PACE: Primitive-Aware Code Evolution for Automated Algorithm Design

• URL: http://arxiv.org/abs/2608.07395v1
• Date: Fri, 07 Aug 2026 16:40:03 GMT
• Title: PACE: Primitive-Aware Code Evolution for Automated Algorithm Design
• Abstract summary: We propose Primitive-Aware Code Evolution (PACE)<n>PACE decouples local logic from complete programs by representing it as persistent units called Executable Algorithmic Primitives (EAPs)<n>To enable code-level transfer, PACE maintains a dynamic set of EAPs.
• Score: 8.27820631099436
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Model (LLM)-based automated algorithm design typically evolves algorithms as complete, indivisible programs. While this whole-program perspective simplifies the search space, it fundamentally couples the useful local logic to its host program. Consequently, valuable code snippets vanish when the overall program is discarded, making it highly difficult to assess the contribution of individual algorithmic components.To address this, we propose Primitive-Aware Code Evolution (PACE), which decouples local logic from complete programs by representing it as persistent units called Executable Algorithmic Primitives (EAPs). To enable code-level transfer, PACE maintains a dynamic set of EAPs. Algorithm evolution is driven by primitive-aware operators that structurally guarantee the retention and cross-program transfer of these components. To evaluate them effectively, PACE leverages Thompson sampling based on parent-relative performance improvements, guiding primitive selection from the set without requiring extra evaluation datasets. Experiments on four tasks demonstrate that PACE effectively discovers competitive algorithms while structurally preserving valuable algorithmic components.

Related papers

• Accelerated Decoding of Centroid Positional Encoding for Instance Segmentation [49.97373153077311]
  We investigate the decoding overhead associated with a centroid encoding for Instance, in which each pixel regresses a positional embedding of its instance centroid.<n>Our solution significantly reduces decoding overhead and improves Endto-End latency, outperforming both CPU-based approaches and naive GPU implementations.
  arXiv  Detail & Related papers  (2026-09-15T09:05:17Z)
• Semantics-Aware Bilevel Co-Evolution: Towards Automated Multicomponent Algorithm Design [34.28112311806716]
  LLM-assisted evolutionary search (LES) has emerged as a promising paradigm for automated algorithm design.<n>This paper proposes STABLE, an LES method purpose-built for automated multicomponent algorithm design.
  arXiv  Detail & Related papers  (2026-06-29T08:28:23Z)
• A2DEPT: Large Language Model-Driven Automated Algorithm Design via Evolutionary Program Trees [8.49373236378493]
  Large Language Model (LLM)-based Automated Heuristic Design (AHD) has shown promise in autonomously generating components with minimal human intervention.<n>To enable open-ended solver beyond rigid templates, we propose Automated Evolutionary Program Trees (A2DEPT)<n>A2DEPT explores the vast program space via a tree-structured evolutionary search with hybrid selection and hierarchical operators, enabling iterative refinement of complete algorithms.
  arXiv  Detail & Related papers  (2026-04-27T05:07:10Z)
• Advancing Automated Algorithm Design via Evolutionary Stagewise Design with LLMs [69.91297564489464]
  EvoStage is a novel evolutionary paradigm that bridges the gap between the rigorous demands of industrial-scale algorithm design and the LLM-based algorithm design methods.<n>EvoStage decomposes the algorithm design process into sequential, manageable stages and integrates real-time intermediate feedback to iteratively refine algorithm design directions.<n>When deployed on a commercial-grade 3D chip placement tool, EvoStage significantly surpasses the original performance metrics, achieving record-breaking efficiency.
  arXiv  Detail & Related papers  (2026-03-09T05:13:44Z)
• DyACE: Dynamic Algorithm Co-evolution for Online Automated Heuristic Design with Large Language Model [12.490525543266807]
  We introduce DyACE (Dynamic Co-evolution) as a Non-stationary Bi-level Control problem.<n>A core element of DyACE is the Look-Ahead Rollout Search, which queries the landscape geometry to extract Search Tray Features.<n>Results demonstrate that DyACE significantly outperforms state-of-the-art static baselines.
  arXiv  Detail & Related papers  (2026-03-07T06:46:53Z)
• Nearly Optimal Active Preference Learning and Its Application to LLM Alignment [68.56793807995417]
  Aligning large language models depends on high-quality datasets of human preference labels.<n>Many existing approaches adopt classical experimental design criteria such as G- or D-optimality.<n>In this work, we identify a simple intuition specific to preference learning that calls into question the suitability of these existing design objectives.
  arXiv  Detail & Related papers  (2026-02-02T03:21:29Z)
• AlgOS: Algorithm Operating System [2.5352713493505785]
  AlgOS is an unopinionated, modular framework for algorithmic implementations.<n>It is designed to reduce the overhead of implementing new algorithms and to standardise the comparison of algorithms.
  arXiv  Detail & Related papers  (2025-04-07T10:36:46Z)
• Benchmarking End-To-End Performance of AI-Based Chip Placement Algorithms [77.71341200638416]
  ChiPBench is a benchmark designed to evaluate the effectiveness of AI-based chip placement algorithms.<n>We have gathered 20 circuits from various domains (e.g., CPU, GPU, and microcontrollers) for evaluation.<n>Results show that even if intermediate metric of a single-point algorithm is dominant, the final PPA results are unsatisfactory.
  arXiv  Detail & Related papers  (2024-07-03T03:29:23Z)
• Process Discovery for Structured Program Synthesis [70.29027202357385]
  A core task in process mining is process discovery which aims to learn an accurate process model from event log data. In this paper, we propose to use (block-) structured programs directly as target process models. We develop a novel bottom-up agglomerative approach to the discovery of such structured program process models.
  arXiv  Detail & Related papers  (2020-08-13T10:33:10Z)
• Iterative Algorithm Induced Deep-Unfolding Neural Networks: Precoding Design for Multiuser MIMO Systems [59.804810122136345]
  We propose a framework for deep-unfolding, where a general form of iterative algorithm induced deep-unfolding neural network (IAIDNN) is developed. An efficient IAIDNN based on the structure of the classic weighted minimum mean-square error (WMMSE) iterative algorithm is developed. We show that the proposed IAIDNN efficiently achieves the performance of the iterative WMMSE algorithm with reduced computational complexity.
  arXiv  Detail & Related papers  (2020-06-15T02:57:57Z)

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.