EUVIMEDSkopri EUVIMED
Open access · CC BY 4.0

CAMA: A Confidence-Aware Multi-Agent System with Adaptive Depth Routing for Automated Writing Assessment

Zhiwu Yin, Jieren Zhang, Jing Wang, Jianqiang Liang, Xing Wu, Jianbiao Dai

Electronics · 2026-07-24 · 15 (15) · 3274

DOI: 10.3390/electronics15153274 ↗

At a glance

Journal article in Electronics, published online on 2026-07-24. Written by Zhiwu Yin and 5 co-authors. 37 references. The full text is freely available (open access, CC BY 4.0).

AstrattDettalji biblijografiċiCiteRelated studies

Abstract (original language)

Existing multi-agent systems for automated writing assessment (AWA) suffer from three structural limitations: uniform agent weighting, fixed-depth computation, and lack of empirical auditing. To resolve these challenges, we propose CAMA, a Confidence-Aware Multi-Agent architecture consisting of three synergistic layers: Confidence-Weighted Aggregation (CWA), Adaptive Depth Routing (ADR), and Contribution-Guided Auditing (CGA). We evaluate its human alignment on 31 EFL essays and extend structural robustness checks to 151 samples across multiple datasets and 8 writing prompts. CAMA addresses the accuracy–efficiency–transparency trilemma. The experimental results show the following: (1) CWA provides a formal error containment bound in simulated agent failure, and multi-agent role decomposition achieves substantial improvement over a holistic baseline (QWK = +0.246); (2) ADR optimizes efficiency by routing 48.4% of standard essays to a low-cost Fast path while scaling up for difficult tasks; and (3) CGA provides an interpretable audit mechanism to quantify per-agent contributions. This framework offers a promising, transparent and principled paradigm for intelligent educational evaluation, with the caveat that broader validation across larger, more diverse populations remains a critical avenue for future work.

Cite

APA

Yin, Z., Zhang, J., Wang, J., Liang, J., Wu, X., & Dai, J. (2026). CAMA: A Confidence-Aware Multi-Agent System with Adaptive Depth Routing for Automated Writing Assessment. Electronics, 15(15), 3274. https://doi.org/10.3390/electronics15153274

Vancouver

Yin Z, Zhang J, Wang J, Liang J, Wu X, Dai J. CAMA: A Confidence-Aware Multi-Agent System with Adaptive Depth Routing for Automated Writing Assessment. Electronics. 2026;15(15):3274. doi:10.3390/electronics15153274

BibTeX
@article{Yin2026,
  author = {Yin, Zhiwu and Zhang, Jieren and Wang, Jing and Liang, Jianqiang and Wu, Xing and Dai, Jianbiao},
  title = {CAMA: A Confidence-Aware Multi-Agent System with Adaptive Depth Routing for Automated Writing Assessment},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {15},
  pages = {3274},
  doi = {10.3390/electronics15153274}
}
Start for free →