collaborators

5 papers

cs.CL2026

Are Large Language Models Suitable for Graph Computation? Progress and Prospects

Yuting Zhang, Yi Han, Kai Wang +3

Large language models (LLMs) have been increasingly explored for graph computation, where tasks require reasoning over structured relationships and algorithmic operations. Yet, it…

cs.LG2026

SHAP-Guided Kernel Actor-Critic for Explainable Reinforcement Learning

Na Li, Hangguan Shan, Wei Ni +2

Actor-critic (AC) methods are a cornerstone of reinforcement learning (RL) but offer limited interpretability. Current explainable RL methods seldom use state attributions to assis…

cs.LG2025

Learning Causal States Under Partial Observability and Perturbation

Na Li, Hangguan Shan, Wei Ni +3

A critical challenge for reinforcement learning (RL) is making decisions based on incomplete and noisy observations, especially in perturbed and partially observable Markov decisio…

cs.LG2025

Sample-Efficient Tabular Self-Play for Offline Robust Reinforcement Learning

Na Li, Zewu Zheng, Wei Ni +3

Multi-agent reinforcement learning (MARL), as a thriving field, explores how multiple agents independently make decisions in a shared dynamic environment. Due to environmental unce…

cs.CL2025

StepChain GraphRAG: Reasoning Over Knowledge Graphs for Multi-Hop Question Answering

Tengjun Ni, Xin Yuan, Shenghong Li +4

Recent progress in retrieval-augmented generation (RAG) has led to more accurate and interpretable multi-hop question answering (QA). Yet, challenges persist in integrating iterati…