arXiv：cs.LG（机器学习，全量分类）· Jose A. Ayala-Romero, Andres Garcia-Saavedra, Xavier Costa-Perez·· 17 小时前AI 评分41
TRACE：用智能体启发式设计解决真实世界资源分配问题
TRACE: Tackling Real-World Resource Assignment Problems via Agentic Heuristic Design
AI 导读
TRACE 将进化式自动启发式设计（AHD）循环与智能体知识提取工作流结合，通过 Reasoner 分析日志模式提出假设、Coder 编写并执行代码验证，解决现有 AHD 仅依赖标量适应度、无法获知系统动态的问题。在合成云基准和基于工业测试床测量与运营流量轨迹构建的 5G vRAN 场景中，TRACE 持续优于 SOTA AHD 方法，开销低于 2%，并产出更可审计的启发式规则。
正文
Abstract:Dynamic resource assignment, the real-time allocation of task streams to heterogeneous processing nodes, is the backbone of modern computing infrastructure. While learning-based schedulers excel in research, industrial deployments still rely on hand-written rules that operators can read, audit, and execute within tight latency budgets. LLM-based Automatic Heuristic Design (AHD) promises to automate writing such rules. However, existing AHD frameworks were developed for combinatorial problems fully specified to the LLM, and they learn only from a scalar fitness score. In real systems, the behaviour that determines a good heuristic, such as processor speeds or power consumption, is unknown a priori: the score reveals which heuristic performs better, but not why. This missing information is recorded in the system logs that every evaluation produces. Exploiting it is non-trivial: logs are massive and noisy, the relevant signals depend on the objective, and their content and format vary across hardware and software stacks, so they can neither be fed to an LLM as is nor processed by a fixed parser. We propose TRACE, which couples an evolutionary AHD loop with an agentic knowledge-extraction workflow. A Reasoner agent analyzes the log schema in light of the objective and formulates hypotheses about the system dynamics; a Coder agent writes and executes schema-specific code to test them, producing insights or executable tools for the evolved heuristics. We evaluate TRACE on a synthetic cloud benchmark and a 5G vRAN scenario built from industrial testbed measurements and operational traffic traces. TRACE consistently outperforms state-of-the-art AHD methods in resource assignment problems and yields more auditable heuristics at under 2% overhead.
| Subjects: | Neural and Evolutionary Computing (cs.NE); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.01887 [cs.NE] |
| (or arXiv:2610.01887v1 [cs.NE] for this version) | |
| https://doi.org/10.48550/arXiv.2610.01887 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jose A. Ayala-Romero [view email]
[v1]
Thu, 1 Oct 2026 15:38:04 UTC (532 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org