Search papers, labs, and topics across Lattice.
The paper introduces Dual-Cluster Memory Agent (DCM-Agent), a training-free method that leverages historical solutions to address structural ambiguity in optimization problems for LLMs. DCM-Agent constructs dual-cluster memories based on modeling and coding paradigms, distilling them into structured knowledge (Approach, Checklist, Pitfall) for guiding solution generation. Experiments across seven optimization benchmarks show DCM-Agent improves performance by 11%-21%, with larger models' memories effectively guiding smaller models.
Smaller LLMs can achieve superior optimization performance by inheriting structured knowledge distilled from the memories of larger models, without any training.
Large Language Models (LLMs) often struggle with structural ambiguity in optimization problems, where a single problem admits multiple related but conflicting modeling paradigms, hindering effective solution generation. To address this, we propose Dual-Cluster Memory Agent (DCM-Agent) to enhance performance by leveraging historical solutions in a training-free manner. Central to this is Dual-Cluster Memory Construction. This agent assigns historical solutions to modeling and coding clusters, then distills each cluster's content into three structured types: Approach, Checklist, and Pitfall. This process derives generalizable guidance knowledge. Furthermore, this agent introduces Memory-augmented Inference to dynamically navigate solution paths, detect and repair errors, and adaptively switch reasoning paths with structured knowledge. The experiments across seven optimization benchmarks demonstrate that DCM-Agent achieves an average performance improvement of 11%- 21%. Notably, our analysis reveals a ``knowledge inheritance''phenomenon: memory constructed by larger models can guide smaller models toward superior performance, highlighting the framework's scalability and efficiency.
