collaborators

18 papers

cs.CL2026

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…

cs.AI2026

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…

cs.CR2026

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…

cs.CL2026

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…

cs.MA2026

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…

cs.LG2026

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…