Research map / Large language models / Reasoning and chain of thought

DeepOR: A Deep Reasoning Foundation Model for Optimization Modeling

AAAI 2026 · Large language models › Reasoning and chain of thought · approach: Routing, pruning and distillation for reasoning · 2 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes DeepOR, a deep reasoning foundation model for optimization modeling, motivated by the limits of straightforward input-output LLMs on hard instances. Only the abstract is available, so details are limited.

Problem

LLMs tailored for optimization modeling typically use a straightforward input-output paradigm and struggle with challenging optimization modeling instances.

Approach

Brings deep, generative-style reasoning (as in recent reasoning-oriented LLMs) into optimization modeling, moving beyond direct input-output mapping. Details beyond the abstract are not available.

Limitations

• Only the abstract was available; experimental details unknown

Closest papers by meaning

• DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search (ICLR 2026 · similarity 0.90)
• Solver-Informed RL: Grounding Large Language Models for Authentic Optimization Modeling (NeurIPS 2025 · similarity 0.90)
• Step-by-Step Optimization-like Reasoning in LLMs over Expanding Search Spaces (NeurIPS 2026 · similarity 0.89)
• DeepCompress: A Dual Reward Strategy for Dynamically Exploring and Compressing Reasoning Chains (ICLR 2026 · similarity 0.89)
• Rectifying LLM Thought from Lens of Optimization (ICLR 2026 · similarity 0.89)
• MATH-Beyond: A Benchmark for RL to Expand Beyond the Base Model (ICLR 2026 · similarity 0.88)