1 citations · 1 across the 9 of their papers we have counts for
10 papers
SeOPD: Self-Evolving LLMs via Online Policy Distillation from Self-Generated Chain-of-Thought
Xiaoshu Chen, Xiangyu Wong, Sihang Zhou +2
Recent advances in online policy self-distillation (OPSD) have demonstrated that large language models (LLMs) can improve their capabilities by leveraging external privileged infor…
AutoViewMem: Self-Configuring Orthogonal Views for Conversational Long-Term Memory
Zijie Cao, Xijun Qu, Zhicheng Gu +7
Long-term memory is essential for large language model (LLM) agents to maintain consistency and personalization over extended interactions. Existing memory systems typically rely o…
Harness-G: A Graph-Structured Harness for Search Agents
Yanning Hou, Haoyuan Chen, Sihang Zhou +7
Reinforcement learning (RL) search agents commonly model retrieval as free-form natural-language query generation and optimize multi-turn interactions using final-answer rewards. C…
Keep the Needle, Prune the Haystack: Defect-Preserving Token Pruning for Efficient Zero-Shot Anomaly Detection
Yanning Hou, Jingyuan Zhang, Xiaoyun Wang +3
Zero-shot visual anomaly detection has achieved remarkable progress, with recent vision-only approaches further improving performance while simplifying the inference pipeline. Howe…
FreqAnchorAD: Language-Free Zero-Shot Anomaly Detection via Frequency-Deviation Anchoring
Jianfeng Qiu, Peiyuan Li, Juan Xie +4
Zero-shot anomaly detection (ZSAD) aims to detect anomalies and localize defective regions in unseen target domains without target training data. Recent ZSAD methods build on pretr…
DRIVE: Modeling Skills at the Reasoning and Interaction Levels for Web Agents under Continual Learning
Xirui Liu, Sihang Zhou, Yanning Hou +6
Web agents require both high-level reasoning (for task decomposition) and low-level interactions (for page elements manipulation) to conduct different tasks. However, these knowled…
Decoupled Travel Planning with Behavior Forest
Duanyang Yuan, Sihang Zhou, Yanning Hou +7
Behavior sequences, composed of executable steps, serve as the operational foundation for multi-constraint planning problems such as travel planning. In such tasks, each planning s…
AtomicRAG: Atom-Entity Graphs for Retrieval-Augmented Generation
Yanning Hou, Duanyang Yuan, Sihang Zhou +5
Recent GraphRAG methods integrate graph structures into text indexing and retrieval, using knowledge graph triples to connect text chunks, thereby improving retrieval coverage and…
Soft Reasoning Paths for Knowledge Graph Completion
Yanning Hou, Sihang Zhou, Ke Liang +6
Reasoning paths are reliable information in knowledge graph completion (KGC) in which algorithms can find strong clues of the actual relation between entities. However, in real-wor…
Knowledge Graph Completion with Relation-Aware Anchor Enhancement
Duanyang Yuan, Sihang Zhou, Xiaoshu Chen +4
Text-based knowledge graph completion methods take advantage of pre-trained language models (PLM) to enhance intrinsic semantic connections of raw triplets with detailed text descr…