3 accepted papers
Large Language Model (LLM)-based multi-agent systems often suffer from high communication cost due to redundant interactions, as existing methods optimize communication structures without explicitly measuring whether exchanged messages contribute to the final decision. To better utilize the semantic…
In many prediction problems, we have extra information during training (for example, measurements that are expensive or slow to collect) that will not be available when the model is deployed. A common strategy is to first train a model that uses all training information, then use its predictions on …
Despite recent advances, Large Language Models (LLMs) still generate vulnerable code. Retrieval-Augmented Generation (RAG) has the potential to enhance LLMs for secure code generation by incorporating external security knowledge. However, the conventional RAG design struggles with the noise of ra…