Leveraging LLM Agents for Automated Optimization Modeling for SASP Problems: A Graph-RAG based Approach
This work addresses the lack of domain-specific knowledge in automated modeling for SASP, an incremental improvement over prompt-based methods.
The paper tackled the problem of automated optimization modeling for sensor array signal processing (SASP) by proposing a multi-agent structure with graph-based retrieval-augmented generation (Graph-RAG), which outperformed existing benchmarks on ten classical signal processing problems.
Automated optimization modeling (AOM) has evoked considerable interest with the rapid evolution of large language models (LLMs). Existing approaches predominantly rely on prompt engineering, utilizing meticulously designed expert response chains or structured guidance. However, prompt-based techniques have failed to perform well in the sensor array signal processing (SASP) area due the lack of specific domain knowledge. To address this issue, we propose an automated modeling approach based on retrieval-augmented generation (RAG) technique, which consists of two principal components: a multi-agent (MA) structure and a graph-based RAG (Graph-RAG) process. The MA structure is tailored for the architectural AOM process, with each agent being designed based on principles of human modeling procedure. The Graph-RAG process serves to match user query with specific SASP modeling knowledge, thereby enhancing the modeling result. Results on ten classical signal processing problems demonstrate that the proposed approach (termed as MAG-RAG) outperforms several AOM benchmarks.