Language models guide symbolic equation discovery by controlling search
Summary
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.
View Cached Full Text
Cached at: 07/07/26, 04:36 AM
# Language models guide symbolic equation discovery by controlling search Source: [https://arxiv.org/abs/2607.04156](https://arxiv.org/abs/2607.04156) [View PDF](https://arxiv.org/pdf/2607.04156) > Abstract:Scientific equation discovery must combine broad domain priors with strict numerical testing\. Symbolic regression supplies numerical grounding but faces a combinatorial search space, whereas many language\-model systems ask the model to propose or select formulas directly\. We test a different division of labour\. We compare role specifications in which the language model acts as equation author, candidate decider or search controller, alongside end\-to\-end language\-model and purely numerical baselines\. In the controller setting we propose here, implemented as LLM\-PySR, language models specify variables, operators, transformations and search depth; symbolic regression enumerates and fits expressions; and deterministic metrics govern retention\. Across 74 AI\-Feynman equations and seven complex formula\-recovery tasks, search control achieved the strongest observed balance of accuracy, complexity, stability and cost\. On an independent battery dataset, LLM\-PySR identified a compact piecewise\-linear relation between early voltage\-curve displacement and cycle life\. The results suggest that language models should shape hypothesis exploration rather than decide which equations survive\. ## Submission history From: Zikai Xie \[[view email](https://arxiv.org/show-email/7b9d36f5/2607.04156)\] **\[v1\]**Sun, 5 Jul 2026 07:50:08 UTC \(2,196 KB\)
Similar Articles
InsightSR: Refining Symbolic Regression Search Spaces via Parallel Semantic and Structural LLM Guidance
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.
When LLMs Develop Languages: Symbolic Communication for Efficient Multi-Agent Reasoning
This paper introduces Communicative Language Symbolism Routing (CLSR), where multiple LLM agents autonomously invent and evolve compact symbolic languages for reasoning, achieving 3-6x token reduction over chain-of-thought while maintaining accuracy.
Towards Reliable and Robust LLM Planning: Symbolic Feedback-Driven Iterative Self-Refinement Framework
This paper proposes a symbolic feedback-driven iterative self-refinement framework to improve the robustness and reliability of large language models in long-horizon planning tasks. The method uses natural language prompting, a symbolic verifier, and a plan recognizer to enhance feasibility and correctness.
Though Language Models Err While They Strive: Conformal Prediction for Self-Correcting Scientific Generation
Introduces Scientific Feasibility Control (SFC), a conformal prediction framework that provides statistical guarantees for scientific reasoning validity in LLMs, achieving 50.1% on PhyX physics reasoning, outperforming DeepSeek-R1 and GPT-4 while reducing scientific violations by 73%.
RLearner-LLM: Balancing Logical Grounding and Fluency in Large Language Models via Hybrid Direct Preference Optimization
This paper introduces RLearner-LLM, a framework using Hybrid-DPO to balance logical correctness and fluency in LLM-generated explanations, achieving significant NLI entailment improvements across multiple domains and base models while mitigating the verbosity bias of standard preference signals.