arXiv cs.MA· Yuqing Cheng, Yan Jia, Yanjie Song, Xiaolu Liu, Lining Xing, Feng Yao·· 3 天前AI 评分22
CIPHEUR：LLM 引导的结构化搜索控制用于冲突图优化
CIPHEUR: LLM-Guided Structural Search Control for Conflict-Graph Optimization
AI 导读
CIPHEUR 是一个 LLM 引导的框架，通过结构化干预单元（SIU）将冲突证据与协调干预及恢复连接，支持离线合成可执行策略与在线上下文决策。在八个卫星-地面调度冲突视图、每视图五次运行、900 秒评估上限下，CIPHEUR-online 在 11 种配置中取得最高平均目标值，平均调度接触时长较贪心基线 GWMIN 提升 14.84%，并在全部 40 次配对运行中优于 CHILS。
正文 · 原文
Abstract:Conflict-graph search can stagnate despite effective operators when interventions fail to address the conflicts blocking progress. A disruptive intervention may also require further search before its value emerges. We propose CIPHEUR, a large language model (LLM)-guided framework that connects conflict evidence to coordinated intervention and recovery through Structured Intervention Units (SIUs). The shared control interface supports offline synthesis of executable policies and online contextual decisions. Asynchronous online control sustains native search during inference, while all policies preserve the original objective and feasibility constraints. Across eight satellite-ground scheduling conflict views with five runs per view and a 900-second evaluation cap, CIPHEUR-online achieves the highest mean objective among 11 configurations and increases mean scheduled contact duration by 14.84% over the greedy baseline GWMIN. It exceeds the strongest external per-view mean in seven of eight views and outperforms CHILS in all 40 paired runs. Within the same runs, its normalized objective improvement from 360 to 900 seconds is 1.50 to 1.86 times that of the two programmatic controllers. A separately frozen, one-shot LLM-generated controller also improves the mean objective over CHILS without runtime model calls. Together, these results demonstrate how structural search control translates LLM design knowledge and contextual reasoning into improved solution quality and sustained search progress.
| Subjects: | Neural and Evolutionary Computing (cs.NE); Multiagent Systems (cs.MA); Systems and Control (eess.SY) |
| Cite as: | arXiv:2610.16158 [cs.NE] |
| (or arXiv:2610.16158v1 [cs.NE] for this version) | |
| https://doi.org/10.48550/arXiv.2610.16158 arXiv-issued DOI via DataCite |
Submission history
From: Yan Jia [view email]
[v1]
Mon, 12 Oct 2026 04:33:11 UTC (1,844 KB)
来源：arXiv cs.MA · arxiv.org