LADeQ is an LLM-driven workflow that autonomously discovers and implements approximation algorithms for CCSD and CISD calculations, delivering speedups while respecting user-specified error tolerances.
arXiv preprint arXiv:2406.13163 , year=
13 Pith papers cite this work, alongside 16 external citations. Polarity classification is still indexing.
13
Pith papers citing it
16
external citations · external index
citation-role summary
background 4
citation-polarity summary
roles
background 4polarities
background 4representative citing papers
Introduces the Matter to Mechanism benchmark of 2,645 structured instances and a composite metric suite for evaluating AI co-scientists on problem-to-hypothesis reasoning in battery materials research.
ChatMOSP is an AI agent that maps natural-language descriptions of catalyst environments to validated multiscale simulations of working-state nanoparticle morphology and activity.
A Creator-Inspector multi-agent LLM pipeline for constitutive artificial neural networks increases the rate of models satisfying all nine physical constraints to 100% or 56% depending on the LLM backbone.
El Agente Quntur is a new multi-agent system that uses reasoning over literature and software documentation to autonomously handle the full workflow of quantum chemistry experiments in ORCA.
AlphaEvolve is an LLM-orchestrated evolutionary coding agent that discovered a 4x4 complex matrix multiplication algorithm using 48 scalar multiplications, the first improvement over Strassen's algorithm in 56 years, plus optimizations for Google data centers and hardware.
General-purpose LLMs recover 96% of low-energy Elpasolites via iterative in-context learning, surpassing task-specific models on an established benchmark.
GenoMAS deploys six specialized LLM agents with guided planning to preprocess transcriptomic data and identify genes, reaching 89.13% composite similarity and 60.48% F1 on the GenoTEX benchmark while outperforming prior methods.
My Chemical Harness performs evolutionary molecular design by searching over validated synthetic routes with LLMs restricted to high-level preferences, outperforming baselines on an sEH proxy task across multiple metrics.
PRISMat generates crystal slabs with mean absolute errors of 0.188 eV/A² for cleavage energy and 2.79 eV for work function, reducing error by 4× versus the next best model while using less inference time.
Larger LLMs handle detailed crystal descriptions better than small ones, and mean negative log-likelihood of predicted numbers tracks prediction error after fine-tuning.
Reinforcement fine-tuning of a generative model produces new topological insulators and crystalline insulators, exemplified by Ge2Bi2O6 with a 0.26 eV full band gap.
The paper proposes a four-role framework for LLMs in scientific innovation and reviews methods, benchmarks, and limitations across Assistant, Collaborator, Scientist, and Evaluator roles.
citing papers explorer
-
LLM-Guided Test-Time Discovery of Quantum-Chemical Approximation Algorithms
LADeQ is an LLM-driven workflow that autonomously discovers and implements approximation algorithms for CCSD and CISD calculations, delivering speedups while respecting user-specified error tolerances.
-
Matter to Mechanism: A Benchmark for AI Co-Scientists in Materials and Battery Research
Introduces the Matter to Mechanism benchmark of 2,645 structured instances and a composite metric suite for evaluating AI co-scientists on problem-to-hypothesis reasoning in battery materials research.
-
ChatMOSP: A Chemistry-Grounded Mobile Agent for Working-State Catalyst Simulations
ChatMOSP is an AI agent that maps natural-language descriptions of catalyst environments to validated multiscale simulations of working-state nanoparticle morphology and activity.
-
LLM-driven design of physics-constrained constitutive models: two agents are better than one
A Creator-Inspector multi-agent LLM pipeline for constitutive artificial neural networks increases the rate of models satisfying all nine physical constraints to 100% or 56% depending on the LLM backbone.
-
El Agente Quntur: A research collaborator agent for quantum chemistry
El Agente Quntur is a new multi-agent system that uses reasoning over literature and software documentation to autonomously handle the full workflow of quantum chemistry experiments in ORCA.
-
AlphaEvolve: A coding agent for scientific and algorithmic discovery
AlphaEvolve is an LLM-orchestrated evolutionary coding agent that discovered a 4x4 complex matrix multiplication algorithm using 48 scalar multiplications, the first improvement over Strassen's algorithm in 56 years, plus optimizations for Google data centers and hardware.
-
General-purpose LLMs as Constrained Crystal Composition Generators
General-purpose LLMs recover 96% of low-energy Elpasolites via iterative in-context learning, surpassing task-specific models on an established benchmark.
-
GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis
GenoMAS deploys six specialized LLM agents with guided planning to preprocess transcriptomic data and identify genes, reaching 89.13% composite similarity and 60.48% F1 on the GenoTEX benchmark while outperforming prior methods.
-
My Chemical Harness: Evolutionary Molecular Design over Synthetic Pathways with Large Language Model Agents
My Chemical Harness performs evolutionary molecular design by searching over validated synthetic routes with LLMs restricted to high-level preferences, outperforming baselines on an sEH proxy task across multiple metrics.
-
PRISMat: Policy-Driven, Permutation-Invariant Autoregressive Material Generation
PRISMat generates crystal slabs with mean absolute errors of 0.188 eV/A² for cleavage energy and 2.79 eV for work function, reducing error by 4× versus the next best model while using less inference time.
-
Scale-Dependent Input Representation and Confidence Estimation for LLMs in Materials Property Prediction
Larger LLMs handle detailed crystal descriptions better than small ones, and mean negative log-likelihood of predicted numbers tracks prediction error after fine-tuning.
-
Design Topological Materials by Reinforcement Fine-Tuned Generative Model
Reinforcement fine-tuning of a generative model produces new topological insulators and crystalline insulators, exemplified by Ge2Bi2O6 with a 0.26 eV full band gap.
-
Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluator
The paper proposes a four-role framework for LLMs in scientific innovation and reviews methods, benchmarks, and limitations across Assistant, Collaborator, Scientist, and Evaluator roles.