OR-Space is a benchmark for LLM agents performing full-lifecycle optimization tasks across Build, Revise, and Explain modes in executable multi-artifact workspaces.
hub
arXiv preprint arXiv:2307.03875 (2023)
16 Pith papers cite this work, alongside 3 external citations. Polarity classification is still indexing.
16
Pith papers citing it
3
external citations · Pith
abstract
Supply chain operations traditionally involve a variety of complex decision making problems. Over the last few decades, supply chains greatly benefited from advances in computation, which allowed the transition from manual processing to automation and cost-effective optimization. Nonetheless, business operators still need to spend substantial efforts in explaining and interpreting the optimization outcomes to stakeholders. Motivated by the recent advances in Large Language Models (LLMs), we study how this disruptive technology can help bridge the gap between supply chain automation and human comprehension and trust thereof. We design OptiGuide -- a framework that accepts as input queries in plain text, and outputs insights about the underlying optimization outcomes. Our framework does not forgo the state-of-the-art combinatorial optimization technology, but rather leverages it to quantitatively answer what-if scenarios (e.g., how would the cost change if we used supplier B instead of supplier A for a given demand?). Importantly, our design does not require sending proprietary data over to LLMs, which can be a privacy concern in some circumstances. We demonstrate the effectiveness of our framework on a real server placement scenario within Microsoft's cloud supply chain. Along the way, we develop a general evaluation benchmark, which can be used to evaluate the accuracy of the LLM output in other scenarios.
hub tools
citation-role summary
background 4
citation-polarity summary
roles
background 4representative citing papers
ORPilot is the first agentic LLM system built specifically for production optimization modeling, using interview, data collection, parameter computation agents and a solver-agnostic intermediate representation to handle real-world ambiguous problems and large raw datasets.
DeInfer reduces parallel inference communication cost for decomposed LLMs by up to 78% by moving collective operations into the low-rank latent space and redesigning KV-cache reconstruction for static graph compatibility.
AgileLog introduces forkable shared logs with cheap forking and isolation to support AI agents on data streams.
ORThought is a structured dual-agent framework with expert chain-of-thought reasoning that outperforms baselines by 9-17 percentage points on the new LogiOR logistics optimization benchmark while improving token efficiency.
LLM agent translates user prompts into model patches and selects primal-aware re-optimization techniques for large-scale dynamic problems, shown on supply-chain and exam-scheduling cases.
A queueing model derives stability conditions for LLM inference services under combined compute and KV cache memory limits, with experimental validation showing typical deviations under 10%.
InvEvolve evolves inventory policies using LLMs with RL and provides statistical safety guarantees, outperforming classical and DL methods on synthetic and real data.
A multi-agent LLM framework with iterative feedback loops achieves state-of-the-art accuracy on 3 of 4 optimization modeling benchmarks by decomposing the NL-to-code pipeline into specialized, self-correcting stages.
A Prolog skill enables LLMs to structure placement intent into facts and queries while delegating constraint reasoning to symbolic logic for cloud-edge service placement.
TabGRAA applies group-relative advantage alignment in an iterative reward-guided post-training loop to improve tabular language model generators on fidelity, utility, and privacy trade-offs across five benchmarks.
A two-step agentic system for extracting insights from VSM simulations achieves up to 86% accuracy with top LLMs by using progressive data discovery and slim context.
An LLM- and VLM-powered workflow integrated with knowledge graphs and model-driven engineering is proposed for analyzing RISC-V semiconductor supply chain data and resilience.
LLM-based agents simulating supply chain tiers exhibit known behavioral biases, and information sharing mitigates resulting inefficiencies.
Proposes a five-bucket taxonomy of LLM harms and calls for dynamic auditing, but the systematic review behind it is not reproducible and contains mismatched citations.
A survey compiling roles, applications, benchmarks, challenges, and future directions for large language models in operations research.
citing papers explorer
-
OR-Space: A Full-Lifecycle Workspace Benchmark for Industrial Optimization Agents
OR-Space is a benchmark for LLM agents performing full-lifecycle optimization tasks across Build, Revise, and Explain modes in executable multi-artifact workspaces.
-
ORPilot: A Production-Oriented Agentic LLM-for-OR Tool for Optimization Modeling
ORPilot is the first agentic LLM system built specifically for production optimization modeling, using interview, data collection, parameter computation agents and a solver-agnostic intermediate representation to handle real-world ambiguous problems and large raw datasets.
-
Co-evolving Agent Architectures and Interpretable Reasoning for Automated Optimization
DeInfer reduces parallel inference communication cost for decomposed LLMs by up to 78% by moving collective operations into the low-rank latent space and redesigning KV-cache reconstruction for static graph compatibility.
-
AgileLog: A Forkable Shared Log for Agents on Data Streams
AgileLog introduces forkable shared logs with cheap forking and isolation to support AI agents on data streams.
-
ORThought: Benchmarking and Automating Logistics Optimization Modeling
ORThought is a structured dual-agent framework with expert chain-of-thought reasoning that outperforms baselines by 9-17 percentage points on the new LogiOR logistics optimization benchmark while improving token efficiency.
-
Democratizing Large-Scale Re-Optimization with LLM-Guided Model Patches
LLM agent translates user prompts into model patches and selects primal-aware re-optimization techniques for large-scale dynamic problems, shown on supply-chain and exam-scheduling cases.
-
A Queueing-Theoretic Framework for Stability Analysis of LLM Inference with KV Cache Memory Constraints
A queueing model derives stability conditions for LLM inference services under combined compute and KV cache memory limits, with experimental validation showing typical deviations under 10%.
-
InvEvolve: Evolving White-Box Inventory Policies via Large Language Models with Performance Guarantees
InvEvolve evolves inventory policies using LLMs with RL and provides statistical safety guarantees, outperforming classical and DL methods on synthetic and real data.
-
OptiAgent: End-to-End Optimization Modeling via Multi-Agent Iterative Refinement
A multi-agent LLM framework with iterative feedback loops achieves state-of-the-art accuracy on 3 of 4 optimization modeling benchmarks by decomposing the NL-to-code pipeline into specialized, self-correcting stages.
-
A Neurosymbolic Prolog Skill for LLM-Driven Service Placement
A Prolog skill enables LLMs to structure placement intent into facts and queries while delegating constraint reasoning to symbolic logic for cloud-edge service placement.
-
Self-Improving Tabular Language Models via Iterative Reward-Guided Post-Training
TabGRAA applies group-relative advantage alignment in an iterative reward-guided post-training loop to improve tabular language model generators on fidelity, utility, and privacy trade-offs across five benchmarks.
-
Agentic Insight Generation in VSM Simulations
A two-step agentic system for extracting insights from VSM simulations achieves up to 86% accuracy with top LLMs by using progressive data discovery and slim context.
-
GenAI-Driven Approach to RISC-V Supply Chain Exploration
An LLM- and VLM-powered workflow integrated with knowledge graphs and model-driven engineering is proposed for analyzing RISC-V semiconductor supply chain data and resilience.
-
Dynamics of Cognitive Heterogeneity: Investigating Behavioral Biases in Multi-Stage Supply Chains with LLM-Based Simulation
LLM-based agents simulating supply chain tiers exhibit known behavioral biases, and information sharing mitigates resulting inefficiencies.
-
LLM Harms: A Taxonomy and Discussion
Proposes a five-bucket taxonomy of LLM harms and calls for dynamic auditing, but the systematic review behind it is not reproducible and contains mismatched citations.
-
Large Language Models for Operations Research: A Comprehensive Survey
A survey compiling roles, applications, benchmarks, challenges, and future directions for large language models in operations research.