Evolution of Benchmark: Black-Box Optimization Benchmark Design through Large Language Model

• URL: http://arxiv.org/abs/2601.21877v2
• Date: Sat, 31 Jan 2026 04:35:14 GMT
• Title: Evolution of Benchmark: Black-Box Optimization Benchmark Design through Large Language Model
• Abstract summary: Early benchmarks are predominantly human-crafted, introducing expert bias and constraining diversity.<n>We propose Evolution of Benchmark (EoB), an automated BBO benchmark designer empowered by the large language model (LLLL)<n>Under this paradigm, EoB iteratively promptsLLLL to evolve a population of benchmark programs and employs a reflection-based scheme to co-evolve the landscape and its corresponding program.
• Score: 14.96004052012247
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Benchmark Design in Black-Box Optimization (BBO) is a fundamental yet open-ended topic. Early BBO benchmarks are predominantly human-crafted, introducing expert bias and constraining diversity. Automating this design process can relieve the human-in-the-loop burden while enhancing diversity and objectivity. We propose Evolution of Benchmark (EoB), an automated BBO benchmark designer empowered by the large language model (LLM) and its program evolution capability. Specifically, we formulate benchmark design as a bi-objective optimization problem towards maximizing (i) landscape diversity and (ii) algorithm-differentiation ability across a portfolio of BBO solvers. Under this paradigm, EoB iteratively prompts LLM to evolve a population of benchmark programs and employs a reflection-based scheme to co-evolve the landscape and its corresponding program. Comprehensive experiments validate our EoB is a competitive candidate in multi-dimensional usages: 1) Benchmarking BBO algorithms; 2) Training and testing learning-assisted BBO algorithms; 3) Extending proxy for expensive real-world problems.

Related papers

• A Decade of Bayesian Optimization for Controller Tuning and Robot Learning: Tutorial, Review, and Future Prospects [49.6839288052673]
  In the past decade, Bayesian optimization has emerged as a powerful framework for automatic controller tuning and robot learning.<n>This article offers a comprehensive overview of the state-of-the-art in BO, designed to support both researchers and practitioners in understanding recent advancements.
  arXiv  Detail & Related papers  (2026-09-08T19:59:54Z)
• 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)
• Topic Modelling Black Box Optimization [0.0]
  Choosing the number of topics $T$ in Latent Dirichlet Allocation (LDA) is a key design decision that strongly affects both the statistical fit and interpretability of topic models.<n>We formulate the selection of $T$ as a discrete black-box optimization problem, where each function evaluation corresponds to training an LDA model and measuring its validation perplexity.
  arXiv  Detail & Related papers  (2025-12-18T12:00:24Z)
• BBOPlace-Bench: Benchmarking Black-Box Optimization for Chip Placement [37.42100258084977]
  Black-box optimization (BBO) for chip placement has a history of several decades.<n>Recent progress has shown the effectiveness and efficiency of BBO for chip placement.<n>Despite these advancements, the field lacks a unified, BBO-specific benchmark.<n>BBOPlace-Bench is the first benchmark designed specifically for evaluating and developing BBO algorithms for chip placement tasks.
  arXiv  Detail & Related papers  (2025-10-27T16:10:32Z)
• BOFormer: Learning to Solve Multi-Objective Bayesian Optimization via Non-Markovian RL [15.127370150885348]
  We present a generalized deep Q-learning framework and propose textitBOFormer, which substantiates this framework for MOBO via sequence modeling.<n>Through extensive evaluation, we demonstrate that BOFormer constantly outperforms the benchmark rule-based and learning-based algorithms.
  arXiv  Detail & Related papers  (2025-05-28T05:00:50Z)
• Reinforced In-Context Black-Box Optimization [64.25546325063272]
  RIBBO is a method to reinforce-learn a BBO algorithm from offline data in an end-to-end fashion. RIBBO employs expressive sequence models to learn the optimization histories produced by multiple behavior algorithms and tasks. Central to our method is to augment the optimization histories with textitregret-to-go tokens, which are designed to represent the performance of an algorithm based on cumulative regret over the future part of the histories.
  arXiv  Detail & Related papers  (2024-02-27T11:32:14Z)
• Enhanced Bayesian Optimization via Preferential Modeling of Abstract Properties [49.351577714596544]
  We propose a human-AI collaborative Bayesian framework to incorporate expert preferences about unmeasured abstract properties into surrogate modeling. We provide an efficient strategy that can also handle any incorrect/misleading expert bias in preferential judgments.
  arXiv  Detail & Related papers  (2024-02-27T09:23:13Z)
• Large Language Models to Enhance Bayesian Optimization [57.474613739645605]
  We present LLAMBO, a novel approach that integrates the capabilities of Large Language Models (LLM) within Bayesian optimization. At a high level, we frame the BO problem in natural language, enabling LLMs to iteratively propose and evaluate promising solutions conditioned on historical evaluations. Our findings illustrate that LLAMBO is effective at zero-shot warmstarting, and enhances surrogate modeling and candidate sampling, especially in the early stages of search when observations are sparse.
  arXiv  Detail & Related papers  (2024-02-06T11:44:06Z)
• Optimizing with Low Budgets: a Comparison on the Black-box Optimization Benchmarking Suite and OpenAI Gym [2.511157007295545]
  Black-box optimization (BO) algorithms are popular in machine learning (ML) We compare BBO tools for ML with more classical COCOs. Some algorithms from the BBO community perform surprisingly well on ML tasks.
  arXiv  Detail & Related papers  (2023-09-29T18:33:10Z)
• Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization [82.02008764719896]
  Black-box model-based optimization problems are ubiquitous in a wide range of domains, such as the design of proteins, DNA sequences, aircraft, and robots. We present Design-Bench, a benchmark for offline MBO with a unified evaluation protocol and reference implementations of recent methods. Our benchmark includes a suite of diverse and realistic tasks derived from real-world optimization problems in biology, materials science, and robotics.
  arXiv  Detail & Related papers  (2022-02-17T05:33:27Z)
• ES-Based Jacobian Enables Faster Bilevel Optimization [53.675623215542515]
  Bilevel optimization (BO) has arisen as a powerful tool for solving many modern machine learning problems. Existing gradient-based methods require second-order derivative approximations via Jacobian- or/and Hessian-vector computations. We propose a novel BO algorithm, which adopts Evolution Strategies (ES) based method to approximate the response Jacobian matrix in the hypergradient of BO.
  arXiv  Detail & Related papers  (2021-10-13T19:36:50Z)
• 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)
• Black-Box Optimization Revisited: Improving Algorithm Selection Wizards through Massive Benchmarking [8.874754363200614]
  Existing studies in black-box optimization for machine learning suffer from low generalizability. We propose a benchmark suite, OptimSuite, which covers a broad range of black-box optimization problems. ABBO achieves competitive performance on all benchmark suites.
  arXiv  Detail & Related papers  (2020-10-08T14:17:30Z)

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.