collaborators

5 papers

cs.CL2026

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…

cs.CL2026

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…

cs.CL2026

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…

cs.AI2026

Evaluating Prompting and Execution-Based Methods for Deterministic Computation in LLMs

Hongkun Yu

Large Language Models (LLMs) have demonstrated strong capabilities in natural language understanding and reasoning. However, their ability to perform exact, deterministic computati…

cs.CL2026

Incentivizing Agentic Reasoning in LLM Judges via Tool-Integrated Reinforcement Learning

Ran Xu, Jingjing Chen, Jiayu Ye +4

Large Language Models (LLMs) are widely used as judges to evaluate response quality, providing a scalable alternative to human evaluation. However, most LLM judges operate solely o…