AI Paper Atlas

Research map / Large language models / Agents, code and math

OR-R1: Automating Modeling and Solving of Operations Research Optimization Problem via Test-Time Reinforcement Learning

Zezhen Ding, Zhen Tan, Jiheng Zhang, Tianlong Chen

AAAI 2026 · Large language models › Agents, code and math · approach: LLMs for optimization and heuristics · 15 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add TGRPO on unlabeled test data after SFT(3K) (ablation)Qwen3-8B · OR benchmarks (average)solution accuracy (%): 64.6 -> 67.7Improved
add TGRPO on unlabeled test data after SFT(100) (ablation)Qwen3-8B · OR benchmarks (average)solution accuracy (%): 59.5 -> 65.9Improved
use Qwen3-8B instead of Qwen2.5-7B or Llama3-8B as SFT base (ablation)SFT(3K) · OR benchmarks (average)solution accuracy (%): 58.2 -> 64.6Improved
add format reward alone (ablation)TGRPO · OR benchmarks (average)solution accuracy (%): 66.0 -> 66.5Improved
add valid-code reward alone (ablation)TGRPO · OR benchmarks (average)solution accuracy (%): 66.0 -> 67.2Improved
add majority voting reward alone (ablation)TGRPO · OR benchmarks (average)solution accuracy (%): 66.0 -> 68.0Improved
combine all three rewards (ablation)TGRPO · OR benchmarks (average)solution accuracy (%): 66.0 -> 70.8Improved
add format reward on top of code and voting rewards (ablation)TGRPO · OR benchmarks (average)solution accuracy (%): 69.7 -> 70.8Improved
add RL rewards (full) on MAMO ComplexLP (ablation)TGRPO · MAMO ComplexLPsolution accuracy (%): 42.3 -> 66.8Improved
add RL rewards (full) on ComplexOR (ablation)TGRPO · ComplexORsolution accuracy (%): 44.4 -> 50.0Improved
add Rcode alone on ComplexOR (ablation)TGRPO · ComplexORsolution accuracy (%): 44.4 -> 38.9Hurt
add TGRPO training data from 10 to 50 samples per test set (ablation)TGRPO · OR benchmarks (average)solution accuracy (%): 66.0 -> 69.1Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy