Discover Fast Power Allocation Solution for Multi-Target Tracking via AlphaEvolve Evolution

2026-05-03

AI Summary

This work addresses the high computational complexity and limited real-time applicability of conventional power allocation methods in radar multi-target tracking by introducing AlphaEvolve, a novel framework that pioneers the integration of large language model–guided symbolic evolutionary search into engineering optimization. By combining physics-informed feature encoding with deterministic constraint-satisfaction transformations, the approach automatically discovers compact, interpretable, and highly generalizable closed-form power allocation solutions directly from high-dimensional radar states. Experimental results demonstrate that the derived solutions incur an average performance loss of only 1.51% across diverse scenarios and target counts, while achieving a speedup of over three orders of magnitude compared to traditional iterative methods—marking a significant departure from established optimization paradigms.

Abstract

Efficient radar resource allocation is a fundamental yet computationally challenging problem, as optimal solutions typically require iterative optimization with high complexity. Motivated by the need for real-time scheduling, robust generalization, and low data dependency, this paper proposes a novel paradigm that leverages large language model (LLM)-guided evolutionary search (AlphaEvolve) to autonomously discover a closed-form power allocation solution for multi-target tracking. The approach encodes high-dimensional radar states into physically inspired features, then evolves a compact and interpretable scoring function, which is transformed to feasible power allocations via a deterministic constraint-satisfying transformation. Extensive experiments demonstrate that the discovered closed-form solution achieves near-optimal tracking accuracy (average relative performance loss of only $1.51\%$), reliable generalization across diverse scenarios and target counts, and over three orders of magnitude speedup compared to conventional iterative solvers. These results highlight the potential of LLM-guided symbolic search to revolutionize not only radar resource management but also broader classes of engineering optimization problems.

Problem

• power allocation
• multi-target tracking
• radar resource allocation
• real-time scheduling
• computational complexity

Innovation

• AlphaEvolve
• LLM-guided evolution
• closed-form solution
• radar resource allocation
• symbolic search