TY - JOUR
T1 - Dimension-Constrained Organizational Relay for Long-Context LLMs
AU - Wang, Xiaoning
AU - Li, Zhutang
AU - Hu, Changzhen
AU - Wei, Shengjun
N1 - Publisher Copyright:
© 2026 by the authors.
PY - 2026/8
Y1 - 2026/8
N2 - Featured Application: The proposed organizational relay framework is intended for structured, multi-stage text-generation workflows in which local prompts do not repeatedly include the complete output history. It is applicable to hierarchical document generation, cumulative structured creative production, and related tasks that require explicit cross-stage state propagation. It is presented as a workflow-level complement to, rather than a general replacement for, long-context architectures, retrieval systems, or memory-augmented models. Long-context modeling is important for long-horizon generation tasks, yet larger context windows do not necessarily ensure stable organizational continuity. We propose Dimension-Constrained Organizational Relay (DCOR), a workflow-level framework that reformulates long-horizon generation as the ordered propagation of finite organizational states rather than repeated replay of complete token histories. DCOR introduces Order and Dimension to represent sequential organizational evolution and task-oriented constraints, and comprises Organizational Set Extraction, Dimension-Constrained Generation, Organizational Relay, and Organizational Convergence. We evaluate DCOR on cumulative multi-instance advertisement generation and long-form article generation. Across ten advertisement runs, DCOR generated 259–315 structured creative blocks per run, averaging 279.3 ± 17.9, while maintaining the required format and producing no exact duplicate blocks. At the matched 30-block scale, its main advantage was cumulative structured production rather than the lowest character-level repetition. In long-form generation, DCOR achieved the lowest mean character-level 4-gram and 6-gram repetition compared with Direct Generation, Rolling-Summary Generation, Hierarchical-Outline Generation, and Neural RAG-Memory, while maintaining high Distinct-2 and Distinct-3 values. Ablation results further showed that removing Dimension, Organizational Relay, or Order increased repetition and reduced sustained multi-section expansion. These findings support organizational-state propagation as a complementary mechanism for structured long-horizon generation under restricted local-context conditions.
AB - Featured Application: The proposed organizational relay framework is intended for structured, multi-stage text-generation workflows in which local prompts do not repeatedly include the complete output history. It is applicable to hierarchical document generation, cumulative structured creative production, and related tasks that require explicit cross-stage state propagation. It is presented as a workflow-level complement to, rather than a general replacement for, long-context architectures, retrieval systems, or memory-augmented models. Long-context modeling is important for long-horizon generation tasks, yet larger context windows do not necessarily ensure stable organizational continuity. We propose Dimension-Constrained Organizational Relay (DCOR), a workflow-level framework that reformulates long-horizon generation as the ordered propagation of finite organizational states rather than repeated replay of complete token histories. DCOR introduces Order and Dimension to represent sequential organizational evolution and task-oriented constraints, and comprises Organizational Set Extraction, Dimension-Constrained Generation, Organizational Relay, and Organizational Convergence. We evaluate DCOR on cumulative multi-instance advertisement generation and long-form article generation. Across ten advertisement runs, DCOR generated 259–315 structured creative blocks per run, averaging 279.3 ± 17.9, while maintaining the required format and producing no exact duplicate blocks. At the matched 30-block scale, its main advantage was cumulative structured production rather than the lowest character-level repetition. In long-form generation, DCOR achieved the lowest mean character-level 4-gram and 6-gram repetition compared with Direct Generation, Rolling-Summary Generation, Hierarchical-Outline Generation, and Neural RAG-Memory, while maintaining high Distinct-2 and Distinct-3 values. Ablation results further showed that removing Dimension, Organizational Relay, or Order increased repetition and reduced sustained multi-section expansion. These findings support organizational-state propagation as a complementary mechanism for structured long-horizon generation under restricted local-context conditions.
KW - context decoupling
KW - dimension constraint
KW - large language models
KW - long-horizon generation
KW - structured state propagation
UR - https://www.scopus.com/pages/publications/105048329639
U2 - 10.3390/app16167903
DO - 10.3390/app16167903
M3 - Article
AN - SCOPUS:105048329639
SN - 2076-3417
VL - 16
JO - Applied Sciences (Switzerland)
JF - Applied Sciences (Switzerland)
IS - 16
M1 - 7903
ER -