Metraipolis › archive › dc_f701c69dae2e

CIPHEUR: LLM-Guided Structural Search Control for Conflict-Graph Optimization — arXiv:2610.16158

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.16158
License (as archived)
CC0-1.0
Archived
2026-10-15T13:50:40.984Z
SHA-256 of the archived text
28165aecc278315aaa9ed8a042f1644477efff0c5e3f67fb73ea280c35c0a4db
Stable URL of this page
https://metraipolis.com/documento/dc_f701c69dae2e

How to cite

CIPHEUR: LLM-Guided Structural Search Control for Conflict-Graph Optimization — arXiv:2610.16158 — arXiv (en), https://arxiv.org/abs/2610.16158 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f701c69dae2e (Metraipolis archive dc_f701c69dae2e, sha256 28165aecc278315aaa9ed8a042f1644477efff0c5e3f67fb73ea280c35c0a4db)
BibTeX
@misc{dcf701c69dae2e,
  title = {CIPHEUR: LLM-Guided Structural Search Control for Conflict-Graph Optimization — arXiv:2610.16158},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.16158},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f701c69dae2e; sha256 28165aecc278315aaa9ed8a042f1644477efff0c5e3f67fb73ea280c35c0a4db},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.16158. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Neural and Evolutionary Computing (cs.NE) ; Multiagent Systems (cs.MA); Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2610.16158 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T13:48:35.443Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).