用推理智能体优化元启发式算法，自动发现并验证控制策略。
RACL: Reasoning-Agent Control Layers for Continuous Metaheuristic Learning
- 在现有优化器上加推理代理，通过观察和反思调整搜索行为。
- 21个案例中21次优于或持平基准，平均成本降低0.641%。
- 适合需要自动调参与可解释性优化的工业场景研究者。
本文提出RACL，一种用于元启发式算法的推理代理控制层。RACL在现有优化器之上引入一个推理代理，不替代优化器，也不修改业务约束。代理通过观察运行时内存，分析历史行为，生成有界假设，测试干预措施，评估结果，施加约束，整合有效策略并解释决策。实验以车辆路径问题为测试场景，贡献并非新求解器、特定ALNS配置或路由规则，而是提出一种推理代理发现、验证、整合和解释元启发式控制规则的方法。在当前设置下，RACL在21个可行案例中全部优于或持平操作内存策略，在21个案例中18次优于或持平非推理的停滞触发策略，平均成本差为-0.641%。在Sevilla-9/10运行时样本中，相比固定策略平均成本降低8.337%，相比停滞触发策略降低1.605%，且未带来显著计算开销。概念验证阶段使用Codex作为实时推理代理，观测执行过程，解析日志并提出实时有界干预；后期仅用策略代理进行量化评估的可复现性。
原文摘要 · Abstract (English)
This paper introduces RACL, a Reasoning-Agent Control Layer for metaheuristics. RACL places a reasoning agent above an existing optimizer. The agent does not replace the optimizer and does not modify business constraints. Instead, it controls the optimizer's internal search behavior by observing operational memory, reasoning over past behavior, formulating bounded hypotheses, testing interventions, evaluating outcomes, applying guardrails, consolidating useful policies and explaining its decisions. The experiment uses vehicle routing as a testbed, but the contribution is not a new routing solver, a particular ALNS configuration or a specific set of routing rules. The contribution is the RACL method: a way for a reasoning agent to discover, validate, consolidate and explain algorithmic control rules for a metaheuristic. In the current experimental setting, RACL improves or ties the Operational Memory Policy in 21 of 21 feasible cases and improves or ties a non-reasoning Stagnation-Triggered Policy in 18 of 21 feasible cases, with an average RACL vs STP cost delta of -0.641%. In the Sevilla-9/10 runtime sample, RACL improves average cost by -8.337% versus Fixed and -1.605% versus STP without showing material computational overhead. During the proof-of-concept, Codex was used as an in-the-loop reasoning agent observing executions, interpreting logs and proposing live bounded interventions. The policy proxy was later used only to make quantitative evaluation reproducible.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。