collaborators

6 papers

cs.AI2026

RubricWorld: World Model-Guided Rubric Optimization for LLM Graders

Hongji Pu, Hang Li, Yucheng Chu +1

Rubric optimization improves LLM grading by revising scoring instructions while keeping the grader's parameters fixed. Existing optimizers often judge edits by aggregate validation…

cs.SE2026

Launder-Bench: Can Repository-Level Agentic Code Laundering Be Detected?

Yuntong Hu, Hongji Pu, Zimo Li +5

Coding agents can now rewrite repository-scale codebases while preserving tested behavior, creating a new challenge for plagiarism detection, license auditing, and software provena…

cs.AI2026

PAPER2LLM++: Continual Self-Evolution of LLMs from Research Papers

Hongji Pu, Yilun Zhao, Wenpeng Yin

Research on LLMs continually uncovers model limitations, their causes, and potential solutions. Yet these human discoveries remain largely disconnected from model evolution: an LLM…

cs.AI2026

Network World Models as Environments for Algorithm Design on Complex Systems

Rishab Alagharu, Hongji Pu, Zeeshan Memon +3

World models, which simulate an environment and predict how it changes under actions, are increasingly used in real-world applications such as robotics. Complex systems call for th…

cs.AI2026

BELIEFRAG: Making Adaptive RAG State-Aware under Evolving Evidence

Hongji Pu

Adaptive RAG uses signals such as confidence, relevance, support, and retrieval quality to decide when to search or correct evidence. In multi-step retrieval, however, these local…

cs.CE2026

Beyond Forecasting: Recasting Volatility Control as a Routing Problem

Hongji Pu, Leyang Zhou

Volatility control converts risk estimates into portfolio exposure, yet existing approaches often rely on a fixed volatility estimator or a pre-defined control rule that may not ad…