Newest papers

VERAS: Verification-Guided Adaptive Search for Reliable Operations Research

Minbo Ma, Honglin Zhang, Bangtao Zhou, Chunguang Yu, Dasheng Ju, Yichen Shen, Fengli Xu, Yong Li · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.24329 · cited by 0 works (OpenAlex) · open-access PDF

Spanish

Los avances en el razonamiento, codificación y uso de herramientas permiten que los agentes de LLM resuelvan problemas de investigación de operaciones (OR) a través de modelado iterativo de problemas, construcción de programas y verificación. Sin embargo, pasar la verificación auténtica no garantiza que las soluciones cumplan con las restricciones de tareas y cumplan con la calidad de la optimización. Esta brecha puede surgir de errores de especificación correlacionados, donde el programa generado y sus controles comparten omisiones o malinterpretaciones de los requisitos de tareas, junto con la cobertura de verificación incompleta y estrategias de optimización ineficaces. Proponemos VERAS, una herramienta de búsqueda adaptativa guiada por verificación para confiable OU que utiliza la verificación para priorizar la reparación de la viabilidad

Machine translation (Meta M2M100); the English original follows.

Abstract

Advances in reasoning, coding, and tool use enable LLM agents to solve operations research (OR) problems through iterative problem modeling, program construction, and verification. Yet passing self-authored verification does not ensure that the solutions satisfy task constraints and meet optimization quality. This gap can arise from correlated specification errors, where the generated program and its checks share omissions or misinterpretations of task requirements, alongside incomplete verification coverage and ineffective optimization strategies. We propose VERAS, a verification-guided adaptive search harness for reliable OR that uses verification evidence to prioritize feasibility repair, constraint-coverage review, and solution-quality improvement. VERAS combines task-specific solution checkers with a separate verification agent to examine candidate solutions against the task requirements. It uses verification feedback to guide feasibility repair, additional constraint checking, and objective improvement, while candidate acceptance criteria screen revisions for deterioration in output validity or constraint satisfaction. On ORAgentBench, VERAS achieves a 42.99% pass rate, exceeding the reported 35.51% of Codex using the same LLM. Across two industrial-scale OR problems, VERAS reduces inter-datacenter peak bandwidth by 10.34% relative to native Codex and lowers annualized distribution network planning costs by 6.28% compared with expert-designed solutions. Code and evidence are available at https://github.com/holimario/VERAS.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Task (project management), Constraint (computer-aided design), Code (set theory), Set (abstract data type), Software verification

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange