11 papers
Counterfactual Graph for Multi-Agent LLM Calibration
Jiatan Huang, Mingchen Li, Ziming Li +3
Multi-agent LLM systems often treat agreement as evidence: when many agents in a panel give the same answer, that answer is assumed to be more reliable. We show that this assumptio…
Where LLM Annotators Fail: Label-Free Learning on Graphs with LLMs
Safal Thapaliya, Jiatan Huang, Chuxu Zhang
Node classification on graphs often requires labeled nodes, yet obtaining labels at graph scale is expensive. When node attributes contain semantic content, such as paper abstracts…
In-Context Optimization for Retrieval-Augmented Generation: A Gradient-Descent Perspective
Mingchen Li, Jiatan Huang, Chuxu Zhang +2
In-context learning has recently been linked to implicit gradient descent in linear self-attention models, suggesting that context can induce a forward-pass update. Retrieval-augme…
RICE-PO: Turning Retrieval Interactions into Credit Signals for Reasoning Agents
Mingchen Li, Hansi Zeng, Zhuo Qian +4
Retrieval is increasingly moving from one-shot matching toward interactive reasoning, where language agents iteratively inspect evidence, reformulate queries, and search again. Tra…
Same Signal, Opposite Meaning: Direction-Informed Adaptive Learning for LLM Agents
Ziming Li, Jiatan Huang, Xiaoguang Guo +2
Adaptive test-time compute for LLM agents aims to invoke extra computation only when it improves performance. Existing methods typically use confidence-, uncertainty-, or difficult…
RiTeK: A Dataset for Large Language Models Complex Reasoning over Textual Knowledge Graphs in Medicine
Jiatan Huang, Mingchen Li, Zonghai Yao +8
Answering complex real-world questions in the medical domain often requires accurate retrieval from medical Textual Knowledge Graphs (medical TKGs), as the relational path informat…