The paper introduces a self‑guided reasoning framework that enables large language models (LLMs) to detect and correct errors in Vehicle Routing Problem (VRP) instances. By autonomously generating code that offers structured insights, the approach addresses limitations of existing methods, especially for complex instances or errors that increase reasoning load. Experiments across various problem settings and LLMs show that this framework markedly improves error detection, achieving near‑perfect accuracy.
By Ni Zhang, Jianan Zhou, Yue-Jiao Gong, Zhiguang Cao
arXiv:2510.07073v2 Announce Type: replace
Abstract: Designing high-performing heuristics for vehicle routing problems (VRPs) is a complex task that requires both intuition and deep domain knowledge....
By Andr\'e Hottung, Federico Berto, Chuanbo Hua, Nayeli Gast Zepeda, Daniel Wetzel, Michael R\"omer, Haoran Ye, Davide Zago, Michael Poli, Stefano Massaroli, Jinkyoo Park, Kevin Tierney
arXiv:2606. 27757v1 Announce Type: new Abstract: Large language models (LLMs) have attracted widespread attention from academia and industry, yet their deployment raises critical security concerns regarding robustness and reliability.
By Jiajing Zhang, Jiamei Jiang, Chenyang Zhang, Feifei Mo, Linjing Li, Daniel Zeng
arXiv:2602. 23092v2 Announce Type: replace Abstract: The Capacitated Vehicle Routing Problem (CVRP), a fundamental combinatorial optimization challenge, focuses on optimizing fleet operations under vehicle capacity constraints.
By Zhuoliang Xie, Fei Liu, Zhenkun Wang, Qingfu Zhang
arXiv:2611.06606v1 Announce Type: new
Abstract: Large language models can solve many multi-step reasoning problems, but their reasoning remains brittle: plausible intermediate steps often lead to inc...
By Ekaterina Fadeeva, Xueyan Li, Mrinmaya Sachan, Maxim Panov
AdaR is a framework designed to enhance large language models (LLMs) with adaptive reasoning for mathematical tasks. It identifies and mitigates spurious reasoning—where models rely on superficial correlations—by generating logically equivalent queries and training with Reinforcement Learning with Verifiable Rewards (RLVR) to penalize incorrect logic and promote adaptive logic. The approach includes extracting problem‑solving logic, executing code to verify answers, and applying sanity checks, resulting in significant gains in mathematical reasoning performance and improved data efficiency.
By Zhejian Lai, Xiang Geng, Zhijun Wang, Yang Bai, Jiahuan Li, Rongxiang Weng, Jingang Wang, Xuezhi Cao, Xunliang Cai, Shujian Huang
arXiv:2609.15145v1 Announce Type: new
Abstract: The reasoning ability of large language models (LLMs) is a critical factor for practical LLM-based applications. To investigate the current reasoning c...
By Runa Yoshida, Kosuke Nishida, Kyosuke Nishida
arXiv:2511. 09373v2 Announce Type: replace-cross Abstract: LLMs now tackle a wide range of software-related tasks, yet we show that their performance varies markedly both across and within these tasks.
By Adam \v{S}torek, Vikas Upadhyay, Marianne Menglin Liu, Daniel W. Peterson, Anshul Mittal, Sujeeth Bharadwaj, Fahad Shah, Sujith Ravi, Dan Roth
arXiv:2604. 16694v2 Announce Type: replace Abstract: Large reasoning models (LRMs) enhance problem-solving capabilities by generating explicit multi-step chains of thought (CoT) reasoning; however, they incur substantial inference latency and computational overhead.
By Jiayi Tian, Yupeng Su, Ryan Solgi, Souvik Kundu, Zheng Zhang
arXiv:2606. 06635v1 Announce Type: cross Abstract: Failures in language model reasoning emerge through distinct processes that leave identifiable signatures in the reasoning trace.
By Tanvi Thoria, Kiana Jafari, Marc R. Schlichting, Mykel J. Kochenderfer
The paper introduces an automated method that employs Large Language Models in a check–fix–verify loop to generate executable Python scripts for extracting problem-specific features from constraint satisfaction problems. Given a MiniZinc model and instance, the LLM agent produces code that builds a typed graph representation and computes structural properties such as graph density, variable clustering, and constraint tightness. Evaluated on vehicle routing, car sequencing, and fixed‑length error‑correcting codes, the synthesized extractors enable algorithm selectors that outperform expert‑curated mzn2feat features and transformer‑based trans2feat variants, while remaining interpretable.
By Hai Xia, Carlos Ans\'otegui, Stefan Szeider
arXiv:2607. 20474v1 Announce Type: new Abstract: Natural language interfaces can greatly benefit the accessibility and usability of optimization modeling, and recent advances in large language models (LLMs) show promise in automatically translating textual problem descriptions into executable solver formulations.
By Sumaya Abdul Rahman, Seckhen Ariel Andrade Cuellar, Ghani Raissov, Mohammad Raza