The field of large language models (LLMs) is rapidly advancing, with a focus on integrating these models into various applications to improve reliability, efficiency, and decision-making. Recent developments have explored the combination of LLMs with traditional software engineering techniques, such as scenario-based programming, to streamline the development process and reduce errors. Additionally, LLMs are being leveraged in medical decision-making, effort estimation, and risk negotiation, demonstrating their potential to augment human capabilities and improve outcomes. Noteworthy papers in this area include:
- A paper proposing a methodology for combining LLMs with scenario-based programming to improve software reliability, which demonstrated the approach's effectiveness in a case study.
- A study presenting an AI-assisted negotiation framework that incorporates LLMs to facilitate cross-sectoral engagement and risk analysis.
- A paper introducing a novel sparse medical LLM, SparseDoctor, which achieved state-of-the-art performance on medical benchmarks.
- A framework for agile effort estimation using LLMs, which outperformed traditional methods in evaluation metrics.
- A knowledge-driven adaptive multi-agent collaboration framework, KAMAC, which enables LLM agents to dynamically form expert teams for medical decision-making.