Learning First Integrals via Backward-Generated Data and Guided Reinforcement Learning

• URL: http://arxiv.org/abs/2605.21160v1
• Date: Wed, 20 May 2026 13:27:39 GMT
• Title: Learning First Integrals via Backward-Generated Data and Guided Reinforcement Learning
• Abstract summary: Existing symbolic computation tools and Large Language Models (LLMs) remain limited on the discovery of first integrals.<n>This paper presents FIr, an LLM-based solver developed to address this challenge.<n>We introduce a "Backward Generation" algorithm that builds large-scale datasets of intuition (differential equation, first integral) pairs.<n>Experiments show that FIr, while requiring substantially lower computational cost, significantly outperforms larger mathematical LLMs and commercial solvers.
• Score: 7.891851139983605
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The discovery of first integrals is of fundamental scientific importance for understanding conservation laws in dynamical systems. However, existing symbolic computation tools and Large Language Models (LLMs) remain limited on this task because high-quality training data are scarce and successful solutions often depend on mathematical intuition. This paper presents FISolver, an LLM-based solver developed to address this challenge. First, we introduce a "Backward Generation" algorithm that systematically builds large-scale datasets of (differential equation, first integral) pairs by deriving differential equations from sampled integrals, thereby alleviating the data scarcity bottleneck. Second, we apply supervised fine-tuning to a compact mathematical model and further improve its performance through reinforcement learning with a Levenshtein Distance-based shaped reward. In addition, we design data synthesis and blending strategies that support effective adaptation to difficult problem families from sparse examples. Experiments show that FISolver, while requiring substantially lower computational cost, significantly outperforms larger mathematical LLMs and commercial solvers such as Mathematica on challenging benchmarks, indicating a new data-driven route for automated discovery of first integrals.

Related papers

• Bidirectional Curriculum Generation: A Multi-Agent Framework for Data-Efficient Mathematical Reasoning [16.95900718416944]
  We introduce a novel Bidirectional Curriculum Generation framework to maximize the instructional value of every training sample.<n>Unlike rigid trajectories, our multi-agent ecosystem mimics adaptive pedagogy to establish a closed feedback loop.<n>This mechanism ensures that the model consumes only the most effective data at any given stage.
  arXiv  Detail & Related papers  (2026-03-05T12:49:21Z)
• Mathematical artificial data for operator learning [1.4579344926652846]
  We present the Mathematical Artificial Data (MAD) framework, a new paradigm that integrates physical laws with data-driven learning to facilitate large-scale operator discovery.<n>We show MAD's generalizability and superior efficiency/accuracy across various differential equations scenarios.
  arXiv  Detail & Related papers  (2025-07-09T11:23:05Z)
• Bridging the Domain Gap in Equation Distillation with Reinforcement Feedback [37.06543502352577]
  We propose a reinforcement learning-based finetuning framework to enhance the domain adaptability of foundation models for Data2Eqn tasks.<n>Our method allows the model to adapt to specific and complex data distributions and generate mathematically meaningful equations.
  arXiv  Detail & Related papers  (2025-05-21T14:25:41Z)
• RV-Syn: Rational and Verifiable Mathematical Reasoning Data Synthesis based on Structured Function Library [58.404895570822184]
  RV-Syn is a novel mathematical Synthesis approach.<n>It generates graphs as solutions by combining Python-formatted functions from this library.<n>Based on the constructed graph, we achieve solution-guided logic-aware problem generation.
  arXiv  Detail & Related papers  (2025-04-29T04:42:02Z)
• Advancing Mathematical Reasoning in Language Models: The Impact of Problem-Solving Data, Data Synthesis Methods, and Training Stages [13.377908992869814]
  Problem-solving data significantly enhances the model's mathematical capabilities compared to general mathematical corpora.<n>We identify effective data synthesis methods, demonstrating that the tutorship amplification synthesis method achieves the best performance.
  arXiv  Detail & Related papers  (2025-01-23T12:14:57Z)
• Unleashing LLM Reasoning Capability via Scalable Question Synthesis from Scratch [54.12139707822201]
  We propose ScaleQuest, a novel, scalable, and cost-effective data synthesis method.<n>By generating diverse questions from scratch, we produce a dataset of 1 million problem-solution pairs.<n>Our experiments demonstrate that models trained on our data outperform existing open-source datasets.
  arXiv  Detail & Related papers  (2024-10-24T12:42:04Z)
• AlphaIntegrator: Transformer Action Search for Symbolic Integration Proofs [3.618534280726541]
  We present the first correct-by-construction learning-based system for step-by-step mathematical integration. The key idea is to learn a policy, represented by a GPT transformer model, which guides the search for the right mathematical integration rule. We introduce a symbolic engine with axiomatically correct actions on mathematical expressions, as well as the first dataset for step-by-step integration.
  arXiv  Detail & Related papers  (2024-10-03T16:50:30Z)
• Discovering physical laws with parallel symbolic enumeration [67.36739393470869]
  We introduce parallel symbolic enumeration (PSE) to efficiently distill generic mathematical expressions from limited data.<n>Experiments show that PSE achieves higher accuracy and faster computation compared to the state-of-the-art baseline algorithms.<n> PSE represents an advance in accurate and efficient data-driven discovery of symbolic, interpretable models.
  arXiv  Detail & Related papers  (2024-07-05T10:41:15Z)
• Deep Generative Symbolic Regression [83.04219479605801]
  Symbolic regression aims to discover concise closed-form mathematical equations from data. Existing methods, ranging from search to reinforcement learning, fail to scale with the number of input variables. We propose an instantiation of our framework, Deep Generative Symbolic Regression.
  arXiv  Detail & Related papers  (2023-12-30T17:05:31Z)
• End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes [52.818579746354665]
  This paper proposes the first end-to-end differentiable meta-BO framework that generalises neural processes to learn acquisition functions via transformer architectures. We enable this end-to-end framework with reinforcement learning (RL) to tackle the lack of labelled acquisition data.
  arXiv  Detail & Related papers  (2023-05-25T10:58:46Z)
• Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL [106.82295532402335]
  Existing reinforcement learning algorithms suffer from computational intractability, strong statistical assumptions, and suboptimal sample complexity. We provide the first computationally efficient algorithm that attains rate-optimal sample complexity with respect to the desired accuracy level. Our algorithm, MusIK, combines systematic exploration with representation learning based on multi-step inverse kinematics.
  arXiv  Detail & Related papers  (2023-04-12T14:51:47Z)
• AttNS: Attention-Inspired Numerical Solving For Limited Data Scenarios [51.94807626839365]
  We propose the attention-inspired numerical solver (AttNS) to solve differential equations due to limited data.<n>AttNS is inspired by the effectiveness of attention modules in Residual Neural Networks (ResNet) in enhancing model generalization and robustness.
  arXiv  Detail & Related papers  (2023-02-05T01:39:21Z)
• Model-Based Deep Learning [155.063817656602]
  Signal processing, communications, and control have traditionally relied on classical statistical modeling techniques. Deep neural networks (DNNs) use generic architectures which learn to operate from data, and demonstrate excellent performance. We are interested in hybrid techniques that combine principled mathematical models with data-driven systems to benefit from the advantages of both approaches.
  arXiv  Detail & Related papers  (2020-12-15T16:29:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.