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
Fortschritte bei der Begründung, Codierung und Verwendung von Werkzeugen ermöglichen es LLM-Agenten, Operationsforschung (OR) -Probleme durch iterative Problemmodellierung, Programmbau und Verifizierung zu lösen. Dennoch gewährleistet die Übermittlung einer selbstverfassten Verifizierung nicht, dass die Lösungen Aufgabenbeschränkungen erfüllen und die Qualität der Optimierung erfüllen. Diese Lücke kann aus korrelierten Spezifikationsfehlern resultieren, bei denen das erzeugte Programm und seine Kontrollen Auslassungen oder Fehlinterpretationen der Aufgabenanforderungen teilen, zusammen mit unvollständiger Verifizierung und ineffektiven Optimierungsstrategien. Wir schlagen VERAS vor, ein verifizierungsgeleitetes adaptives Suchgerät für zuverlässige OR, das Verifizierungs
Machine translation (Meta M2M100); the English original follows.
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
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.24329, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange