A Closer Look at Agentic BBO: Benchmarking LLM Agents for Black-Box Optimization

  • 类型：arxiv
  • 标识：2610.12183
  • 链接：https://arxiv.org/abs/2610.12183
  • 主分类：agent
  • 形态：benchmark
  • TLDR：Black-box optimization (BBO) arises in many scientific and engineering problems where objective evaluations are expensive and limited. Recent large language model (LLM) agents offer a new way to approach BBO by combining task semantics, computation, optimization tools, and feedback-driven decision making, showing great potential due to the integration with mathematically rigorous tools. However, existing agentic BBO studies use different task domains and system configurations, making their results difficult to compare and the effects of individual design choices hard to isolate. We therefore i
  • 副分类：evaluation
  • 待LLM分类：否
  • 标题中文：深入探究 Agentic BBO：面向黑盒优化的 LLM 智能体基准测试
  • TLDR中文：黑盒优化（BBO）出现在许多目标和工程问题中，其目标函数评估代价高昂且次数有限。近期的大语言模型（LLM）智能体通过结合任务语义、计算、优化工具以及反馈驱动的决策，提供了一种新的 BBO 解决方式，因与数学严谨工具的集成而展现出巨大潜力。然而，现有的 Agentic BBO 研究使用不同的任务领域和系统配置，导致结果难以比较，且单个设计选择的影响难以孤立分析。因此，我们引入
  • 来源文件：
  • /inbox/tom/_candidates/2026-10-09-agent-rag-longcontext-candidates.json