Shiqi Yan — accepted AI-conference papers

2026

Backjump-on-Graph: Empowering LLMs with Reinforced Retrospective Exploration for Agentic KG Reasoning

Yunqi Zhang, Shiqi Yan, Zhenzhao Yuan, Wenrui Liang, Yangming Liu, Zhixiao Qi +7

ICML 2026poster

Grounding Large Language Models (LLMs) in Knowledge Graphs (KGs) has shown significant promise for complex Question Answering (QA) tasks. Since LLMs' limited context window cannot accommodate the sheer volume of large-scale KGs, existing work usually utilizes agents to reason on real-world KGs, whic…

Cited by 0 Source ↗Scholar ↗

2026

Explore-on-Graph: Incentivizing Autonomous Exploration of Large Language Models on Knowledge Graphs with Path-refined Reward Modeling

Shiqi Yan, Yubo Chen, Ruiqi Zhou, Zhengxi Yao, Shuai Chen, Tianyi Zhang +5

ICLR 2026poster

The reasoning process of Large Language Models (LLMs) is often plagued by hallucinations and missing facts in question-answering tasks. A promising solution is to ground LLMs' answers in verifiable knowledge sources, such as Knowledge Graphs (KGs). Prevailing KG-enhanced methods typically constrain…

Cited by 0 Source ↗Scholar ↗