mlsanityData to 14 Oct 2026

OptArgus: A Multi-Agent System to Detect Hallucinations in LLM-based Optimization Modeling

arXiv 2605.11738 ↗First posted 12 May 2026cs.AIcited by 3

On the map: LLM agents and tool use → Medical and scientific domain agents

Abstract (arXiv)

Large language models (LLMs) are increasingly used to translate natural-language optimization problems into mathematical formulations and solver code, but matching the reference objective value is not a reliable test of correctness: an artifact may agree numerically while still changing the underlying optimization semantics. We formulate this issue as optimization-modeling hallucination detection, namely structural consistency auditing over the problem description, symbolic model, and solver implementation. We develop, to our knowledge, the first fine-grained hallucination taxonomy specifically for optimization modeling, spanning objective, variable, constraint, and implementation failures. We use this taxonomy to design OptArgus, a multi-agent detector with conductor routing, specialist auditors, and evidence consolidation. To evaluate this setting, we introduce a three-part benchmark suite with 484 clean artifacts, 1266 controlled injected artifacts, and 6292 natural LLM-generated artifacts. Against a matched single-agent baseline, OptArgus produces fewer false alarms on clean artifacts, more accurate top-ranked localization on controlled single-error cases, and stronger detection on natural model outputs. Together, these contributions turn optimization-modeling hallucination detection into a concrete empirical problem and suggest that modular, taxonomy-grounded auditing is a practical route to more reliable optimization modeling.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use. Builds on 6 of its 33 references that are in the map. First posted on arXiv 12 May 2026.

Builds on

6 of 33 references.

References · 6

  1. 2024Improve Mathematical Reasoning in Language Models by Automated Process Supervisioncited by 441
  2. 2025Enhancing Mathematical Reasoning in Large Language Models with Self-Consistency-Based Hallucination Detectioncited by 13
  3. 2026Constructing Industrial-Scale Optimization Modeling Benchmarkcited by 12
  4. 2025ORGEval: Graph-Theoretic Evaluation of LLMs in Optimization Modelingcited by 10
  5. 2025Peering Inside the Black Box: Uncovering LLM Errors in Optimization Modelling through Component-Level Evaluationcited by 3
  6. 2026ProOPF: Benchmarking and Improving LLMs for Professional-Grade Power Systems Optimization Modelingcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limitscited by 1
  2. 2026Admission Without Answers: Label-Free Certification and Experience Learning for LLM-Based Optimization Modelingcited by 0
  3. 2026Right Answers, Costly Models: The Efficiency Gap in LLM-based Optimization Modelingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Internal Representations as Indicators of Hallucinations in Agent Tool Selection
  2. 2026MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
  3. 2026AgentHallu: Benchmarking Automated Hallucination Attribution of LLM-based Agents
  4. 2026HalluClear: Diagnosing, Evaluating and Mitigating Hallucinations in GUI Agents
  5. 2026Closed-World Resolution Against Tool Hallucination in LLM Agents
  6. 2026Reasoning Error from Known Fact: Step-Level Self-Consistency Group Relative Policy Optimization for LLM
  7. 2026The Hallucination Snowball: Modeling Error Propagation as State Transitions in Multi-Agent LLM Pipelines
  8. 2025MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them