Tag
L2G-SR 提出用学习到的结构验证器（基于改进的树编辑距离）引导 LLM 进行符号回归搜索，弥补纯数值误差无法识别正确公式结构的不足，并在 LLM-SRBench 上取得最先进的数值拟合与结构准确率。
提出 Dirichlet-Sinkhorn Constant Averaging（DSCA）校准策略，通过在不同协变量分布的数据子集上独立校准候选表达式并取参数均值，为符号回归进化搜索提供额外选择压力，提升函数恢复精度与复杂度权衡。
A framework combining deep generative models (flow and score-based) with symbolic regression to automatically infer analytical forms of unnormalized probability densities from samples, demonstrated on toy distributions and lattice physics systems like the XY model and φ⁴ theory renormalization.
EvoMO-SR is a new LLM-driven symbolic regression framework where a small LLM (Llama-3.1-8B-Instruct) generates equation skeletons whose coefficients are fitted by an external optimizer, using multiobjective survival selection and substructure guidance to control bloating and improve structural recovery.
MOSAIC-SR introduces a Transformer-guided approach for symbolic regression, using initial sketches to improve equation recovery and predictive accuracy on scientific datasets.
The paper investigates using Large Language Models as post-hoc auditors to evaluate symbolic regression models for interpretability and medical plausibility, with clinician assessments showing comparative model rankings are more favorably perceived than term-level interpretations.
DeSyR is a decoupled symbolic recovery framework that combines PINN-guided structure search with physics-informed coefficient refinement to accurately recover symbolic solutions for differential equations.
Introduces geometry-constrained Kolmogorov-Arnold Networks that learn edge geometry via Banach duality, demonstrating superior performance in symbolic regression tasks, especially under measurement noise.
InsightSR is a framework that leverages Large Language Models to refine the search space for symbolic regression, improving accuracy and physical consistency through iterative semantic and structural guidance.
This paper proposes an adaptive protection mechanism for evolutionary feature construction in symbolic regression to preserve important constructed features during evolution, demonstrating improved performance on regression benchmarks and credit classification tasks.
This paper proposes a symbolic machine learning approach to discover interpretable corrections to the Peng-Robinson equation of state for predicting vapor-liquid equilibrium in hydrocarbon-nitrogen binary mixtures, improving accuracy over the original EOS.
This paper introduces a verifier-guided workflow around ODEFormer, a pretrained symbolic transformer, to discover interpretable equations for physical dynamical systems. It demonstrates transfer to vortex shedding and other systems using dynamical and physical-admissibility criteria to select equations from a candidate pool.
This paper introduces DDRSR, a method that broadens expression decomposition and reduction in symbolic regression, avoiding brute-force sub-structure searches and providing theoretical correctness, with empirical advantages over prior approaches.
This paper studies the LSR-Synth benchmark and finds that a fixed vocabulary covers most tasks, while language-model-generated candidates rarely expand the set of solvable instances except when vocabulary coverage is disrupted.
This paper investigates using symbolic regression to discover explicit neural network weight-update rules that outperform standard hand-designed optimizers on small symbolic regression benchmarks, achieving an aggregate MSE reduction of 44.47% in 25 out of 30 benchmark/network combinations.
This paper introduces MEDA, an LLM- and symbolic regression-powered agentic framework for automatically discovering ordinary differential equation (ODE) models of biological dynamical systems. It retrieves background knowledge, proposes candidate ODEs, and evaluates them across canonical model retrieval, extrapolation, and open-ended discovery tasks, demonstrating strong structural recovery and biologically plausible models.
GAE introduces a framework combining graph neural networks, reinforcement learning, and LLM fine-tuning to overcome bottlenecks in evolutionary program search, achieving state-of-the-art performance on symbolic regression for complex nonlinear oscillator systems.
This paper introduces LLM-PySR, a method where language models guide symbolic equation discovery by controlling search parameters while using numerical symbolic regression for fitting. The approach achieves strong balance of accuracy and complexity across benchmark tasks.
GP_ELITE is a pure-Python library for genetic-programming based symbolic regression, enabling discovery of interpretable mathematical formulas from small experimental datasets. Version 0.2.0 introduces Levenberg–Marquardt constant fitting, multi-restart reliability, Pareto front output, and extrapolation mode.
This paper introduces Minimalist Genetic Programming (MGP), a novel algorithm that replaces evolution with a syntactic derivation process inspired by the Minimalist Program from linguistics, using a MERGE operator to construct symbolic expressions. MGP consistently finds exact ground truth models on symbolic regression tasks where standard GP struggles due to bloat.