Comparing Single-Agent and Multi-Agent Strategies in LLM-Based Title-Abstract Screening
Electronics · 15.04.2026 · 15 (8) · 1661
DOI: 10.3390/electronics15081661 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 15.04.2026. Verfasst von Irina Radeva und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Education and Science.
Abstract (Originalsprache)
Title-abstract screening remains labour-intensive, especially in interdisciplinary domains where shared terminology increases misclassification risk. This study compared five LLM coordination strategies—single-agent baseline, majority voting, recall-focused ensemble, confidence-weighted aggregation, and two-stage filtering—using four 4-bit quantised open-source models (Mistral 7B, LLaMA 3.1 8B, Granite 3.3 8B, Qwen 2.5 7B) in zero-shot and few-shot configurations. The evaluation was conducted on a Gold Standard of 200 papers from a corpus of 2036 records on blockchain-based e-voting. The best-performing configuration—a single-agent strategy with Qwen 2.5 7B in few-shot mode—achieved recall of 100%, precision of 70.4%, F1 of 82.6%, and a 43.4% reduction in manual screening effort, outperforming all multi-agent alternatives. Confidence-weighted aggregation produced results identical to majority voting, indicating that self-reported confidence from 7–8B parameter models did not add discriminative value. All screening decisions were logged on a private blockchain with timestamped anchoring for reproducibility. These results suggest that, for domain-specific screening tasks, careful model selection outweighs multi-agent coordination overhead, and that few-shot prompting with a well-matched model can achieve human-level recall with substantially reduced manual effort.
Förderung
- Ministry of Education and Science
Zitieren
APA
Radeva, I., Noncheva, T., Doukovska, L., & Popchev, I. (2026). Comparing Single-Agent and Multi-Agent Strategies in LLM-Based Title-Abstract Screening. Electronics, 15(8), 1661. https://doi.org/10.3390/electronics15081661
Vancouver
Radeva I, Noncheva T, Doukovska L, Popchev I. Comparing Single-Agent and Multi-Agent Strategies in LLM-Based Title-Abstract Screening. Electronics. 2026;15(8):1661. doi:10.3390/electronics15081661
BibTeX
@article{Radeva2026,
author = {Radeva, Irina and Noncheva, Teodora and Doukovska, Lyubka and Popchev, Ivan},
title = {Comparing Single-Agent and Multi-Agent Strategies in LLM-Based Title-Abstract Screening},
journal = {Electronics},
year = {2026},
volume = {15},
number = {8},
pages = {1661},
doi = {10.3390/electronics15081661}
}
EUVIMED