发表机构
NEC Laboratories Europe; i2CAT Foundation; ICREA（NEC欧洲实验室; i2CAT基金会; 加泰罗尼亚研究与高等教育机构）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
TRACE通过结合进化自动启发式设计与智能体日志知识提取，解决现实资源分配问题，在云和5G vRAN场景中优于现有方法，且开销低于2%。
AI 中文摘要
动态资源分配，即任务流到异构处理节点的实时分配，是现代计算基础设施的支柱。虽然基于学习的调度器在研究领域表现出色，但工业部署仍然依赖操作员可以在严格的延迟预算内阅读、审计和执行的手写规则。基于LLM的自动启发式设计（AHD）有望实现此类规则的自动化编写。然而，现有的AHD框架是为完全指定给LLM的组合问题开发的，并且它们仅从标量适应度分数中学习。在真实系统中，决定良好启发式的行为（如处理器速度或功耗）是先验未知的：分数揭示了哪种启发式表现更好，但未揭示原因。这些缺失的信息记录在每次评估产生的系统日志中。利用这些信息并非易事：日志庞大且嘈杂，相关信号取决于目标，且其内容和格式因硬件和软件栈而异，因此既不能将其原样输入LLM，也不能由固定解析器处理。我们提出了TRACE，它将进化AHD循环与智能体知识提取工作流相结合。一个推理者代理根据目标分析日志模式，并制定关于系统动态的假设；一个编码者代理编写并执行特定于模式的代码来测试这些假设，为进化启发式产生见解或可执行工具。我们在合成云基准和基于工业测试平台测量和运营流量轨迹构建的5G vRAN场景中评估TRACE。TRACE在资源分配问题上始终优于最先进的AHD方法，并在低于2%的开销下产生更可审计的启发式。
英文摘要
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.
