Optimizing the Optimizer: Language Models Discover Faster Molecular Relaxation
Summary
A paper showing an LLM agent rewriting the Sella molecular geometry optimizer to cut force-evaluation counts, producing AutoSella, a family of optimizers that reduces r2SCAN-3c DFT force calls to 40.2–77.2% of Sella's while matching energy reduction on held-out molecules.
View Cached Full Text
Cached at: 10/06/26, 12:55 PM
Paper page - Optimizing the Optimizer: Language Models Discover Faster Molecular Relaxation
Source: https://huggingface.co/papers/2610.06577
Abstract
Geometryoptimizationisamajorcostinmanyquantum-chemicalworkflows:eachoptimizationsteprequiresoneforceevaluation,andatthedensity-functionallevelthatevaluationdominatesthewalltime.Researchinthisareahasproducedabroadrangeofoptimizationmethods,andweaskwhetheralanguagemodelcanimproveonthebestofthemthroughautoresearch.Anagentrewritestheoptimizeritselftominimizeforce-callcounts,restrainedbytwoadmissiongatesthatrejectprematurestoppingandimprovementsthatdonotgeneralizetounseenmolecules.StartingfromSella,thefastestopen-sourceoptimizeravailable,thesearchproducesAutoSella,afamilyoftwooptimizers.Bothofthemdeliverconsistentforce-callreductionsrelativetoSellaacrossheld-outmolecularbenchmarksandpotentialsnotusedduringthesearch.Mostnotably,atther2SCAN-3cDFTlevel,thebestvariantrequiresonly40.2--77.2%ofSella’sforcecallswhileachievingthesameenergyreduction,eventhoughagentusednoDFTgradients.
View arXiv pageView PDFGitHub1Add to collection
Get this paper in your agent:
hf papers read 2610\.06577
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2610.06577 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2610.06577 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2610.06577 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
Automated optimization of a molecular simulation program
This article describes the automated optimization of the MBX molecular simulation program using compiler vectorization and parallel computation to enhance performance through SIMD instructions.
Do Language Models Dream of Binding Molecules? Benchmarking LLMs under Spatial Constraints
This paper benchmarks general-purpose LLMs against specialized diffusion models for generating binding molecules under 3D spatial constraints, finding that LLMs show promise despite currently lagging behind state-of-the-art approaches.
Improving Natural-Language Combinatorial-Optimization Accuracy in Resource-Constrained Language Models via Formal Abstractions
The paper introduces SDDL, a neuro-symbolic framework that improves combinatorial optimization accuracy in resource-constrained language models by translating natural-language problems into formal representations, resulting in higher feasibility rates compared to direct-generation and solver-code baselines.
AccelOpt: A Self-Improving LLM Agentic System for AI Accelerator Kernel Optimization
AccelOpt is a self-improving LLM agentic system that autonomously optimizes AI accelerator kernels through iterative generation and optimization memory, achieving 49-61% peak throughput improvements on AWS Trainium while being 26x cheaper than Claude Sonnet 4.
Zero-order Parameter-free Optimization for LMO-based Methods: Novel Approach for Efficient Fine-tuning
This paper introduces AdaNAGED, a method that combines zero-order optimization, parameter-free adaptation, and non-Euclidean update geometry for memory-efficient fine-tuning of large language models, with theoretical convergence guarantees and validation on the OPT-1.3B model.