6 papers
From Memory to Skills: Evidence-Grounded Co-Evolution Governance for Long-Horizon LLM Agents
Bo Tang, Yang Zhang, Guomian Zhuang +8
Existing memory systems for long-horizon LLM agents often retrieve prior traces as passive context rather than converting them into executable capabilities. In this paper, we propo…
Search-Induced Issues in Web-Augmented LLM Code Generation: Detecting and Repairing Error-Inducing Pages
Guoqing Wang, Zeyu Sun, Xiaofei Xie +4
Web-augmented large language models (LLMs) offer promising capabilities for automatic code generation. However, integrating live web search exposes models to unreliable or maliciou…
TAdaRAG: Task Adaptive Retrieval-Augmented Generation via On-the-Fly Knowledge Graph Construction
Jie Zhang, Bo Tang, Wanzi Shao +8
Retrieval-Augmented Generation (RAG) improves large language models by retrieving external knowledge, often truncated into smaller chunks due to the input context window, which lea…
MoLoRAG: Bootstrapping Document Understanding via Multi-modal Logic-aware Retrieval
Xixi Wu, Yanchao Tan, Nan Hou +2
Document Understanding is a foundational AI capability with broad applications, and Document Question Answering (DocQA) is a key evaluation task. Traditional methods convert the do…
Hierarchical Graph Information Bottleneck for Multi-Behavior Recommendation
Hengyu Zhang, Chunxu Shen, Xiangguo Sun +5
In real-world recommendation scenarios, users typically engage with platforms through multiple types of behavioral interactions. Multi-behavior recommendation algorithms aim to lev…
Multi-Perspective Attention Mechanism for Bias-Aware Sequential Recommendation
Mingjian Fu, Hengsheng Chen, Dongchun Jiang +1
In the era of advancing information technology, recommender systems have emerged as crucial tools for dealing with information overload. However, traditional recommender systems st…