REVIEW 30 cited by
LLM-SR: Scientific Equation Discovery via Programming with Large Language Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
LLM-SR: Scientific Equation Discovery via Programming with Large Language Models
read the original abstract
Mathematical equations have been unreasonably effective in describing complex natural phenomena across various scientific disciplines. However, discovering such insightful equations from data presents significant challenges due to the necessity of navigating extremely large combinatorial hypothesis spaces. Current methods of equation discovery, commonly known as symbolic regression techniques, largely focus on extracting equations from data alone, often neglecting the domain-specific prior knowledge that scientists typically depend on. They also employ limited representations such as expression trees, constraining the search space and expressiveness of equations. To bridge this gap, we introduce LLM-SR, a novel approach that leverages the extensive scientific knowledge and robust code generation capabilities of Large Language Models (LLMs) to discover scientific equations from data. Specifically, LLM-SR treats equations as programs with mathematical operators and combines LLMs' scientific priors with evolutionary search over equation programs. The LLM iteratively proposes new equation skeleton hypotheses, drawing from its domain knowledge, which are then optimized against data to estimate parameters. We evaluate LLM-SR on four benchmark problems across diverse scientific domains (e.g., physics, biology), which we carefully designed to simulate the discovery process and prevent LLM recitation. Our results demonstrate that LLM-SR discovers physically accurate equations that significantly outperform state-of-the-art symbolic regression baselines, particularly in out-of-domain test settings. We also show that LLM-SR's incorporation of scientific priors enables more efficient equation space exploration than the baselines. Code and data are available: https://github.com/deep-symbolic-mathematics/LLM-SR
Forward citations
Cited by 30 Pith papers
-
LLM-Guided ODE Discovery and Parameter Inference from Small-Cohort Aggregate Data
AgentODE uses LLMs to discover ODE structures and infer parameter distributions from aggregate data, recovering consistent structures on benchmarks and RDEB clinical data with 231 observations from 46 patients.
-
A Novel Method for Differential-Algebraic Dynamic Model Discovery in Power Systems: An LLM-Based Multi-Agent Collaborative Framework
An LLM multi-agent framework decomposes differential-algebraic model discovery into parallel structure search and algebraic closure, recovering state dynamics and constraints from data and outperforming single-agent L...
-
Agentic Symbolic Search: Characterizing PDEs Beyond Hand-crafted Expressions, Meshes, and Neural Networks
ASYS recovers known analytical PDE forms and generates new interpretable symbolic approximations, such as a geometric interface formula for 2D Allen-Cahn and a nine-parameter contraction law for Keller-Segel blow-up, ...
-
FunctionEvolve: Structure-Guided Symbolic Regression with LLMs
FunctionEvolve recovers 107 exact symbolic forms out of 129 synthetic tasks (82.9% SA@50) by using expression-tree structure for evolutionary search, parent selection, mutation, and coefficient scoring with LLMs.
-
Learning First Integrals via Backward-Generated Data and Guided Reinforcement Learning
FISolver trains a compact LLM on backward-generated (differential equation, first integral) pairs and uses guided reinforcement learning to outperform larger models and Mathematica on first-integral benchmarks at lower cost.
-
SMCEvolve: Principled Scientific Discovery via Sequential Monte Carlo Evolution
SMCEvolve applies Sequential Monte Carlo sampling to LLM program search with adaptive resampling, mutation mixtures, and convergence control, delivering finite-sample complexity bounds and benchmark gains over prior systems.
-
Neuro-Symbolic ODE Discovery with Latent Grammar Flow
Latent Grammar Flow discovers ODEs by placing grammar-based equation representations in a discrete latent space, using a behavioral loss to cluster similar equations, and sampling via a discrete flow model guided by d...
-
Retrieval-Augmented Large Language Models for Evidence-Informed Guidance on Cannabidiol Use in Older Adults
Retrieval-augmented LLMs produce more cautious and guideline-aligned recommendations on cannabidiol for older adults than standalone models, demonstrated via automated evaluation on 64 diverse scenarios.
-
Identifying Topological Invariants of Non-Hermitian Systems via Domain-Adaptive Multimodal Model for Mathematics
There are only finitely many k-vertex-critical graphs in the classes (P4+ℓP1, B4(m), B3(m)+)-free and (P4+ℓP1, 2P2)-free for all k, ℓ, m, with improved χ-bounds for (P4+ℓP1, Kk)-free graphs.
-
LLM-PDESR: Robust PDE Discovery via Subdomain Weighted Residuals and LLM-Guided Symbolic Hypothesis Generation
LLM-PDESR pairs LLM structural hypotheses with C4 quintic splines and subdomain weighted residuals to recover PDEs from noisy data more robustly than prior symbolic methods.
-
GAE: Graph-Augmented Evolution for Scientific Discovery via Reinforcement Optimization
GAE couples a relational GNN program encoder, a Discrete SAC mutation-type controller, and online GRPO LLM fine-tuning to beat static LLM evolution baselines on nonlinear-oscillator symbolic regression, especially out...
-
EditSR: Enhancing Neural Symbolic Regression via Edit-based Rectification
EditSR improves neural symbolic regression accuracy on complex expressions by pretraining an edit-based rectifier on state-transition correction chains that enforce syntactic validity and condition edits only on the c...
-
Programmatic Context Augmentation for LLM-based Symbolic Regression
Programmatic context augmentation lets LLM-based symbolic regression perform code-driven data analysis during search, yielding superior efficiency and accuracy over baselines on LLM-SRBench.
-
From Data to Theory: Autonomous Large Language Model Agents for Materials Science
An LLM agent autonomously selects, codes, and validates materials equations from data, recovering known laws reliably but requiring checks for new or specialized cases.
-
FELA: A Multi-Agent Evolutionary System for Feature Engineering of Industrial Event Log Data
FELA deploys specialized LLM agents in an evolutionary framework to generate, validate, and refine explainable features from heterogeneous industrial event logs, improving downstream model performance.
-
LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizers
LLM-FE is a framework that treats feature engineering as LLM-driven program search with data feedback, reporting consistent gains over baselines on classification and regression tabular tasks.
-
Joint discovery of governing partial differential equations from multi-source datasets by competitive optimization
MCO-PDE trains per-dataset neural surrogates, applies soft-competitive weighting for consensus coefficients, and uses a genetic algorithm to identify shared PDE structures from multi-source data.
-
SciLens: Multi-modal Scientific Claim Verification with Agentic Entailment and Grounding
SciLens introduces an evidence-conditioned atomic entailment framework that grounds claims to modality-specific witnesses in tables and figures, achieving 79.2% macro-F1 on SciClaimEval.
-
Physics-Distilled Neural Network enabled by Large Language Models for Manufacturing Process-Property Predictive Modeling
A framework extracts physics priors via LLMs, distills them through a Graph-Masked Attention teacher into a fast student model, and shows high accuracy plus fault tolerance across five manufacturing processes.
-
EvoGens: A Population-Based Heuristic Search Framework for Scientific Idea Generation
EvoGens uses rank-based mutation, semantic-aware crossover, and lightweight evaluation to evolve populations of LLM-generated scientific ideas, boosting novelty and diversity metrics.
-
GP-GOMEA with GPU-Based Fitness Evaluations: Design and Performance Analysis
GPU fitness evaluation for GP-GOMEA boosts throughput, improves benchmark results especially on large datasets, and allows reliable regression of large Feynman equations within hours.
-
PACEvolve++: Improving Test-time Learning for Evolutionary Search Agents
PACEvolve++ uses a phase-adaptive reinforcement learning advisor to decouple hypothesis selection from execution in LLM-driven evolutionary search, delivering faster convergence than prior frameworks on load balancing...
-
Neuro-Symbolic ODE Discovery with Latent Grammar Flow
Latent Grammar Flow embeds grammar-based ODE representations into a discrete latent space with a behavioural loss and samples candidate equations via discrete flow to fit observed data.
-
In Context Learning and Reasoning for Symbolic Regression with Large Language Models
GPT-4 models rediscover Langmuir isotherms and produce fits on Nikuradse pipe-flow data via iterative chain-of-thought prompting with scientific context and external code feedback.
-
MOOSE-Copilot: A Web-Based Interactive Assistant for Unified Exploratory and Fine-Grained Scientific Hypothesis Discovery
MOOSE-Copilot introduces a unified HAII framework and no-code web interface for LLM-driven scientific hypothesis discovery that integrates exploratory search with fine-grained refinement via user-provided blueprints, ...
-
Identifying Topological Invariants of Non-Hermitian Systems via Domain-Adaptive Multimodal Model for Mathematics
A domain-adaptive multimodal model with a mathematics LLM backbone identifies topological invariants of non-Hermitian systems from eigenvalues and eigenvectors in momentum space.
-
Identifying Topological Invariants of Non-Hermitian Systems via Domain-Adaptive Multimodal Model for Mathematics
A multimodal model with Qwen Math backbone identifies topological invariants of non-Hermitian systems from eigenvalues and eigenvectors in momentum space.
-
Time Series Forecasting Through the Lens of Dynamics
Proposes dynamics-based analysis of time series models showing partial dynamics learning and end-positioning as key to performance, plus a plug-and-play improvement method.
-
Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models
The paper surveys reinforced reasoning techniques for LLMs, covering automated data construction, learning-to-reason methods, and test-time scaling as steps toward Large Reasoning Models.
-
Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning
Position paper claims multimodal LLMs can significantly advance scientific reasoning and proposes a four-stage roadmap plus challenges and suggestions.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.