9 papers
Personalized Recommendation Tool Learning via Autonomous Language Agents
Mingdai Yang, Zhiwei Liu, Weizhi Zhang +3
Although large language models (LLMs) have recently gained traction in recommender systems due to their strong reasoning capabilities and extensive world knowledge, previous LLM-ba…
Learning to Retrieve: Dual-Level Long-Term Memory for Text-to-SQL Agents
Yibo Wang, Nikki Lijing Kuang, Philip S. Yu +2
Interactive text-to-SQL agents solve database tasks through multi-turn interactions involving schema exploration, query execution, feedback interpretation, and decision revision. L…
Why LLMs Hallucinate on Structured Knowledge: A Mechanistic Analysis of Reasoning over Linearized Representations
Shanghao Li, Jinda Han, Yibo Wang +5
In many reasoning tasks, large language models (LLMs) rely on structured external knowledge, such as graphs and tables, which is typically linearized into sequential token represen…
TodyComm: Task-Oriented Dynamic Communication for Multi-Round LLM-based Multi-Agent System
Wenzhe Fan, Tommaso Tognoli, Henry Peng Zou +3
Multi-round LLM-based multi-agent systems rely on effective communication structures to support collaboration across rounds. However, most existing methods employ a fixed communica…
MultiFileTest: A Multi-File-Level LLM Unit Test Generation Benchmark and Impact of Error Fixing Mechanisms
Yibo Wang, Congying Xia, Wenting Zhao +5
Unit test generation has become a promising and important Large Language Model (LLM) use case. However, existing evaluation benchmarks for LLM unit test generation focus on functio…
Detecting Hallucinations in Graph Retrieval-Augmented Generation via Attention Patterns and Semantic Alignment
Shanghao Li, Jinda Han, Yibo Wang +5
Graph-based Retrieval-Augmented Generation (GraphRAG) enhances Large Language Models (LLMs) by incorporating external knowledge from linearized subgraphs retrieved from knowledge g…