Preprint · 2026 · Open access
Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application
arXiv (Cornell University) · Published 10 June 2026 · DOI 10.48550/arxiv.2606.12191
In brief
“Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application” is a 2026 preprint by Jiachun Li and 14 co-authors, published in arXiv (Cornell University). OpenAlex counts 17 citations as of 18 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).
- Citations
- 17
- Most cited in
- 2026 (17)
- References
- 526
- Authors
- 15
Abstract
Environments serve as interactive systems for large language model (LLM) based agents across diverse scenarios and play a crucial role in driving the continual evolution of model capabilities. Despite this importance, existing work lacks a systematic categorization and deep analysis. This paper systematically studies current researches on agentic environments from the perspective of the environment engineering lifecycle, covering their modeling, synthesis, evaluation and application. Specifically, the paper first introduces representative environments from the perspectives of eight attributes and eight domains, providing detailed analyses of their development paths and highlighting their core capabilities. Second, for automated environment synthesis, two paradigms are introduced, such as symbolic synthesis and neural synthesis. This paper also shows different environment evaluation methods in each paradigm. Thirdly, the corresponding environment applications from the perspective of agent-environment co-evolution are discussed. In specific, the paper characterizes the primary pathways for agent evolution in dynamic environments from four complementary perspectives: memory-centric experience evolution, orchestration-centric workflow evolution, trajectory-centric offline evolution, and exploration-centric online evolution. And three paradigms of environment evolution are identified, namely neural-driven, difficulty-driven, and scaling-driven approaches. At last, several promising future directions are discussed, including Environment-as-a-Service, Multi-agent Environments, and Neural-Symbolic Environments.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Li, J., Jin, Z., Men, T., Hao, Y., Zhu, K., Wang, L., Huang, D., Wang, L., Hua, S., (45927), L. W., Gao, J., Yuan, H., Xu, R., Liu, K., & (59250), J. Z. (2026). Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2606.12191
MLA 9
Li, Jiachun, et al. “Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2606.12191.
Chicago
Li, Jiachun, Zhuoran Jin, Tianyi Men, Yupu Hao, Kejian Zhu, Lingshuai Wang, Dongqi Huang, et al. 2026. “Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2606.12191.
Harvard
Li, J. et al. (2026) ‘Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application’, arXiv (Cornell University). doi:10.48550/arxiv.2606.12191.
IEEE
J. Li et al., “Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2606.12191.
BibTeX
@misc{li2026agentic,
title = {{Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application}},
author = {Li, Jiachun and Jin, Zhuoran and Men, Tianyi and Hao, Yupu and Zhu, Kejian and Wang, Lingshuai and Huang, Dongqi and Wang, Longxiang and Hua, Shengjia and (45927), Lu Wang and Gao, Jinshan and Yuan, Hongbang and Xu, Ruilin and Liu, Kang and (59250), Jun Zhao},
howpublished = {arXiv (Cornell University)},
year = {2026},
doi = {10.48550/arxiv.2606.12191},
url = {https://doi.org/10.48550/arxiv.2606.12191}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › AI-based Problem Solving and Planning
- LLM agents
- environment modeling
- symbolic synthesis
- agent evolution
- workflow evolution
- online exploration
- multi-agent environments
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Li, J., Jin, Z., Men, T., Hao, Y., Zhu, K., Wang, L., Huang, D., Wang, L., Hua, S., (45927), L. W., Gao, J., Yuan, H., Xu, R., Liu, K., & (59250), J. Z. (2026). Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2606.12191
How many times has this paper been cited?
17 times, according to OpenAlex on 18 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Jiachun Li, Zhuoran Jin, Tianyi Men, Yupu Hao, Kejian Zhu, Lingshuai Wang, Dongqi Huang, Longxiang Wang, Shengjia Hua, Lu Wang (45927), Jinshan Gao, Hongbang Yuan and 3 more.
What is the DOI of this paper?
10.48550/arxiv.2606.12191, permanently at https://doi.org/10.48550/arxiv.2606.12191. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 18 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.