Optimization modeling enables critical decisions across industries but remains difficult to automate: informal language must be mapped to precise mathematical formulations and executable solver code. Prior LLM approaches either rely on brittle prompting or costly retraining with limited generalization. We present AlphaOPT, a self-improving experience library that enables an LLM to learn from limited demonstrations (even answers alone, without gold-standard programs) and solver feedback - without annotated reasoning traces or parameter updates. AlphaOPT operates in a continual two-phase cycle: (i) a Library Learning phase that reflects on failed attempts, extracting solver-verified, structured insights as {taxonomy, condition, explanation, example}; and (ii) a Library Evolution phase that diagnoses retrieval misalignments and refines the applicability conditions of stored insights, improving transfer across tasks. This design (1) learns efficiently from limited demonstrations without curated rationales, (2) expands continually without costly retraining by updating the library rather than model weights, and (3) makes knowledge explicit and interpretable for human inspection and intervention. Experiments show that AlphaOPT steadily improves with more data (65% to 72% from 100 to 300 training items) and surpasses the strongest baseline by 7.7% on the out-of-distribution OptiBench dataset when trained only on answers. Code and data are available at: https://github.com/Minw913/AlphaOPT.

Building on advancements in Large Language Models (LLMs), we can tackle complex analytical and mathematical reasoning tasks requiring nuanced contextual understanding. A prime example of such complex tasks is modelling resource allocation optimization in networks, which extends beyond translating natural language inputs into mathematical equations or Linear Programming (LP), Integer Linear Programming (ILP), and Mixed-Integer Linear Programming (MILP) models. However, existing benchmarks and datasets cannot address the complexities of such problems with dynamic environments, interdependent variables, and heterogeneous constraints. To address this gap, we introduce NL4RA, a curated dataset comprising 50 resource allocation optimization problems formulated as LP, ILP, and MILP. We then evaluate the performance of well-known open-source LLMs with varying parameter counts. To enhance existing LLM based methods, we introduce LM4Opt RA, a multi candidate framework that applies diverse prompting strategies such as direct, few shot, and chain of thought, combined with a structured ranking mechanism to improve accuracy. We identified discrepancies between human judgments and automated scoring such as ROUGE, BLEU, or BERT scores. However, human evaluation is time-consuming and requires specialized expertise, making it impractical for a fully automated end-to-end framework. To quantify the difference between LLM-generated responses and ground truth, we introduce LLM-Assisted Mathematical Evaluation (LAME), an automated metric designed for mathematical formulations. Using LM4Opt-RA, Llama-3.1-70B achieved a LAME score of 0.8007, outperforming other models by a significant margin, followed closely by Llama-3.1-8B. While baseline LLMs demonstrate considerable promise, they still lag behind human expertise; our proposed method surpasses these baselines regarding LAME and other metrics.

In this reproducibility study, we revisit the LLAMBO framework of Daxberger et al. (2024), a prompting-based Bayesian optimization (BO) method that uses large language models as discriminative surrogates and acquisition optimizers via text-only interactions. We replicate the core Bayesmark and HPOBench experiments under the original evaluation protocol, but replace GPT-3.5 with the open-weight Llama 3.1 70B model used for all text encoding components. Our results broadly confirm the main claims of LLAMBO. Contextual warm starting via textual problem and hyperparameter descriptions substantially improves early regret behaviour and reduces variance across runs. LLAMBO's discriminative surrogate is weaker than GP or SMAC as a pure single task regressor, yet benefits from cross task semantic priors induced by the language model. Ablations that remove textual context markedly degrade predictive accuracy and calibration, while the LLAMBO candidate sampler consistently generates higher quality and more diverse proposals than TPE or random sampling. Experiments with smaller backbones (Gemma 27B, Llama 3.1 8B) yield unstable or invalid predictions, suggesting insufficient capacity for reliable surrogate behaviour. Overall, our study shows that the LLAMBO architecture is robust to changing the language model backbone and remains effective when instantiated with Llama 3.1 70B.

Recently, using Large Language Models (LLMs) to generate optimization models from natural language descriptions has became increasingly popular. However, a major open question is how to validate that the generated models are correct and satisfy the requirements defined in the natural language description. In this work, we propose a novel agent-based method for automatic validation of optimization models that builds upon and extends methods from software testing to address optimization modeling . This method consists of several agents that initially generate a problem-level testing API, then generate tests utilizing this API, and, lastly, generate mutations specific to the optimization model (a well-known software testing technique assessing the fault detection power of the test suite). In this work, we detail this validation framework and show, through experiments, the high quality of validation provided by this agent ensemble in terms of the well-known software testing measure called mutation coverage.

One of the long-standing goals in optimisation and constraint programming is to describe a problem in natural language and automatically obtain an executable, efficient model. Large language models appear to bring this vision closer, showing impressive results in automatically generating models for classical benchmarks. However, much of this apparent success may derive from data contamination rather than genuine reasoning: many standard CP problems are likely included in the training data of these models. To examine this hypothesis, we systematically rephrased and perturbed a set of well-known CSPLib problems to preserve their structure while modifying their context and introducing misleading elements. We then compared the models produced by three representative LLMs across original and modified descriptions. Our qualitative analysis shows that while LLMs can produce syntactically valid and semantically plausible models, their performance drops sharply under contextual and linguistic variation, revealing shallow understanding and sensitivity to wording.

LLM-based solvers have emerged as a promising means of automating problem modeling and solving. However, they remain unreliable and often depend on iterative repair loops that result in significant latency. We introduce OptiHive, a framework that enhances any solver-generation pipeline to produce higher-quality solvers from natural-language descriptions of optimization problems. OptiHive uses a single batched generation to produce diverse components (solvers, problem instances, and validation tests) and filters out erroneous components to ensure fully interpretable outputs. Accounting for the imperfection of the generated components, we employ a statistical model to infer their true performance, enabling principled uncertainty quantification and solver selection. On tasks ranging from traditional optimization problems to challenging variants of the Multi-Depot Vehicle Routing Problem, OptiHive significantly outperforms baselines, increasing the optimality rate from 5% to 92% on the most complex problems.

Answer Set Programming (ASP) is a declarative programming paradigm based on logic programming and non-monotonic reasoning. It is a tremendously powerful tool for describing and solving combinatorial problems. Like any other language, ASP requires users to learn how it works and the syntax involved. It is becoming increasingly required for those unfamiliar with programming languages to interact with code. This paper proposes a novel method of translating unconstrained English into ASP programs for logic puzzles using an LLM and Abstract Meaning Representation (AMR) graphs. Everything from ASP rules, facts, and constraints is generated to fully represent and solve the desired problem. Example logic puzzles are used to demonstrate the capabilities of the system. While most current methods rely entirely on an LLM, our system minimizes the role of the LLM only to complete straightforward tasks. The LLM is used to simplify natural language sentences, identify keywords, and generate simple facts. The AMR graphs are then parsed from simplified language and used to generate ASP constraints systematically. The system successfully creates an entire ASP program that solves a combinatorial logic problem. This approach is a significant first step in creating a lighter-weight, explainable system that converts natural language to solve complex logic problems.

Large Language Models (LLMs) often exhibit limited logical coherence, mapping premises to conclusions without adherence to explicit inference rules. We propose Proof-Carrying Reasoning with LLMs (PCRLLM), a framework that constrains reasoning to single-step inferences while preserving natural language formulations. Each output explicitly specifies premises, rules, and conclusions, thereby enabling verification against a target logic. This mechanism mitigates trustworthiness concerns by supporting chain-level validation even in black-box settings. Moreover, PCRLLM facilitates systematic multi-LLM collaboration, allowing intermediate steps to be compared and integrated under formal rules. Finally, we introduce a benchmark schema for generating large-scale step-level reasoning data, combining natural language expressiveness with formal rigor.

Competitive programming benchmarks are widely used in scenarios such as programming contests and large language model assessments. However, the growing presence of duplicate or highly similar problems raises concerns not only about competition fairness, but also about the validity of competitive programming as a benchmark for model evaluation. In this paper, we propose a new problem, similar question retrieval, to tackle this issue. Due to the lack of both data and models, solving this problem is challenging. To this end, we introduce CPRet, a retrieval-oriented benchmark suite for competitive programming, covering four retrieval tasks: two code-centric (i.e., Text-to-Code, Code-to-Code) and two newly proposed problem-centric tasks (i.e., Problem-to-Duplicate, Simplified-to-Full) built from a combination of automatically crawled problem-solution data and manually curated annotations. Our contribution includes both high-quality training data and temporally separated test sets for reliable evaluation. Besides, we further develop two task-specialized retrievers based on this dataset: CPRetriever-Code, trained with a novel Group-InfoNCE loss for problem-code alignment, and CPRetriever-Prob, fine-tuned for identifying problem-level similarity. Both models achieve strong results and are open-sourced for local use. Finally, we analyze LiveCodeBench and find that high-similarity problems inflate model pass rates and reduce differentiation, underscoring the need for similarity-aware evaluation in future benchmarks. Github: https://github.com/coldchair/CPRet Online Demo: https://www.cpret.online/