18 papers
SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries
Xingyu Tan, Xiaoyang Wang, Qing Liu +4
Large Language Models (LLMs) increasingly act as agents whose procedural knowledge is stored in reusable skill packages and loaded at inference time. As skill libraries grow, a cen…
HyperAgent: Planning and Acting over Tool-Schema Hypergraphs for Tool-Use LLM Agents
Zian Zhai, Xingyu Tan, Gaowang Zou +2
Large language model (LLM) agents increasingly rely on external tools to complete complex real-world tasks. However, reliable tool-use planning remains challenging due to the limit…
Selection Integrity for LLM Graph Memory: An Accumulability Criterion for Information-Flow-Blind Retrieval
Zeming Fei, Hongming Fei, Xiaoyang Wang +4
Agent memory is moving to graphs, and the provenance defenses now being built for it all check one thing: the provenance of the records an agent retrieves. We show that this entire…
Trace Only What You Need: Structure-Aware On-Demand Hypergraph Memory for Long-Document Question Answering
Xiangjun Zai, Xingyu Tan, Chen Chen +2
Long-document question answering (QA) requires large language models (LLMs) to reason over evidence scattered across lengthy documents, where answers often depend on event order, s…
The Consistency Illusion: How Multi-Agent Debate Hides Reasoning Misalignment
Xiaoyang Wang, Christopher C. Yang
Multi-agent LLM systems for medical question answering often treat consensus as a reliability signal: if multiple agents agree on an answer, it is presumed trustworthy. However, an…
Graph is a Natural Regularization: Revisiting Vector Quantization for Graph Representation Learning
Zian Zhai, Fan Li, Xingyu Tan +2
Vector Quantization (VQ) has recently emerged as a promising approach for learning compressed and discrete representations for graph-structured data. However, a fundamental challen…