collaborators

16 papers

cs.LG2026

DICE: Entropy-Regularized Equilibrium Selection for Stable Multi-Agent LLM Coordination

Yi Xie, Zhanke Zhou, Chentao Cao +2

Multi-agent large language model (LLM) systems often fail to reliably outperform a single strong model equipped with best-of-N sampling. We argue that a core source of this instabi…

cs.LG2026

Beyond Homophily: Towards Generalized Graph Reconstruction Attack and Defense

Zhanke Zhou, Bo Han, Xuan Li +3

Graph neural networks (GNNs) are widely deployed on relational data, yet they can leak sensitive or proprietary information about the training graph adjacency, e.g., social ties, t…

cs.LG2026

The Easy, the Hard, and the Learnable: Confidence and Difficulty-Adaptive Policy Optimization for LLM Reasoning

Zhanke Zhou, Xiangyu Lu, Chentao Cao +4

RL with verifiable rewards can substantially improve LLM reasoning, yet standard GRPO-style training often treats easy, hard, and learnable questions alike through uniform sampling…

cs.CL2026

Deliberate Evolution: Agentic Reasoning for Sample-Efficient Symbolic Regression with LLMs

Xinyu Pang, Zhanke Zhou, Xuan Li +5

Symbolic regression (SR) discovers compact mathematical expressions from data, yet recent LLM-based evolutionary methods remain sample-inefficient because they rely mainly on scala…

cs.AI2026

RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with Large Language Models

Xiao Feng, Bo Han, Zhanke Zhou +5

Reinforcement learning (RL) shows promise for enhancing LLM agentic reasoning, yet sparse terminal rewards hinder fine-grained optimization. Process reward modeling offers an alter…

cs.NE2026

What Do Evolutionary Coding Agents Evolve?

Nico Pelleriti, Sree Harsha Nelaturu, Zhanke Zhou +4

Recent work pairs LLMs with evolutionary search to iteratively generate, modify, and select code using task-specific feedback. These systems have produced strong results in mathema…