irace-evo: Automatic Algorithm Configuration Extended With LLM-Based Code Evolution

• URL: http://arxiv.org/abs/2511.14794v1
• Date: Sat, 15 Nov 2025 12:42:18 GMT
• Title: irace-evo: Automatic Algorithm Configuration Extended With LLM-Based Code Evolution
• Abstract summary: irace-evo is an extension of irace that integrates code evolution through large language models (LLMs)<n>We evaluate irace-evo on the Construct, Merge, Solve & Adapt (CMSA) metaheuristic for the Variable-Sized Bin Packing Problem (VSBPP)
• Score: 1.1313571663082607
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Automatic algorithm configuration tools such as irace efficiently tune parameter values but leave algorithmic code unchanged. This paper introduces a first version of irace-evo, an extension of irace that integrates code evolution through large language models (LLMs) to jointly explore parameter and code spaces. The proposed framework enables multi-language support (e.g., C++, Python), reduces token consumption via progressive context management, and employs the Always-From-Original principle to ensure robust and controlled code evolution. We evaluate irace-evo on the Construct, Merge, Solve & Adapt (CMSA) metaheuristic for the Variable-Sized Bin Packing Problem (VSBPP). Experimental results show that irace-evo can discover new algorithm variants that outperform the state-of-the-art CMSA implementation while maintaining low computational and monetary costs. Notably, irace-evo generates competitive algorithmic improvements using lightweight models (e.g., Claude Haiku 3.5) with a total usage cost under 2 euros. These results demonstrate that coupling automatic configuration with LLM-driven code evolution provides a powerful, cost-efficient avenue for advancing heuristic design and metaheuristic optimization.

Related papers

• EvoGM: Learning to Merge LLMs via Evolutionary Generative Optimization [27.31325788417927]
  We propose Evolutionary Generative Merging (EvoGM), a framework that employs learnable generative modeling to optimize merging coefficients.<n>EvoGM features a dual-generator architecture with cycle-consistent learning to adaptively sample and refine promising merging candidates.<n>Experiments across diverse benchmarks demonstrate that EvoGM significantly outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-05-28T03:22:54Z)
• Autonomous Evolution of EDA Tools: Multi-Agent Self-Evolved ABC [10.017322958247172]
  This paper introduces the first emph self-evolving logic synthesis framework.<n>Our framework operates on the emphentire integrated ABC, and the output repository preserves its single-binary execution model and command interface.<n>We detail the architecture of this self-improving system, its integration with textscABC, and results demonstrating that the framework can autonomously and progressively improve EDA tool at full million-line scale.
  arXiv  Detail & Related papers  (2026-04-16T14:42:55Z)
• BEAM: Bi-level Memory-adaptive Algorithmic Evolution for LLM-Powered Heuristic Design [49.50107918295052]
  Large Language Model-based Hyper Heuristic (LHH) has recently emerged as an efficient way for automatic design.<n>We propose textbfBEAM (Bi-level Memory-adaptive Algorithmic Evolution) to address this problem.<n>We show that BEAM significantly outperforms existing LHHs, notably reducing the optimality gap by 37.84% on aggregate.
  arXiv  Detail & Related papers  (2026-04-14T15:46:47Z)
• Squeeze Evolve: Unified Multi-Model Orchestration for Verifier-Free Evolution [81.46210789228296]
  We introduce Squeeze Evolve, a unified multi-model orchestration framework for verifier-free evolutionary inference.<n>Our approach is guided by a simple principle: allocate model capability where it has the highest marginal utility.
  arXiv  Detail & Related papers  (2026-04-09T02:14:45Z)
• AdaFuse: Accelerating Dynamic Adapter Inference via Token-Level Pre-Gating and Fused Kernel Optimization [84.25316984309725]
  Integration of dynamic, sparse structures with parameter-efficient adapters (e.g., LoRA) is a powerful technique for enhancing Large Language Models (LLMs)<n>Despite minimal increases in computational load, the computation latency often skyrockets, leading to decoding speeds slowing by over 2.5 times.<n>AdaFuse is a framework built on a tight co-design between the algorithm and the underlying hardware system to enable efficient dynamic adapter execution.
  arXiv  Detail & Related papers  (2026-03-12T12:46:42Z)
• Saber: An Efficient Sampling with Adaptive Acceleration and Backtracking Enhanced Remasking for Diffusion Language Model [98.35868970993232]
  Diffusion language models (DLMs) are emerging as a powerful and promising alternative to the dominant autoregressive paradigm.<n>We introduce efficient Sampling with Adaptive acceleration and Backtracking Enhanced Remasking (i.e., Saber) to achieve better inference speed and output quality in code generation.
  arXiv  Detail & Related papers  (2025-10-20T23:38:12Z)
• Experience-Guided Reflective Co-Evolution of Prompts and Heuristics for Automatic Algorithm Design [124.54166764570972]
  Combinatorial optimization problems are traditionally tackled with handcrafted algorithms.<n>Recent progress has highlighted the potential of automatics design powered by large language models.<n>We propose the Experience-Evolution Reflective Co-Guided of Prompt and Heuristics (EvoPH) for automatic algorithm design.
  arXiv  Detail & Related papers  (2025-09-29T09:24:09Z)
• Dynamic Context-oriented Decomposition for Task-aware Low-rank Adaptation with Less Forgetting and Faster Convergence [131.41894248194995]
  We propose context-oriented decomposition adaptation (CorDA), a novel method that initializes adapters in a task-aware manner.<n>Thanks to the task awareness, our method enables two optional adaptation modes, knowledge-preserved mode (KPM) and instruction-previewed mode (IPM)
  arXiv  Detail & Related papers  (2025-06-16T07:55:14Z)
• CALM: Co-evolution of Algorithms and Language Model for Automatic Heuristic Design [11.639825726501659]
  Large language models (LLMs) can autonomously discover high-performings at a fraction of the traditional cost.<n>We propose a hybrid framework that combines verbal and numerical guidance.<n>Our method outperforms state-of-the-art (SOTA) baselines across various optimization tasks.
  arXiv  Detail & Related papers  (2025-05-18T07:48:47Z)
• MERGE$^3$: Efficient Evolutionary Merging on Consumer-grade GPUs [14.791853860278914]
  We introduce MERGE$3$, an efficient framework that makes evolutionary merging feasible on a single GPU.<n>MerGE$3$ achieves this by Extracting a reduced dataset for evaluation, Estimating model abilities using Item Response Theory (IRT), and Evolving optimal merges via IRT-based performance estimators.<n>Our method enables state-of-the-art multilingual and cross-lingual merging, transferring knowledge across languages with significantly lower computational overhead.
  arXiv  Detail & Related papers  (2025-02-09T14:24:16Z)
• EvoRL: A GPU-accelerated Framework for Evolutionary Reinforcement Learning [24.389896398264202]
  We introduce $texttt$textbfEvoRL$$, the first end-to-end EvoRL framework optimized for GPU acceleration.<n>The framework executes the entire training pipeline on accelerators, including environment simulations and EC processes.
  arXiv  Detail & Related papers  (2025-01-25T08:31:07Z)
• Open Source Evolutionary Computation with Chips-n-Salsa [0.0]
  This paper concerns the evolutionary algorithms that Chips-n-Salsa now provides.<n>Chips-n-Salsa's evolutionary algorithms include implementations with adaptive mutation and crossover rates.
  arXiv  Detail & Related papers  (2024-12-02T22:18:31Z)
• COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement [80.18490952057125]
  Iterative refinement has emerged as an effective paradigm for enhancing the capabilities of large language models (LLMs) on complex tasks. We propose Context-Wise Order-Agnostic Language Modeling (COrAL) to overcome these challenges. Our approach models multiple token dependencies within manageable context windows, enabling the model to perform iterative refinement internally.
  arXiv  Detail & Related papers  (2024-10-12T23:56:19Z)
• Large Language Models As Evolution Strategies [6.873777465945062]
  In this work, we investigate whether large language models (LLMs) are in principle capable of implementing evolutionary optimization algorithms. We introduce a novel prompting strategy, consisting of least-to-most sorting of discretized population members. We find that our setup allows the user to obtain an LLM-based evolution strategy, which we call EvoLLM', that robustly outperforms baseline algorithms.
  arXiv  Detail & Related papers  (2024-02-28T15:02:17Z)
• Extreme Compression of Large Language Models via Additive Quantization [59.3122859349777]
  Our algorithm, called AQLM, generalizes the classic Additive Quantization (AQ) approach for information retrieval. We provide fast GPU and CPU implementations of AQLM for token generation, which enable us to match or outperform optimized FP16 implementations for speed.
  arXiv  Detail & Related papers  (2024-01-11T18:54:44Z)
• AutoBERT-Zero: Evolving BERT Backbone from Scratch [94.89102524181986]
  We propose an Operation-Priority Neural Architecture Search (OP-NAS) algorithm to automatically search for promising hybrid backbone architectures. We optimize both the search algorithm and evaluation of candidate models to boost the efficiency of our proposed OP-NAS. Experiments show that the searched architecture (named AutoBERT-Zero) significantly outperforms BERT and its variants of different model capacities in various downstream tasks.
  arXiv  Detail & Related papers  (2021-07-15T16:46:01Z)

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.