Lune

ACL Findings2026

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

Wantong Xie, Yinghao Chen, Yi-Xiang Hu, Feng Wu, Jieyang Xu, Sijia Zhang, Xiangyang Li

Abstract

Large Language Models have shown promise in translating natural language into executable optimization models, yet they often suffer from the Sisyphus Dilemma: a memoryless cycle where identical errors are repeated across structurally similar problems. Existing retrieval-augmented strategies primarily fetch static problem-model pairs as few-shot demonstrators, failing to capture the dynamic reasoning required to resolve execution failures. To bridge this gap, we propose EOM, a framework that implements Experience Replay to transform transient rectification steps into persistent knowledge. EOM distills interaction histories into Causal Correction Mappings, indexing both diagnostic insights and prohibitive traps. By utilizing a structure-aware retrieval mechanism that aligns semantic intent with abstract syntax trees and solver tracebacks, the system enables models to recall specific correction strategies for isomorphic errors. Extensive experiments across seven benchmarks demonstrate that EOM improves modeling accuracy by 8.45% on complex tasks while reducing token consumption by 28.65% and interaction turns by 25.82%, validating the efficiency of a "Rectify Once, Solve Many" paradigm.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Large Language Models Cannot Self-Correct Reasoning Yet cites Teaching Large Language Models to Self-Debug
  • Large Language Models Cannot Self-Correct Reasoning Yet cites Reflexion: language agents with verbal reinforcement learning
  • Reflexion: language agents with verbal reinforcement learning cites Teaching Large Language Models to Self-Debug
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on13

  1. Reflexion: language agents with verbal reinforcement learningNoah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan et al.NeurIPS 2023 · 5,828 citations
  2. Let's Verify Step by StepHunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards et al.ICLR 2024 · 3,045 citations
  3. Self-RAG: Learning to Retrieve, Generate, and Critique through Self-ReflectionAkari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil et al.ICLR 2024 · 1,798 citations
  4. Teaching Large Language Models to Self-DebugXinyun Chen, Maxwell Lin, Nathanael Schärli, Denny ZhouICLR 2024 · 1,085 citations
  5. Large Language Models Cannot Self-Correct Reasoning YetJie Huang, Xinyun Chen, Swaroop Mishra, Huaixiu Steven Zheng et al.ICLR 2024 · 858 citations

Related papers

  1. AlphaOPT: Formulating Optimization Programs with Self-Improving LLM Experience LibraryMinwei Kong, Ao Qu, Xiaotong Guo, Wenbin Ouyang et al.KDD 2026 · 16 citations
  2. SAC-Opt: Semantic Anchors for Iterative Correction in Optimization ModelingYansen Zhang, Qingcan Kang, Yujie chen, Yufei Wang et al.ICML 2026
  3. Beyond Experience Retrieval: Learning to Generate Utility-Optimized Structured Experience for Frozen LLMsXuancheng Li, Haitao Li, Yujia Zhou, Yiqun Liu et al.ACL 2026 · 1 citation
  4. a1: Steep Test-time Scaling Law via Environment Augmented GenerationLingrui Mei, Shenghua Liu, Yiwei Wang, Baolong Bi et al.ACL Findings 2026
  5. LEMMA: Learning from Errors for MatheMatical Advancement in LLMsZhuoshi Pan, Yu Li, Honglin Lin, Qizhi Pei et al.ACL Findings 2025 · 1 citation
Dusk over the sea between two cliffs drawn in fine vertical lines