Open Access

ARTICLE

Research on an Emergence Mechanism in Large Language Models for Command and Decision-Making

Yazhi Zheng^1,2, Xiaolong Cui^1,*, Xin Wang^1,2,#, Xuanzhu Sheng^1,2,#

1 Key Laboratory of CTC & IE, Ministry of Education, Engineering University of PAP, Xi’an, China
2 Graduate Brigade, Engineering University of PAP, Xi’an, China

* Corresponding Author: Xiaolong Cui. Email:
# These authors contributed equally to this work

Computers, Materials & Continua 2026, 89(2), 68 https://doi.org/10.32604/cmc.2026.084480

Received 23 April 2026; Accepted 03 August 2026; Issue published 15 September 2026

Abstract

Large Language Models (LLMs) currently lack the robust command and decision-making (C&D) capabilities essential for the command and control domain. To address this critical gap, this paper proposes an emergence mechanism that integrates a domain-specialized Chain of Thought (CoT) framework with a Process Reward Model (PRM)-inspired evaluation and inference-time optimization paradigm. We construct a novel Chain of Command and Decision (CoCD) framework, a C2-specific CoT structure with contextual persistence, knowledge accumulation, and a human-in-the-loop feedback loop, and define a four-dimensional PRM-inspired evaluation framework for process-level assessment of C&D reasoning. Experimental evaluations on 40 C&D scenarios of varying complexity demonstrate that the CoCD framework significantly outperforms direct prompting (Mann–Whitney $U=1314$, $p<0.0001$, Cohen’s $d=1.340$) and Standard-CoT ($p=0.005$, $d=0.606$) in composite performance. PRM-guided Best-of-N selection further improves performance by 5.8% over single-sample CoCD ($p<0.001$, $d=0.855$), providing direct empirical evidence for the utility of process-aware reward signals at inference time. CoCD’s structural advantage is greatest in high-uncertainty, structurally ambiguous scenarios (Level 3 gap: $+0.925$ points), revealing a complexity-type effect that informs the deployment scope of structured CoT frameworks. These findings provide empirical support for domain-specialized structured reasoning and process-level evaluation as foundations for future RL-based C&D capability development in LLMs.

---

Keywords

---