---
title: "Escaping the Sisyphus Dilemma — paper by Xie et al. (2026)"
description: "The paper proposes EOM (Experience for Optimization Modeling), an experience-replay framework. 28 references."
authors: ["Wantong Xie", "Yinghao Chen", "Yi-Xiang Hu", "Feng Wu", "Jieyang Xu", "Sijia Zhang", "Xiangyang Li"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.690/"
doi: "10.18653/v1/2026.findings-acl.690"
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/xie-2026-escaping-sisyphus-dilemma-experience-replay/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/xie-2026-escaping-sisyphus-dilemma-experience-replay/)

[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/31/) / Escaping the Sisyphus Dilemma: Experience Replay for Robust Text-to-Optimization Modeling

# Escaping the Sisyphus Dilemma: Experience Replay for Robust Text-to-Optimization Modeling

**Authors:** Wantong Xie, Yinghao Chen, Yi-Xiang Hu, [Feng Wu](https://md.research.elamur.ai/free/en/authors/feng-wu/), Jieyang Xu, Sijia Zhang and [Xiangyang Li](https://md.research.elamur.ai/free/en/authors/xiangyang-li/) · **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.690/) · [PDF](https://aclanthology.org/2026.findings-acl.690.pdf) · [DOI 10.18653/v1/2026.findings-acl.690](https://doi.org/10.18653/v1/2026.findings-acl.690) · [OpenAlex](https://openalex.org/W7166815626)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
LLMs can turn natural-language problem descriptions into executable optimization models, such as MILP formulations for solvers like Gurobi. They usually repair errors through repeated exchanges with the solver, but they keep nothing between sessions. As a result, the same mistakes come back on structurally similar problems, which the authors call the Sisyphus Dilemma. Standard retrieval-augmented methods only supply finished problem-model examples. These show what a correct answer looks like, not how to repair a broken model.

The paper proposes EOM (Experience for Optimization Modeling), an experience-replay framework. After each session, an LLM distiller condenses the interaction log into a Causal Correction Mapping. This links a symptom to an insight:
- **Symptom:** problem semantics, a linearized AST of the faulty code, and the solver traceback.
- **Insight:** a diagnosis and targeted patch for successful sessions, or traps and warnings for failed ones.

A structure-aware retriever then matches new errors against this growing pool. Across seven benchmarks, EOM improves accuracy on complex tasks while lowering token usage and dialogue turns. This suggests that persistent error memory makes LLM-based OR modeling more reliable and cheaper.

## Key points
- Reported gains: +8.45% modeling accuracy on complex benchmarks, 28.65% fewer tokens, and 25.82% fewer interaction turns, evaluated on seven benchmarks.
- Two nested loops make up the design: the outer one, called the Execution Loop, uses solver feedback to refine models, while the inner Experience Loop builds up distilled knowledge over time.
- Each experience unit pairs a hybrid symptom vector (semantic embedding, AST signature that ignores variable names, solver traceback) with a corrective insight.
- Failed sessions are kept as negative knowledge ("Traps" and "Warnings") to narrow future search, alongside positive Diagnosis/Prescription pairs.
- Limitations: EOM depends on explicit solver errors, so it cannot catch silent semantic mistakes, and it is vulnerable to noisy or hallucinated distilled experiences. Planned future work covers filtering low-quality experiences and extending to nonlinear optimization.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works

## Cite

Cite as: Wantong Xie, Yinghao Chen, Yi-Xiang Hu, Feng Wu, Jieyang Xu, Sijia Zhang and Xiangyang Li. 2026. Escaping the Sisyphus Dilemma: Experience Replay for Robust Text-to-Optimization Modeling. 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{xie2026escaping,
  title = {{Escaping the Sisyphus Dilemma: Experience Replay for Robust Text-to-Optimization Modeling}},
  author = {Wantong Xie, Yinghao Chen, Yi-Xiang Hu, Feng Wu, Jieyang Xu, Sijia Zhang and Xiangyang Li},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.690},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.690}
}
```

- [← previous Eraserhead at OSACT7 Shared Task: ASR Consistency Filtering and Speaker-Adaptive Post-Processing for Arabic Speech Diacritization](https://md.research.elamur.ai/free/en/papers/horaira-2026-eraserhead-osact7-shared-task-asr/)
- [next → eSciBench: An Extensible Scientific PDF Extraction Benchmark](https://md.research.elamur.ai/free/en/papers/taillon-2026-escibench-extensible-scientific-pdf-extraction/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/31/)

## References

28 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Ali AhmadiTeshnizi, Wenzhi Gao, Herman Brunborg, Shayan Talaei, Connor Lawless, and Madeleine Udell. 2024a. Optimus-0.3: Using large language models to model and solve optimization problems at scale. arXiv preprint arXiv:2407.19633. — [arXiv:2407.19633](https://arxiv.org/abs/2407.19633) [find](https://scholar.google.com/scholar?q=Ali+AhmadiTeshnizi%2C+Wenzhi+Gao%2C+Herman+Brunborg%2C+Shayan+Talaei%2C+Connor+Lawless%2C+and+Madeleine+Udell%2E+2024a%2E+Optimus%2D0%2E3%3A+Using+large+language+models+to+model+and+solve+optimization+problems+at+scale%2E+)
2. Ali AhmadiTeshnizi, Wenzhi Gao, and Madeleine Udell. 2024b. Optimus: Scalable optimization modeling with (mi) lp solvers and large language models. In Forty-first International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Ali+AhmadiTeshnizi%2C+Wenzhi+Gao%2C+and+Madeleine+Udell%2E+2024b%2E+Optimus%3A+Scalable+optimization+modeling+with+%28mi%29+lp+solvers+and+large+language+models%2E+In+Forty%2Dfirst+International+Conference+on+Machine+L)
3. Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2024. [Self-rag: Learning to retrieve, generate, and critique through self-reflection](https://md.research.elamur.ai/free/en/papers/asai-2023-self-rag-learning-retrieve-generate/). In The Twelfth International Conference on Learning Representations.
4. Nicolás Astorga, Tennison Liu, Yuanzhang Xiao, and Mihaela van der Schaar. 2025. Autoformulation of mathematical optimization models using llms. In Forty-second International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Nicol%C3%A1s+Astorga%2C+Tennison+Liu%2C+Yuanzhang+Xiao%2C+and+Mihaela+van+der+Schaar%2E+2025%2E+Autoformulation+of+mathematical+optimization+models+using+llms%2E+In+Forty%2Dsecond+International+Conference+on+Machine+Lea)
5. Albert Camus. 2013. The myth of Sisyphus. Penguin UK. [find](https://scholar.google.com/scholar?q=Albert+Camus%2E+2013%2E+The+myth+of+Sisyphus%2E+Penguin+UK%2E)
6. Xinyun Chen, Maxwell Lin, Nathanael Schärli, and Denny Zhou. 2023. Teaching large language models to self-debug. In The Twelfth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Xinyun+Chen%2C+Maxwell+Lin%2C+Nathanael+Sch%C3%A4rli%2C+and+Denny+Zhou%2E+2023%2E+Teaching+large+language+models+to+self%2Ddebug%2E+In+The+Twelfth+International+Conference+on+Learning+Representations%2E)
7. DeepSeek-AI. 2025. [Deepseek-v3.2: Pushing the frontier of open large language models](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-v3-2-pushing/).
8. Gurobi Optimization, LLC. 2025. Gurobi Optimizer Reference Manual. [find](https://scholar.google.com/scholar?q=Gurobi+Optimization%2C+LLC%2E+2025%2E+Gurobi+Optimizer+Reference+Manual%2E)
9. Chenyu Huang, Zhengyang Tang, Shixi Hu, Ruoqing Jiang, Xin Zheng, Dongdong Ge, Benyou Wang, and Zizhuo Wang. 2025. Orlm: A customizable framework in training large models for automated optimization modeling. Operations Research. [find](https://scholar.google.com/scholar?q=Chenyu+Huang%2C+Zhengyang+Tang%2C+Shixi+Hu%2C+Ruoqing+Jiang%2C+Xin+Zheng%2C+Dongdong+Ge%2C+Benyou+Wang%2C+and+Zizhuo+Wang%2E+2025%2E+Orlm%3A+A+customizable+framework+in+training+large+models+for+automated+optimization+mo)
10. Jie Huang, Xinyun Chen, Swaroop Mishra, Huaixiu Steven Zheng, Adams Wei Yu, Xinying Song, and Denny Zhou. 2024a. [Large language models cannot self-correct reasoning yet](https://md.research.elamur.ai/free/en/papers/huang-2023-large-language-models-cannot-self/). In The Twelfth International Conference on Learning Representations.
11. Xuhan Huang, Qingning Shen, Yan Hu, Anningzhe Gao, and Benyou Wang. 2024b. Mamo: a mathematical modeling benchmark with solvers. arXiv preprint arXiv:2405.13144. [find](https://scholar.google.com/scholar?q=Xuhan+Huang%2C+Qingning+Shen%2C+Yan+Hu%2C+Anningzhe+Gao%2C+and+Benyou+Wang%2E+2024b%2E+Mamo%3A+a+mathematical+modeling+benchmark+with+solvers%2E+arXiv+preprint+arXiv%3A2405%2E13144%2E)
12. Caigao Jiang, Xiang Shu, Hong Qian, Xingyu Lu, JUN ZHOU, Aimin Zhou, and Yang Yu. 2025. Llmopt: Learning to define and solve general optimization problems from scratch. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Caigao+Jiang%2C+Xiang+Shu%2C+Hong+Qian%2C+Xingyu+Lu%2C+JUN+ZHOU%2C+Aimin+Zhou%2C+and+Yang+Yu%2E+2025%2E+Llmopt%3A+Learning+to+define+and+solve+general+optimization+problems+from+scratch%2E+In+The+Thirteenth+International)
13. Hunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. 2023. [Let’s verify step by step](https://md.research.elamur.ai/free/en/papers/lightman-2023-let-s-verify-step-step/). In The Twelfth International Conference on Learning Representations.
14. Haoyang Liu, Jie Wang, Yuyang Cai, Xiongwei Han, Yufei Kuang, and Jianye HAO. 2025a. Optitree: Hierarchical thoughts generation with tree search for llm optimization modeling. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Haoyang+Liu%2C+Jie+Wang%2C+Yuyang+Cai%2C+Xiongwei+Han%2C+Yufei+Kuang%2C+and+Jianye+HAO%2E+2025a%2E+Optitree%3A+Hierarchical+thoughts+generation+with+tree+search+for+llm+optimization+modeling%2E+In+The+Thirty%2Dninth+Annu)
15. Yitao Liu, Chenglei Si, Karthik R Narasimhan, and Shunyu Yao. 2025b. Contextual experience replay for self-improvement of language agents. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 14179–14198. [find](https://scholar.google.com/scholar?q=Yitao+Liu%2C+Chenglei+Si%2C+Karthik+R+Narasimhan%2C+and+Shunyu+Yao%2E+2025b%2E+Contextual+experience+replay+for+self%2Dimprovement+of+language+agents%2E+In+Proceedings+of+the+63rd+Annual+Meeting+of+the+Association+)
16. Hongliang Lu, Zhonglin Xie, Yaoyu Wu, Can Ren, Yuxuan Chen, and Zaiwen Wen. 2025. Optmath: A scalable bidirectional data synthesis framework for optimization modeling. arXiv preprint arXiv:2502.11102. learning. Advances in Neural Information Processing Systems, 36:8634–8652. — [arXiv:2502.11102](https://arxiv.org/abs/2502.11102) [find](https://scholar.google.com/scholar?q=Hongliang+Lu%2C+Zhonglin+Xie%2C+Yaoyu+Wu%2C+Can+Ren%2C+Yuxuan+Chen%2C+and+Zaiwen+Wen%2E+2025%2E+Optmath%3A+A+scalable+bidirectional+data+synthesis+framework+for+optimization+modeling%2E+arXiv+preprint+arXiv%3A2502%2E11102%2E)
17. Segev Wasserkrug, Leonard Boussioux, Dick Den Hertog, Farzaneh Mirzazadeh, Ş Ilker Birbil, Jannis Kurtz, and Donato Maragno. 2025. Enhancing decision making through the integration of large language models and operations research optimization. In Proceedings of the AAAI Conference on Artificial Int… [find](https://scholar.google.com/scholar?q=Segev+Wasserkrug%2C+Leonard+Boussioux%2C+Dick+Den+Hertog%2C+Farzaneh+Mirzazadeh%2C+S%CC%A7+Ilker+Birbil%2C+Jannis+Kurtz%2C+and+Donato+Maragno%2E+2025%2E+Enhancing+decision+making+through+the+integration+of+large+language+)
18. 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](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). Advances in neural information processing systems, 35:24824–24837.
19. Ziyang Xiao, Dongxiang Zhang, Yangjun Wu, Lilin Xu, Yuan Jessica Wang, Xiongwei Han, Xiaojin Fu, Tao Zhong, Jia Zeng, Mingli Song, and 1 others. 2023. Chain-of-experts: When llms meet complex operations research problems. In The twelfth international conference on learning representations. [find](https://scholar.google.com/scholar?q=Ziyang+Xiao%2C+Dongxiang+Zhang%2C+Yangjun+Wu%2C+Lilin+Xu%2C+Yuan+Jessica+Wang%2C+Xiongwei+Han%2C+Xiaojin+Fu%2C+Tao+Zhong%2C+Jia+Zeng%2C+Mingli+Song%2C+and+1+others%2E+2023%2E+Chain%2Dof%2Dexperts%3A+When+llms+meet+complex+operatio)
20. Wantong Xie, Yi-Xiang Hu, Jieyang Xu, Feng Wu, and Xiangyang Li. 2025. Murka: Multi-reward reinforcement learning with knowledge alignment for optimization tasks. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Wantong+Xie%2C+Yi%2DXiang+Hu%2C+Jieyang+Xu%2C+Feng+Wu%2C+and+Xiangyang+Li%2E+2025%2E+Murka%3A+Multi%2Dreward+reinforcement+learning+with+knowledge+alignment+for+optimization+tasks%2E+In+The+Thirty%2Dninth+Annual+Conference)
21. 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](https://scholar.google.com/scholar?q=Aman+Madaan%2C+Niket+Tandon%2C+Prakhar+Gupta%2C+Skyler+Hallinan%2C+Luyu+Gao%2C+Sarah+Wiegreffe%2C+Uri+Alon%2C+Nouha+Dziri%2C+Shrimai+Prabhumoye%2C+Yiming+Yang%2C+and+1+others%2E+2023%2E+Self%2Drefine%3A+Iterative+refinement+with)
22. Zhicheng Yang, Yiwei Wang, Yinya Huang, Zhijiang Guo, Wei Shi, Xiongwei Han, Liang Feng, Linqi Song, Xiaodan Liang, and Jing Tang. 2024. Optibench meets resocratic: Measure and improve llms for optimization modeling. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Zhicheng+Yang%2C+Yiwei+Wang%2C+Yinya+Huang%2C+Zhijiang+Guo%2C+Wei+Shi%2C+Xiongwei+Han%2C+Liang+Feng%2C+Linqi+Song%2C+Xiaodan+Liang%2C+and+Jing+Tang%2E+2024%2E+Optibench+meets+resocratic%3A+Measure+and+improve+llms+for+optimi)
23. Stephen Maher, Matthias Miltenberger, João Pedro Pedroso, Daniel Rehfeldt, Robert Schwarz, and Felipe Serrano. 2016. PySCIPOpt: Mathematical programming in python with the SCIP optimization suite. In Mathematical Software – ICMS 2016, pages 301– 307. Springer International Publishing. [find](https://scholar.google.com/scholar?q=Stephen+Maher%2C+Matthias+Miltenberger%2C+Jo%C3%A3o+Pedro+Pedroso%2C+Daniel+Rehfeldt%2C+Robert+Schwarz%2C+and+Felipe+Serrano%2E+2016%2E+PySCIPOpt%3A+Mathematical+programming+in+python+with+the+SCIP+optimization+suite%2E+In+)
24. 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](https://scholar.google.com/scholar?q=Andrew+Zhao%2C+Daniel+Huang%2C+Quentin+Xu%2C+Matthieu+Lin%2C+Yong%2DJin+Liu%2C+and+Gao+Huang%2E+2024%2E+Expel%3A+Llm+agents+are+experiential+learners%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence%2C+v)
25. Xiaotian Pan, Junhao Fang, Feng Wu, Sijia Zhang, Yi-Xiang Hu, Shaoang Li, and Xiang-Yang Li. 2025. Guiding large language models in modeling optimization problems via question partitioning. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, pages 2657– 266… [find](https://scholar.google.com/scholar?q=Xiaotian+Pan%2C+Junhao+Fang%2C+Feng+Wu%2C+Sijia+Zhang%2C+Yi%2DXiang+Hu%2C+Shaoang+Li%2C+and+Xiang%2DYang+Li%2E+2025%2E+Guiding+large+language+models+in+modeling+optimization+problems+via+question+partitioning%2E+In+Proceed)
26. Lily Zhong, Zilong Wang, and Jingbo Shang. 2024. [Ldb: A large language model debugger via verifying runtime execution step-by-step](https://md.research.elamur.ai/free/en/papers/zhong-2024-debug-like-human-large-language/). arXiv preprint arXiv:2402.16906.
27. Rindranirina Ramamonjison, Timothy Yu, Raymond Li, Haley Li, Giuseppe Carenini, Bissan Ghaddar, Shiqi He, Mahdi Mostajabdaveh, Amin Banitalebi-Dehkordi, Zirui Zhou, and 1 others. 2023. Nl4opt competition: Formulating optimization problems based on their natural language descriptions. In NeurIPS 2022… [find](https://scholar.google.com/scholar?q=Rindranirina+Ramamonjison%2C+Timothy+Yu%2C+Raymond+Li%2C+Haley+Li%2C+Giuseppe+Carenini%2C+Bissan+Ghaddar%2C+Shiqi+He%2C+Mahdi+Mostajabdaveh%2C+Amin+Banitalebi%2DDehkordi%2C+Zirui+Zhou%2C+and+1+others%2E+2023%2E+Nl4opt+competit)
28. Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. 2023. Reflexion: Language agents with verbal reinforcement [find](https://scholar.google.com/scholar?q=Noah+Shinn%2C+Federico+Cassano%2C+Ashwin+Gopinath%2C+Karthik+Narasimhan%2C+and+Shunyu+Yao%2E+2023%2E+Reflexion%3A+Language+agents+with+verbal+reinforcement)

*Updated 2 November 2026*