2 citations · 6 across the 16 of their papers we have counts for
5 papers · 1 filter
SEEDS: Preview-Guided Evidence Admission for Search Agents
Jiajin Liu, Chenxi Xu, Dongzhe Fan +2
Search agents extend large reasoning models with multi-round access to external knowledge, yet most existing systems largely conflate retrieving evidence with consuming it. Retriev…
DAGent: Evaluate-then-Grow Planning for Deep Research Agents
Hanwen Liu, Yuanfu Sun, Qiaoyu Tan
Deep research tasks require agents to navigate large knowledge spaces, synthesize evidence across many sources, and adapt their plans as findings emerge. Directed acyclic graph (DA…
AgentGL: Towards Agentic Graph Learning with LLMs via Reinforcement Learning
Yuanfu Sun, Kang Li, Dongzhe Fan +2
Large Language Models (LLMs) increasingly rely on agentic capabilities-iterative retrieval, tool use, and decision-making-to overcome the limits of static, parametric knowledge. Ye…
GraphSearch: Agentic Search-Augmented Reasoning for Zero-Shot Graph Learning
Jiajin Liu, Yuanfu Sun, Dongzhe Fan +1
Recent advances in search-augmented large reasoning models (LRMs) enable the retrieval of external knowledge to reduce hallucinations in multistep reasoning. However, their ability…
UniGLM: Training One Unified Language Model for Text-Attributed Graph Embedding
Yi Fang, Dongzhe Fan, Sirui Ding +2
Representation learning on text-attributed graphs (TAGs), where nodes are represented by textual descriptions, is crucial for textual and relational knowledge systems and recommend…