arXiv cs.AI· Chenxing Wei, Sichen Liu, Lizhao Liu, Ningyuan Sun, Chen Bingzhou, Ying He, Bo Jiang, Fei Yu, Yao Shu·· 4 小时前AI 评分30
OptiCom：LLM 驱动优化中状态条件组合的统一框架
OptiCom : A Unified Framework for State-Conditioned Composition in LLM-Driven Optimization
AI 导读
论文提出 OptiCom 框架，将 LLM 驱动的优化器统一到共享配置空间 C=(A,Q,O,E,M,S)，由快速的 Optimization Controller 通过结构化 Action Packages 动态组合机制，较慢的 Strategy Adapter 基于轨迹反馈调整长期策略。
正文 · 原文
Abstract:Large language models (LLMs) are increasingly deployed to solve complex scientific and practical problems via iterative optimization. However, dynamically coordinating diverse search mechanisms as candidate quality, failure modes, and resource budgets evolve remains a critical open challenge. Targeted empirical diagnostics reveal that mechanism effectiveness is highly state-dependent. Motivated by this, we analyze how individual decisions drive final outcomes, decomposing the expected terminal improvement under a shared budget into cumulative decision opportunities minus cumulative selection losses. Guided by this opportunity-loss theoretical foundation, we propose OptiCom, a unified framework that represents LLM-driven optimizers within a shared configuration space: C=(A,Q,O,E,M,S), corresponding to artifact, query, operator, evaluation, memory, and strategy. Operating within this space, a fast LLM-based Optimization Controller dynamically composes immediate mechanisms through structured Action Packages, while a slower Strategy Adapter refines long-term selection preferences, operator weights, and templates based on accumulated trajectory feedback. Comprehensive evaluations across 32 benchmark groups demonstrate the superiority of framework: OptiCom achieves an average Max-score rank of 1.72 among 14 evaluated configurations, securing the top score in 23 groups. Ultimately, these results highlight the broad applicability and high extensibility of OptiCom as a general-purpose paradigm for robust LLM test-time scaling.
| Comments: | 43 pages, 11 figures |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2609.37221 [cs.AI] |
| (or arXiv:2609.37221v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2609.37221 arXiv-issued DOI via DataCite |
Submission history
From: Chenxing Wei [view email]
[v1]
Tue, 29 Sep 2026 10:38:06 UTC (904 KB)
[v2]
Mon, 26 Oct 2026 05:15:17 UTC (904 KB)
来源：arXiv cs.AI · arxiv.org