The First Step of Decision Making: Alignment under Semantic Uncertainty for Automated Operations Research
Abstract
Problem definition: Automated operations research (OR) depends on correctly understanding the problem users intend to solve. In practice, limited user knowledge and vague expressions can obscure that problem, creating semantic uncertainty in the descriptions used for modeling. This uncertainty can lead to mathematical models that depart from users' intentions. We study semantic alignment to identify and correct errors or omissions in these descriptions before mathematical modeling. Methodology/results: We develop AMAO, an ambiguity-aware multi-agent framework for automated OR under semantic uncertainty. Its two-stage alignment process first uses semantic cues and contextual information to identify and correct potential semantic errors, then obtains additional information via human--AI interaction for further revision when the available context is insufficient. Specifically, AMAO integrates OR-guided mixture-of-experts (MoE) tuning and trajectory-based harness evolution to enhance semantic alignment capabilities. In addition, an ambiguity-aware benchmark and its matched multi-turn dialogue extension are proposed. Extensive experiments support that AMAO can recover the intended operational problem from ambiguous descriptions and recognize when available information is insufficient. Managerial implications: AMAO provides managers with an integrated workflow for translating ambiguous operational descriptions into mathematical models and optimization solutions. By combining semantic alignment with targeted user interaction, it supports recovery of the intended problem and improves downstream solution accuracy.
Related
- On the possibilities and limitations of LLM-based multi-agent systems for multi-criteria decision-making in healthcare operations management
- Credal Large Language Models for Semantic Commitment under Uncertainty
- Classes of Aggregation Rules for Ethical Decision Making in Automated Systems
- Generalized Semi-Infinite Programming for Robust Optimal Control with Decision-Dependent Uncertainty
- Aggregation Consistency in collective decision-making under uncertainty
BibTeX
@misc{she2026first,
title = {{The First Step of Decision Making: Alignment under Semantic Uncertainty for Automated Operations Research}},
author = {Chengxi She and Xingyu Lu and Yue Zhao and Qitao Shi and Caihua Chen},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.05169},
eprint = {2610.05169},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.05169},
}
RIS
TY - UNPB
TI - The First Step of Decision Making: Alignment under Semantic Uncertainty for Automated Operations Research
AU - Chengxi She
AU - Xingyu Lu
AU - Yue Zhao
AU - Qitao Shi
AU - Caihua Chen
PY - 2026
DA - 2026/10/12
PB - arXiv
DO - 10.48550/arxiv.2610.05169
UR - https://arxiv.org/abs/2610.05169
AB - Problem definition: Automated operations research (OR) depends on correctly understanding the problem users intend to solve. In practice, limited user knowledge and vague expressions can obscure that problem, creating semantic uncertainty in the descriptions used for modeling. This uncertainty can lead to mathematical models that depart from users' intentions. We study semantic alignment to identify and correct errors or omissions in these descriptions before mathematical modeling. Methodology/results: We develop AMAO, an ambiguity-aware multi-agent framework for automated OR under semantic uncertainty. Its two-stage alignment process first uses semantic cues and contextual information to identify and correct potential semantic errors, then obtains additional information via human--AI interaction for further revision when the available context is insufficient. Specifically, AMAO integrates OR-guided mixture-of-experts (MoE) tuning and trajectory-based harness evolution to enhance semantic alignment capabilities. In addition, an ambiguity-aware benchmark and its matched multi-turn dialogue extension are proposed. Extensive experiments support that AMAO can recover the intended operational problem from ambiguous descriptions and recognize when available information is insufficient. Managerial implications: AMAO provides managers with an integrated workflow for translating ambiguous operational descriptions into mathematical models and optimization solutions. By combining semantic alignment with targeted user interaction, it supports recovery of the intended problem and improves downstream solution accuracy.
ER -