+Qineng+Wang%2C+Kangrui+Wang%2C+Yu+Zhou%2C+Sanjana+Srivastava%2C+Cem+Gokmen%2C+Tony+Lee%2C+Li+Erran+Li%2C+Ruohan+Zhang%2C+and+1+others%2E+2024%2E+Embodied+agent+interface%3A+Benchmarking+llms+for+emb)
17. Hunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. 2024. [Let’s verify step by step](https://md.research.elamur.ai/free/en/papers/lightman-2023-let-s-verify-step-step/). In ICLR. Open-Review.net.
18. Yuning Mao, Pengcheng He, Xiaodong Liu, Yelong Shen, Jianfeng Gao, Jiawei Han, and Weizhu Chen. 2020. [Generation-augmented retrieval for open-domain question answering](https://md.research.elamur.ai/free/en/papers/mao-2020-generation-augmented-retrieval-open-domain/). arXiv preprint arXiv:2009.08553.
19. Grégoire Mialon, Clémentine Fourrier, Thomas Wolf, Yann LeCun, and Thomas Scialom. 2024. [GAIA: a benchmark for general AI assistants](https://md.research.elamur.ai/free/en/papers/mialon-2023-gaia-benchmark-general-ai-assistants/). In ICLR. Open-Review.net.
20. Zirui Guo, Lianghao Xia, Yanhua Yu, Tu Ao, and Chao Huang. 2024. [Lightrag: Simple and fast retrieval-augmented generation](https://md.research.elamur.ai/free/en/papers/guo-2024-lightrag-simple-fast-retrieval-augmented/).
21. Microsoft. 2024. Multi-agent experiment v0.1 msr ai frontiers (autogen team members). [https://aka.ms/gaia_multiagent_v01_march_1st](https://aka.ms/gaia_multiagent_v01_march_1st). [↗](https://aka.ms/gaia_multiagent_v01_march_1st)
22. H2O.ai. 2024. Autonomous agentic ai: execute multi-step workflows autonomously. [https://h2o.ai/](https://h2o.ai/) platform/enterprise-h2ogpte/\#AgenticAI. [↗](https://h2o.ai/)
23. OpenAI. 2023. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). arXiv:2303.08774.
24. 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. 2024a. [MetaGPT: Meta programming for a multi-agent collaborative framework](https://md.research.elamur.ai/free/en/papers/hong-2023-metagpt-meta-programming-multi/). In The…
25. Preprint, OpenAI. 2024. Educational framework exploring ergonomic, lightweight multi-agent orchestration. [https://github.com/openai/swarm](https://github.com/openai/swarm). [↗](https://github.com/openai/swarm)
26. Significant-Gravitas. 2023. Autogpt. [https://github.com/Significant-Gravitas/AutoGPT](https://github.com/Significant-Gravitas/AutoGPT). [↗](https://github.com/Significant-Gravitas/AutoGPT)
27. Yueqi Song, Frank Xu, Shuyan Zhou, and Graham Neubig. 2024. Beyond browsing: Api-based web agents. arXiv preprint arXiv:2410.16464. [find](https://scholar.google.com/scholar?q=Yueqi+Song%2C+Frank+Xu%2C+Shuyan+Zhou%2C+and+Graham+Neubig%2E+2024%2E+Beyond+browsing%3A+Api%2Dbased+web+agents%2E+arXiv+preprint+arXiv%3A2410%2E16464%2E)
28. Yixuan Tang and Yi Yang. 2024. [Multihop-rag: Benchmarking retrieval-augmented generation for multi-hop queries](https://md.research.elamur.ai/free/en/papers/tang-2024-multihop-rag-benchmarking-retrieval-augmented/). CoRR, abs/2401.15391.
29. Trase. 2024. Meet trase systems, the ai agent platform. [https://www.trasesystems.com/](https://www.trasesystems.com/). Accessed: 2025-01-15. [↗](https://www.trasesystems.com/)
30. Evan Wang, Federico Cassano, Catherine Wu, Yunfeng Bai, Will Song, Vaskar Nath, Ziwen Han, Sean Hendryx, Summer Yue, and Hugh Zhang. 2024a. Planning in natural language improves LLM search for code generation. CoRR, abs/2409.03733. [find](https://scholar.google.com/scholar?q=Evan+Wang%2C+Federico+Cassano%2C+Catherine+Wu%2C+Yunfeng+Bai%2C+Will+Song%2C+Vaskar+Nath%2C+Ziwen+Han%2C+Sean+Hendryx%2C+Summer+Yue%2C+and+Hugh+Zhang%2E+2024a%2E+Planning+in+natural+language+improves+LLM+search+for+code+ge)
31. Xingyao Wang, Boxuan Li, Yufan Song, Frank F. Xu, Xiangru Tang, Mingchen Zhuge, Jiayi Pan, Yueqi Song, Bowen Li, Jaskirat Singh, Hoang H. Tran, Fuqiang Li, Ren Ma, Mingzhang Zheng, Bill Qian, Yanjun Shao, Niklas Muennighoff, Yizhe Zhang, Binyuan Hui, and 5 others. 2024b. [OpenHands: An Open Platform…](https://md.research.elamur.ai/free/en/papers/wang-2024-openhands-open-platform-ai/)
32. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R. Narasimhan, and Yuan Cao. 2023. [React: Synergizing reasoning and acting in language models](https://md.research.elamur.ai/free/en/papers/yao-2022-react-synergizing-reasoning-acting-language/). In ICLR. OpenReview.net.
33. Jiayi Zhang, Jinyu Xiang, Zhaoyang Yu, Fengwei Teng, Xionghui Chen, Jiaqi Chen, Mingchen Zhuge, Xin Cheng, Sirui Hong, Jinlin Wang, Bingnan Zheng, Bang Liu, Yuyu Luo, and Chenglin Wu. 2024. Aflow: Automating agentic workflow generation. CoRR, abs/2410.10762. [find](https://scholar.google.com/scholar?q=Jiayi+Zhang%2C+Jinyu+Xiang%2C+Zhaoyang+Yu%2C+Fengwei+Teng%2C+Xionghui+Chen%2C+Jiaqi+Chen%2C+Mingchen+Zhuge%2C+Xin+Cheng%2C+Sirui+Hong%2C+Jinlin+Wang%2C+Bingnan+Zheng%2C+Bang+Liu%2C+Yuyu+Luo%2C+and+Chenglin+Wu%2E+2024%2E+Aflow%3A+Aut)
34. Mingchen Zhuge, Wenyi Wang, Louis Kirsch, Francesco Faccio, Dmitrii Khizbullin, and Jürgen Schmidhuber. 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+Gptswarm%3A+Language+agents+as+optimizable+graphs%2E+In+Forty%2Dfirst+International+Conference+on+Mach)
35. Mingchen Zhuge, Wenyi Wang, Louis Kirsch, Francesco Faccio, Dmitrii Khizbullin, and Jürgen Schmidhuber. 2024. Gptswarm: Language agents as optimizable graphs. In ICML. OpenReview.net. [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+ICML%2E+OpenReview%2Enet%2E)
36. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2023. [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 ICLR. OpenReview.net.
37. 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. CoRR, abs/2308.08155.
38. Zhiyong Wu, Chengcheng Han, Zichen Ding, Zhenmin Weng, Zhoumianze Liu, Shunyu Yao, Tao Yu, and Lingpeng Kong. 2024. Os-copilot: Towards generalist computer agents with self-improvement. arXiv preprint arXiv:2402.07456. [find](https://scholar.google.com/scholar?q=Zhiyong+Wu%2C+Chengcheng+Han%2C+Zichen+Ding%2C+Zhenmin+Weng%2C+Zhoumianze+Liu%2C+Shunyu+Yao%2C+Tao+Yu%2C+and+Lingpeng+Kong%2E+2024%2E+Os%2Dcopilot%3A+Towards+generalist+computer+agents+with+self%2Dimprovement%2E+arXiv+preprint)
39. Tianbao Xie, Fan Zhou, Zhoujun Cheng, Peng Shi, Luoxuan Weng, Yitao Liu, Toh Jing Hua, Junning Zhao, Qian Liu, Che Liu, Leo Z. Liu, Yiheng Xu, Hongjin Su, Dongchan Shin, Caiming Xiong, and Tao Yu. 2023. [Openagents: An open platform for language agents in the wild](https://md.research.elamur.ai/free/en/papers/xie-2023-openagents-open-platform-language-agents/). Preprint, arXiv:2310.10634.
40. Yiheng Xu, Zekun Wang, Junli Wang, Dunjie Lu, Tianbao Xie, Amrita Saha, Doyen Sahoo, Tao Yu, and Caiming Xiong. 2024. Aguvis: Unified pure vision agents for autonomous gui interaction. [find](https://scholar.google.com/scholar?q=Yiheng+Xu%2C+Zekun+Wang%2C+Junli+Wang%2C+Dunjie+Lu%2C+Tianbao+Xie%2C+Amrita+Saha%2C+Doyen+Sahoo%2C+Tao+Yu%2C+and+Caiming+Xiong%2E+2024%2E+Aguvis%3A+Unified+pure+vision+agents+for+autonomous+gui+interaction%2E)
41. John Yang, Carlos E Jimenez, Alexander Wettig, Kilian Lieret, Shunyu Yao, Karthik R Narasimhan, and Ofir Press. 2024. [SWE-agent: Agent-computer interfaces enable automated software engineering](https://md.research.elamur.ai/free/en/papers/yang-2024-swe-agent-agent-computer-interfaces/). In The Thirty-eighth Annual Conference on Neural Information Processing Systems.
42. Shunyu Yao, Noah Shinn, Pedram Razavi, and Karthik Narasimhan. 2024. [τ -bench: A benchmark for tool-agent-user interaction in real-world domains](https://md.research.elamur.ai/free/en/papers/yao-2024-tau-bench-benchmark-tool/). CoRR, abs/2406.12045.

*Updated 31 October 2026*