Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

STRIDE: A Self-Reflective Agent Framework for Reliable Automatic Equation Discovery

About

LLM-based equation discovery offers a promising route to recovering symbolic laws from data, but many systems still rely on generation-centered loops that propose candidates, fit parameters, score results, and reuse selected examples. Such loops can misjudge useful skeletons under unreliable fitting, discard near-correct equations that require repair, and accumulate redundant memories that provide limited guidance. We propose STRIDE, a self-reflective agent framework that improves reliability by coordinating data-aware generation, mixed-fitting evaluation, critic--executor repair, and diversity-preserving semantic memory. By turning fitted scores and candidate behavior into shared feedback, STRIDE enables equations to be proposed, assessed, refined, and reused within a closed-loop discovery process. Experiments on representative symbolic-regression benchmarks and LSR-Synth suites show that STRIDE improves accuracy, OOD robustness, and structural recovery across multiple LLM backbones, with ablations and analyses confirming the contribution of its core components.

Jiarui Su, Songjun Tu, Bei Sun, Xiaojun Liang• 2026

Related benchmarks

TaskDatasetResultRank
Symbolic RegressionOscillator 1 (OOD)
NMSE5.97e-12
32
Symbolic RegressionE. coli growth (OOD)
Acc0.19.23
14
Symbolic RegressionOscillator 1
Accuracy (Tol 0.1)100
14
Symbolic RegressionOscillator 2
Accuracy (0.1)100
14
Symbolic RegressionE. coli Growth
Acc@0.114.6
14
Symbolic RegressionStress-Strain
Accuracy @ 0.188.28
14
Symbolic RegressionPO LSR-SYNTH (OOD)
Acc@0.196.6
12
Symbolic RegressionPO LSR-SYNTH
Accuracy@0.199.92
12
Symbolic RegressionCRK LSR-SYNTH OOD
Acc@0.1100
6
Symbolic RegressionCRK LSR-SYNTH
Acc@0.1100
6
Showing 10 of 13 rows

Other info

Follow for update