From Phenomenological Fitting to Endogenous Deduction: A Paradigm Leap via Meta-Principle Physics Architecture
This work addresses the problem of building AI with physical common sense and causal reasoning for researchers and practitioners, representing a new paradigm rather than an incremental improvement.
The paper tackles the problem of neural networks lacking understanding of fundamental physical principles by proposing a paradigm shift to combine phenomenological fitting with endogenous deduction through the Meta-Principle Physics Architecture (MPPA). The result includes significant improvements, such as achieving a physical reasoning score of 0.436 from near zero, a 2.18x gain in mathematical tasks, a 52% gain in logical tasks, and a 3.69% lower validation perplexity with only 11.8% more parameters.
The essence of current neural network architectures is phenomenological fitting: they learn input-output statistical correlations via massive parameters and data, yet lack intrinsic understanding of the fundamental principles governing physical reality. This paper proposes a paradigm leap from pure phenomenological fitting to the fusion of phenomenological fitting and endogenous deduction. By embedding physical meta-principles into neural network architecture, we construct the Meta-Principle Physics Architecture (MPPA). Specifically, MPPA embeds three core meta-principles - Connectivity, Conservation, Periodicity - into its architecture, implemented via three core components: the Gravitator realizes Connectivity via standard causal attention; the Energy Encoder implements Conservation via log-domain energy tracking and delayed compensation; the Periodicity Encoder fulfills Periodicity via FFT-based spectral analysis and delayed modulation. These components collaborate via a learnable independent gating fusion mechanism, forming a complete physical cognition framework of 'local relational connectivity - global conservation constraint - evolutionary periodic law'. Experiments show MPPA achieves significant improvements: physical reasoning (from near zero to 0.436, 0.436 vs 0.000), 2.18x mathematical task improvement (0.330 vs 0.151), 52% logical task gain (0.456 vs 0.300), and 3.69% lower validation perplexity (259.45 vs 269.40), with only 11.8% more parameters (242.40M vs 216.91M). Notably, MPPA shows strong generalization on out-of-distribution physical scenarios, proving the robustness and interpretability of this principle-embedded design. This work establishes a new theoretical foundation and technical path for next-generation AI with physical common sense, causal reasoning, and mathematical rigor.