---
title: "Skill Discovery for Software Scripting Automation via Offline"
description: "The authors instead build a library of verified scripts (\"skills\") offline, which can then… 90.9% precision. 43 references, cited by 2 papers here."
authors: ["Paiheng Xu", "Gang Wu", "Xiang Chen", "Tong Yu", "Chang Xiao", "Franck Dernoncourt", "Tianyi Zhou", "Wei Ai", "Viswanathan Swaminathan"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: EACL 2026"
source: "https://aclanthology.org/2026.findings-eacl.37/"
doi: "10.18653/v1/2026.findings-eacl.37"
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/xu-2026-skill-discovery-software-scripting-automation/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/xu-2026-skill-discovery-software-scripting-automation/)

[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/page/6/) / Skill Discovery for Software Scripting Automation via Offline Simulations with LLMs

# Skill Discovery for Software Scripting Automation via Offline Simulations with LLMs

**Authors:** Paiheng Xu, [Gang Wu](https://md.research.elamur.ai/free/en/authors/gang-wu/), [Xiang Chen](https://md.research.elamur.ai/free/en/authors/xiang-chen/), [Tong Yu](https://md.research.elamur.ai/free/en/authors/tong-yu/), Chang Xiao, [Franck Dernoncourt](https://md.research.elamur.ai/free/en/authors/franck-dernoncourt/), [Tianyi Zhou](https://md.research.elamur.ai/free/en/authors/tianyi-zhou/), [Wei Ai](https://md.research.elamur.ai/free/en/authors/wei-ai/) and Viswanathan Swaminathan · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: EACL 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-eacl.37/) · [PDF](https://aclanthology.org/2026.findings-eacl.37.pdf) · [DOI 10.18653/v1/2026.findings-eacl.37](https://doi.org/10.18653/v1/2026.findings-eacl.37) · [OpenAlex](https://openalex.org/W7140144175)

**Citations:** 1 citations (OpenAlex, 2026-10-14) · 2 in our library, of the 149,439 papers whose bibliographies we read

## Summary
The paper addresses how to make software scripting accessible to users who lack programming skills or knowledge of an application's API. Generating code with LLMs at query time produces unverified scripts that may be unsafe, and it adds latency and token costs. The authors instead build a library of verified scripts ("skills") offline, which can then be retrieved when a user submits a request. Their framework combines public scripting guides with LLM knowledge in two stages. Task creation works top-down from high-level functionality categories and bottom-up from individual APIs. In the bottom-up direction, a GNN-based link prediction model trained on a graph of APIs that co-occur in working skills suggests compatible API pairs. This pushes the LLM toward rarely used APIs and broadens the skillset. Skill generation then refines each script over several trials using execution errors and an LVLM's judgment of the visual output. On Adobe Illustrator, the skillset achieved higher success rates, wider functional coverage, faster responses and lower runtime token use than runtime generation. The authors present this as the first use of scripting interfaces as a testbed for LLM systems.

## Key points
- Testbed: Adobe Illustrator scripted with ExtendScript, which is Adobe's JavaScript variant. Excel was explored only in a preliminary way, because external programmatic control of other software is limited.
- Allowing up to three trials with execution feedback roughly doubled simulation success (16.7%→34.9% and 23.1%→46.6% across the two strategies). Similar gains appeared with Llama-3.1-70B and deepseek-r1 as code generators.
- The GCN-based API link predictor identified synergistic API pairs better than plain semantic matching.
- The LVLM judge was checked against human labels on 122 tasks and reached 90.9% precision and 80.0% recall, so its errors lean toward rejecting valid outputs.
- Stated limitations:
  - The approach depends on good documentation and the LLM's existing familiarity with the software.
  - User experience was evaluated only in a small user study.
  - Real queries may not match skill granularity, although a RAG variant showed promise for such cases.

*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 Maryland, College Park](https://md.research.elamur.ai/free/en/universities/university-of-maryland-college-park/) — University, College Park, United States · 132 works · 25,380 citations
- [Adobe Systems](https://md.research.elamur.ai/free/en/companies/adobe-systems/) — Company, San Jose, United States · 35 works · 3,711 citations

📚 Shelves (6): [🖥️ 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 · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,437 works · [💻 Software](https://md.research.elamur.ai/free/en/shelves/computer-science/software/) · 92 works

## Cite

Cite as: Paiheng Xu, Gang Wu, Xiang Chen, Tong Yu, Chang Xiao, Franck Dernoncourt, Tianyi Zhou, Wei Ai and Viswanathan Swaminathan. 2026. Skill Discovery for Software Scripting Automation via Offline Simulations with LLMs. Findings of the Association for Computational Linguistics: EACL 2026.

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

```bibtex
@inproceedings{xu2026skill,
  title = {{Skill Discovery for Software Scripting Automation via Offline Simulations with LLMs}},
  author = {Paiheng Xu, Gang Wu, Xiang Chen, Tong Yu, Chang Xiao, Franck Dernoncourt, Tianyi Zhou, Wei Ai and Viswanathan Swaminathan},
  booktitle = {Findings of the Association for Computational Linguistics: EACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-eacl.37},
  url = {https://doi.org/10.18653/v1/2026.findings-eacl.37}
}
```

- [← previous SFTMix: Elevating Language Model Instruction Tuning with Mixup Recipe](https://md.research.elamur.ai/free/en/papers/xiao-2026-sftmix-elevating-language-model-instruction/)
- [next → Sparse Brains are Also Adaptive Brains: Cognitive-Load-Aware Dynamic Activation for LLMs](https://md.research.elamur.ai/free/en/papers/yang-2026-sparse-brains-are-also-adaptive/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/6/)

## References

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

1. Saleema Amershi, Dan Weld, Mihaela Vorvoreanu, Adam Fourney, Besmira Nushi, Penny Collisson, Jina Suh, Shamsi Iqbal, Paul N Bennett, Kori Inkpen, et al. 2019. Guidelines for human-ai interaction. In Proceedings of the 2019 chi conference on human factors in computing systems, pages 1–13. [find](https://scholar.google.com/scholar?q=Saleema+Amershi%2C+Dan+Weld%2C+Mihaela+Vorvoreanu%2C+Adam+Fourney%2C+Besmira+Nushi%2C+Penny+Collisson%2C+Jina+Suh%2C+Shamsi+Iqbal%2C+Paul+N+Bennett%2C+Kori+Inkpen%2C+et+al%2E+2019%2E+Guidelines+for+human%2Dai+interaction%2E+In+P)
2. Petr Anokhin, Nikita Semenov, Artyom Sorokin, Dmitry Evseev, Mikhail Burtsev, and Evgeny Burnaev. 2024. Arigraph: Learning knowledge graph world models with episodic memory for llm agents. arXiv preprint arXiv:2407.04363. — [arXiv:2407.04363](https://arxiv.org/abs/2407.04363) [find](https://scholar.google.com/scholar?q=Petr+Anokhin%2C+Nikita+Semenov%2C+Artyom+Sorokin%2C+Dmitry+Evseev%2C+Mikhail+Burtsev%2C+and+Evgeny+Burnaev%2E+2024%2E+Arigraph%3A+Learning+knowledge+graph+world+models+with+episodic+memory+for+llm+agents%2E+arXiv+prepr)
3. Jacob Austin, Augustus Odena, Maxwell Nye, Maarten Bosma, Henryk Michalewski, David Dohan, Ellen Jiang, Carrie Cai, Michael Terry, Quoc Le, et al. 2021. [Program synthesis with large language models](https://md.research.elamur.ai/free/en/papers/austin-2021-program-synthesis-large-language-models/). arXiv preprint arXiv:2108.07732.
4. Sébastien Bubeck, Varun Chandrasekaran, Ronen Eldan, Johannes Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, Yin Tat Lee, Yuanzhi Li, Scott Lundberg, et al. 2023. [Sparks of artificial general intelligence: Early experiments with gpt-4](https://md.research.elamur.ai/free/en/papers/bubeck-2023-sparks-artificial-general-intelligence-early/). arXiv preprint arXiv:2303.12712.
5. Tianle Cai, Xuezhi Wang, Tengyu Ma, Xinyun Chen, and Denny Zhou. 2024. Large language models as tool makers. In The Twelfth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Tianle+Cai%2C+Xuezhi+Wang%2C+Tengyu+Ma%2C+Xinyun+Chen%2C+and+Denny+Zhou%2E+2024%2E+Large+language+models+as+tool+makers%2E+In+The+Twelfth+International+Conference+on+Learning+Representations%2E)
6. Ruisheng Cao, Fangyu Lei, Haoyuan Wu, Jixuan Chen, Yeqiao Fu, Hongcheng Gao, Xinzhuang Xiong, Hanchong Zhang, Yuchen Mao, Wenjing Hu, et al. 2024. Spider2-v: How far are multimodal agents from automating data science and engineering workflows? arXiv preprint arXiv:2407.10956. — [arXiv:2407.10956](https://arxiv.org/abs/2407.10956) [find](https://scholar.google.com/scholar?q=Ruisheng+Cao%2C+Fangyu+Lei%2C+Haoyuan+Wu%2C+Jixuan+Chen%2C+Yeqiao+Fu%2C+Hongcheng+Gao%2C+Xinzhuang+Xiong%2C+Hanchong+Zhang%2C+Yuchen+Mao%2C+Wenjing+Hu%2C+et+al%2E+2024%2E+Spider2%2Dv%3A+How+far+are+multimodal+agents+from+automat)
7. Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde De Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al. 2021. [Evaluating large language models trained on code](https://md.research.elamur.ai/free/en/papers/chen-2021-evaluating-large-language-models-trained/). arXiv preprint arXiv:2107.03374.
8. Xiang Deng, Yu Gu, Boyuan Zheng, Shijie Chen, Sam Stevens, Boshi Wang, Huan Sun, and Yu Su. 2024. [Mind2web: Towards a generalist agent for the web](https://md.research.elamur.ai/free/en/papers/deng-2023-mind2web-towards-generalist-agent-web/). Advances in Neural Information Processing Systems, 36.
9. Apurva Gandhi, Thong Q Nguyen, Huitian Jiao, Robert Steen, and Ameya Bhatawdekar. 2023. Natural language commanding via program synthesis. arXiv preprint arXiv:2306.03460. — [arXiv:2306.03460](https://arxiv.org/abs/2306.03460) [find](https://scholar.google.com/scholar?q=Apurva+Gandhi%2C+Thong+Q+Nguyen%2C+Huitian+Jiao%2C+Robert+Steen%2C+and+Ameya+Bhatawdekar%2E+2023%2E+Natural+language+commanding+via+program+synthesis%2E+arXiv+preprint+arXiv%3A2306%2E03460%2E+%E2%80%94+%5BarXiv%3A2306%2E03460%5D%28https%3A%2F)
10. Difei Gao, Lei Ji, Zechen Bai, Mingyu Ouyang, Peiran Li, Dongxing Mao, Qinchen Wu, Weichen Zhang, Peiyi Wang, Xiangwu Guo, et al. 2024. Assistgui: Task-oriented pc graphical user interface automation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13289–… [find](https://scholar.google.com/scholar?q=Difei+Gao%2C+Lei+Ji%2C+Zechen+Bai%2C+Mingyu+Ouyang%2C+Peiran+Li%2C+Dongxing+Mao%2C+Qinchen+Wu%2C+Weichen+Zhang%2C+Peiyi+Wang%2C+Xiangwu+Guo%2C+et+al%2E+2024%2E+Assistgui%3A+Task%2Doriented+pc+graphical+user+interface+automation%2E)
11. Qing Huang, Zhiqiang Yuan, Zhenchang Xing, Zhengkang Zuo, Changjing Wang, and Xin Xia. 2022. 1+ 1\> 2: Programming know-what and know-how knowledge fusion, semantic enrichment and coherent application. IEEE Transactions on Services Computing, 16(3):1540–1554. [find](https://scholar.google.com/scholar?q=Qing+Huang%2C+Zhiqiang+Yuan%2C+Zhenchang+Xing%2C+Zhengkang+Zuo%2C+Changjing+Wang%2C+and+Xin+Xia%2E+2022%2E+1%2B+1%5C%3E+2%3A+Programming+know%2Dwhat+and+know%2Dhow+knowledge+fusion%2C+semantic+enrichment+and+coherent+application)
12. Geunwoo Kim, Pierre Baldi, and Stephen McAleer. 2024. [Language models can solve computer tasks](https://md.research.elamur.ai/free/en/papers/kim-2023-language-models-solve-computer-tasks/).
13. Advances in Neural Information Processing Systems, 36. [find](https://scholar.google.com/scholar?q=Advances+in+Neural+Information+Processing+Systems%2C+36%2E)
14. Thomas N Kipf and Max Welling. 2017. [Semi-supervised classification with graph convolutional networks](https://md.research.elamur.ai/free/en/papers/kipf-2016-semi-supervised-classification-graph-convolutional/). In 5th International Conference on Learning Representations (ICLR).
15. Hongxin Li, Jingran Su, Yuntao Chen, Qing Li, and ZHAO-XIANG ZHANG. 2024. Sheetcopilot: Bringing software productivity to the next level through large language models. Advances in Neural Information Processing Systems, 36. [find](https://scholar.google.com/scholar?q=Hongxin+Li%2C+Jingran+Su%2C+Yuntao+Chen%2C+Qing+Li%2C+and+ZHAO%2DXIANG+ZHANG%2E+2024%2E+Sheetcopilot%3A+Bringing+software+productivity+to+the+next+level+through+large+language+models%2E+Advances+in+Neural+Information+P)
16. Yujia Li, David Choi, Junyoung Chung, Nate Kushman, Julian Schrittwieser, Rémi Leblond, Tom Eccles, James Keeling, Felix Gimeno, Agustin Dal Lago, et al. 2022. [Competition-level code generation with alphacode](https://md.research.elamur.ai/free/en/papers/li-2022-competition-level-code-generation-alphacode/). Science, 378(6624):1092–1097.
17. Chia-Wei Liu, Ryan Lowe, Iulian Serban, Mike Noseworthy, Laurent Charlin, and Joelle Pineau. 2016. [How NOT to evaluate your dialogue system: An empirical study of unsupervised evaluation metrics for dialogue response generation](https://md.research.elamur.ai/free/en/papers/liu-2016-how-not-evaluate-your-dialogue/). In Proceedings of the 2016 Conference on Empirical Methods in Natural L…
18. Guangyi Liu, Yongqi Zhang, Yong Li, and Quanming Yao. 2024a. Explore then determine: A gnn-llm synergy framework for reasoning over knowledge graph. arXiv preprint arXiv:2406.01145. — [arXiv:2406.01145](https://arxiv.org/abs/2406.01145) [find](https://scholar.google.com/scholar?q=Guangyi+Liu%2C+Yongqi+Zhang%2C+Yong+Li%2C+and+Quanming+Yao%2E+2024a%2E+Explore+then+determine%3A+A+gnn%2Dllm+synergy+framework+for+reasoning+over+knowledge+graph%2E+arXiv+preprint+arXiv%3A2406%2E01145%2E+%E2%80%94+%5BarXiv%3A2406%2E0114)
19. Jiawei Liu, Chunqiu Steven Xia, Yuyao Wang, and Lingming Zhang. 2024b. [Is your code generated by chatgpt really correct? rigorous evaluation of large language models for code generation](https://md.research.elamur.ai/free/en/papers/liu-2023-your-code-generated-chatgpt-really/). Advances in Neural Information Processing Systems, 36.
20. Xiaoyu Liu, Paiheng Xu, Junda Wu, Jiaxin Yuan, Yifan Yang, Yuhang Zhou, Fuxiao Liu, Tianrui Guan, Haoliang Wang, Tong Yu, et al. 2025. Large language models and causal inference in collaboration: A comprehensive survey. Findings of the Association for Computational Linguistics: NAACL 2025, pages 766… [find](https://scholar.google.com/scholar?q=Xiaoyu+Liu%2C+Paiheng+Xu%2C+Junda+Wu%2C+Jiaxin+Yuan%2C+Yifan+Yang%2C+Yuhang+Zhou%2C+Fuxiao+Liu%2C+Tianrui+Guan%2C+Haoliang+Wang%2C+Tong+Yu%2C+et+al%2E+2025%2E+Large+language+models+and+causal+inference+in+collaboration%3A+A+co)
21. Chang Ma, Junlei Zhang, Zhihao Zhu, Cheng Yang, Yujiu Yang, Yaohui Jin, Zhenzhong Lan, Lingpeng Kong, and Junxian He. 2024a. Agentboard: An analytical evaluation board of multi-turn llm agents. arXiv preprint arXiv:2401.13178. [find](https://scholar.google.com/scholar?q=Chang+Ma%2C+Junlei+Zhang%2C+Zhihao+Zhu%2C+Cheng+Yang%2C+Yujiu+Yang%2C+Yaohui+Jin%2C+Zhenzhong+Lan%2C+Lingpeng+Kong%2C+and+Junxian+He%2E+2024a%2E+Agentboard%3A+An+analytical+evaluation+board+of+multi%2Dturn+llm+agents%2E+arXiv+)
22. Zeyao Ma, Bohan Zhang, Jing Zhang, Jifan Yu, Xiaokang Zhang, Xiaohan Zhang, Sijia Luo, Xi Wang, and Jie Tang. 2024b. [Spreadsheetbench: Towards challenging real world spreadsheet manipulation](https://md.research.elamur.ai/free/en/papers/ma-2024-spreadsheetbench-towards-challenging-real-world/). In The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track.
23. 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 The Twelfth International Conference on Learning Representations.
24. Dang Nguyen, Jian Chen, Yu Wang, Gang Wu, Namyong Park, Zhengmian Hu, Hanjia Lyu, Junda Wu, Ryan Aponte, Yu Xia, et al. 2025. Gui agents: A survey. In Findings of the Association for Computational Linguistics: ACL 2025, pages 22522–22538. [find](https://scholar.google.com/scholar?q=Dang+Nguyen%2C+Jian+Chen%2C+Yu+Wang%2C+Gang+Wu%2C+Namyong+Park%2C+Zhengmian+Hu%2C+Hanjia+Lyu%2C+Junda+Wu%2C+Ryan+Aponte%2C+Yu+Xia%2C+et+al%2E+2025%2E+Gui+agents%3A+A+survey%2E+In+Findings+of+the+Association+for+Computational+Lin)
25. Dang Nguyen, Viet Dac Lai, Seunghyun Yoon, Ryan A Rossi, Handong Zhao, Ruiyi Zhang, Puneet Mathur, Nedim Lipka, Yu Wang, Trung Bui, et al. 2024. Dynasaur: Large language agents beyond predefined actions. arXiv preprint arXiv:2411.01747. — [arXiv:2411.01747](https://arxiv.org/abs/2411.01747) [find](https://scholar.google.com/scholar?q=Dang+Nguyen%2C+Viet+Dac+Lai%2C+Seunghyun+Yoon%2C+Ryan+A+Rossi%2C+Handong+Zhao%2C+Ruiyi+Zhang%2C+Puneet+Mathur%2C+Nedim+Lipka%2C+Yu+Wang%2C+Trung+Bui%2C+et+al%2E+2024%2E+Dynasaur%3A+Large+language+agents+beyond+predefined+actio)
26. Erik Nijkamp, Bo Pang, Hiroaki Hayashi, Lifu Tu, Huan Wang, Yingbo Zhou, Silvio Savarese, and Caiming Xiong. 2023. Codegen: An open large language model for code with multi-turn program synthesis. In The Eleventh International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Erik+Nijkamp%2C+Bo+Pang%2C+Hiroaki+Hayashi%2C+Lifu+Tu%2C+Huan+Wang%2C+Yingbo+Zhou%2C+Silvio+Savarese%2C+and+Caiming+Xiong%2E+2023%2E+Codegen%3A+An+open+large+language+model+for+code+with+multi%2Dturn+program+synthesis%2E+In+)
27. John K Ousterhout. 1998. Scripting: Higher level programming for the 21st century. Computer, 31(3):23– 30. [find](https://scholar.google.com/scholar?q=John+K+Ousterhout%2E+1998%2E+Scripting%3A+Higher+level+programming+for+the+21st+century%2E+Computer%2C+31%283%29%3A23%E2%80%93+30%2E)
28. Liangming Pan, Michael Saxon, Wenda Xu, Deepak Nathani, Xinyi Wang, and William Yang Wang. 2024. [Automatically correcting large language models: Surveying the landscape of diverse automated correction strategies](https://md.research.elamur.ai/free/en/papers/pan-2024-automatically-correcting-large-language-models/). Transactions of the Association for Computational Linguistics, 12:484–506.
29. Shishir G Patil, Tianjun Zhang, Xin Wang, and Joseph E Gonzalez. 2024. [Gorilla: Large language model connected with massive apis](https://md.research.elamur.ai/free/en/papers/patil-2023-gorilla-large-language-model-connected/). Advances in Neural Information Processing Systems, 37:126544–126565.
30. Lianyong Qi, Wenmin Lin, Xuyun Zhang, Wanchun Dou, Xiaolong Xu, and Jinjun Chen. 2022. A correlation graph based approach for personalized and compatible web apis recommendation in mobile app development. IEEE Transactions on Knowledge and Data Engineering, 35(6):5444–5457. [find](https://scholar.google.com/scholar?q=Lianyong+Qi%2C+Wenmin+Lin%2C+Xuyun+Zhang%2C+Wanchun+Dou%2C+Xiaolong+Xu%2C+and+Jinjun+Chen%2E+2022%2E+A+correlation+graph+based+approach+for+personalized+and+compatible+web+apis+recommendation+in+mobile+app+developm)
31. 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](https://md.research.elamur.ai/free/en/papers/qian-2023-creator-tool-creation-disentangling-abstract/). In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 6922–6939. embodied agent with large language mo…
32. Shiwen Wu, Fei Sun, Wentao Zhang, Xu Xie, and Bin Cui. 2022. Graph neural networks in recommender systems: a survey. ACM Computing Surveys, 55(5):1– 37. [find](https://scholar.google.com/scholar?q=Shiwen+Wu%2C+Fei+Sun%2C+Wentao+Zhang%2C+Xu+Xie%2C+and+Bin+Cui%2E+2022%2E+Graph+neural+networks+in+recommender+systems%3A+a+survey%2E+ACM+Computing+Surveys%2C+55%285%29%3A1%E2%80%93+37%2E)
33. Tianbao Xie, Danyang Zhang, Jixuan Chen, Xiaochuan Li, Siheng Zhao, Ruisheng Cao, Toh Jing Hua, Zhoujun Cheng, Dongchan Shin, Fangyu Lei, et al. 2024. [Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments](https://md.research.elamur.ai/free/en/papers/xie-2024-osworld-benchmarking-multimodal-agents-open/). arXiv preprint arXiv:2404.07972.
34. Paiheng Xu, Jing Liu, Nathan Jones, Julie Cohen, and Wei Ai. 2024. The promises and pitfalls of using language models to measure instruction quality in education. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Tech… [find](https://scholar.google.com/scholar?q=Paiheng+Xu%2C+Jing+Liu%2C+Nathan+Jones%2C+Julie+Cohen%2C+and+Wei+Ai%2E+2024%2E+The+promises+and+pitfalls+of+using+language+models+to+measure+instruction+quality+in+education%2E+In+Proceedings+of+the+2024+Conference)
35. Paiheng Xu, Yuhang Zhou, Bang An, Wei Ai, and Furong Huang. 2025. Gfairhint: Improving individual fairness for graph neural networks via fairness hint. ACM Transactions on Knowledge Discovery from Data, 19(3):1–22. [find](https://scholar.google.com/scholar?q=Paiheng+Xu%2C+Yuhang+Zhou%2C+Bang+An%2C+Wei+Ai%2C+and+Furong+Huang%2E+2025%2E+Gfairhint%3A+Improving+individual+fairness+for+graph+neural+networks+via+fairness+hint%2E+ACM+Transactions+on+Knowledge+Discovery+from+Dat)
36. Shunyu Yao, Howard Chen, John Yang, and Karthik Narasimhan. 2022. [Webshop: Towards scalable real-world web interaction with grounded language agents](https://md.research.elamur.ai/free/en/papers/yao-2022-webshop-towards-scalable-real-world/). Advances in Neural Information Processing Systems, 35:20744–20757.
37. Lifan Yuan, Yangyi Chen, Xingyao Wang, Yi Fung, Hao Peng, and Heng Ji. 2024. Craft: Customizing llms by creating and retrieving from specialized toolsets. In The Twelfth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Lifan+Yuan%2C+Yangyi+Chen%2C+Xingyao+Wang%2C+Yi+Fung%2C+Hao+Peng%2C+and+Heng+Ji%2E+2024%2E+Craft%3A+Customizing+llms+by+creating+and+retrieving+from+specialized+toolsets%2E+In+The+Twelfth+International+Conference+on+Le)
38. Ziyin Zhang, Chaoyu Chen, Bingchang Liu, Cong Liao, Zi Gong, Hang Yu, Jianguo Li, and Rui Wang. 2023. Unifying the perspectives of nlp and software engineering: A survey on language models for code. arXiv preprint arXiv:2311.07989. — [arXiv:2311.07989](https://arxiv.org/abs/2311.07989) [find](https://scholar.google.com/scholar?q=Ziyin+Zhang%2C+Chaoyu+Chen%2C+Bingchang+Liu%2C+Cong+Liao%2C+Zi+Gong%2C+Hang+Yu%2C+Jianguo+Li%2C+and+Rui+Wang%2E+2023%2E+Unifying+the+perspectives+of+nlp+and+software+engineering%3A+A+survey+on+language+models+for+code%2E+a)
39. Nils Reimers and Iryna Gurevych. 2019. [Sentence-bert: Sentence embeddings using siamese bert-networks](https://md.research.elamur.ai/free/en/papers/reimers-2019-sentence-bert-sentence-embeddings-siamese/). In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics.
40. Boshi Wang, Hao Fang, Jason Eisner, Benjamin Van Durme, and Yu Su. 2024a. LLMs in the imaginarium: Tool learning through simulated trial and error. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10583–10604, Bangkok, Thailand… [find](https://scholar.google.com/scholar?q=Boshi+Wang%2C+Hao+Fang%2C+Jason+Eisner%2C+Benjamin+Van+Durme%2C+and+Yu+Su%2E+2024a%2E+LLMs+in+the+imaginarium%3A+Tool+learning+through+simulated+trial+and+error%2E+In+Proceedings+of+the+62nd+Annual+Meeting+of+the+Ass)
41. Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, and Anima Anandkumar. 2024b. Voyager: An open-ended Wei Zhao, Zhitao Hou, Siyuan Wu, Yan Gao, Haoyu Dong, Yao Wan, Hongyu Zhang, Yulei Sui, and Haidong Zhang. 2024a. NL2Formula: Generating spreadsheet formulas f… [find](https://scholar.google.com/scholar?q=Guanzhi+Wang%2C+Yuqi+Xie%2C+Yunfan+Jiang%2C+Ajay+Mandlekar%2C+Chaowei+Xiao%2C+Yuke+Zhu%2C+Linxi+Fan%2C+and+Anima+Anandkumar%2E+2024b%2E+Voyager%3A+An+open%2Dended+Wei+Zhao%2C+Zhitao+Hou%2C+Siyuan+Wu%2C+Yan+Gao%2C+Haoyu+Dong%2C+Yao+W)
42. Xufeng Zhao, Cornelius Weber, and Stefan Wermter. 2024b. Agentic skill discovery. arXiv preprint arXiv:2405.15019. — [arXiv:2405.15019](https://arxiv.org/abs/2405.15019) [find](https://scholar.google.com/scholar?q=Xufeng+Zhao%2C+Cornelius+Weber%2C+and+Stefan+Wermter%2E+2024b%2E+Agentic+skill+discovery%2E+arXiv+preprint+arXiv%3A2405%2E15019%2E+%E2%80%94+%5BarXiv%3A2405%2E15019%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2405%2E15019%29)
43. Yuhang Zhou, Paiheng Xu, Xiaoyu Liu, Bang An, Wei Ai, and Furong Huang. 2024. Explore spurious correlations at the concept level in language models for text classification. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 478–4… [find](https://scholar.google.com/scholar?q=Yuhang+Zhou%2C+Paiheng+Xu%2C+Xiaoyu+Liu%2C+Bang+An%2C+Wei+Ai%2C+and+Furong+Huang%2E+2024%2E+Explore+spurious+correlations+at+the+concept+level+in+language+models+for+text+classification%2E+In+Proceedings+of+the+62nd+)

*Updated 1 November 2026*