Research map / Large language models / Agents, code and math
MATHMO: Automated Mathematical Modeling Through Adaptive Search
Tennison Liu, Mihaela van der Schaar
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add Pareto-UCB framework selection instead of random selection (ablation) | MATHMO · TSP, JSS, Ecology, Epidemiology | hypervolume: average hypervolume decrease of 2.5% with random selection | Improved |
| add Pareto-UCB framework selection instead of random selection (ablation) | MATHMO · Epidemiology | hypervolume: 0.939 -> 0.967 | Improved |
| add Pareto-UCB framework selection instead of random selection (ablation) | MATHMO · Ecology | hypervolume: 0.992 -> 0.992 | No clear effect |
| add bi-level search structure instead of flat search (ablation) | MATHMO · Epidemiology | hypervolume: 0.792 -> 0.967 | Improved |
| add bi-level search structure instead of flat search (ablation) | MATHMO · Ecology | hypervolume: 1.000 -> 0.992 | Hurt |
| add bi-level search structure instead of flat search (ablation) | MATHMO · JSS | hypervolume: 0.945 -> 0.994 | Improved |
| add surrogate-guided local exploration (ablation) | MATHMO · Ecology | hypervolume: 0.894 -> 0.992 | Improved |
| add surrogate-guided local exploration (ablation) | MATHMO · Epidemiology | hypervolume: 0.713 -> 0.967 | Improved |
| add surrogate-guided local exploration (ablation) | MATHMO · JSS | hypervolume: 0.973 -> 0.994 | Improved |
| use MATHMO instead of MEoH | MEoH · JSSP | hypervolume: 0.8587 -> 0.9655 | Improved |
| use MATHMO instead of FunSearch | FunSearch · Epidemiology | hypervolume: 0.6628 -> 0.9793 | Improved |
| remove symbolic regression from search space (ablation) | MATHMO · Ecology | hypervolume: 16.71% drop in hypervolume | Hurt |
Closest papers by meaning
- MathSmith: Towards Extremely Hard Mathematical Reasoning by Forging Synthetic Problems with a Reinforced Policy (AAAI 2026 · similarity 0.86)
- MM-Agent: LLM as Agents for Real-world Mathematical Modeling Problem (NeurIPS 2025 · similarity 0.86)
- MathSE: Improving Multimodal Mathematical Reasoning via Self-Evolving Iterative Reflection and Reward-Guided Fine-Tuning (AAAI 2026 · similarity 0.86)
- Autoformulation of Mathematical Optimization Models Using LLMs (ICML 2025 · similarity 0.85)
- We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning (ICLR 2026 · similarity 0.85)
- MARGE: Improving Math Reasoning with Guided Exploration (ICML 2025 · similarity 0.84)
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.
