Papers by Zhewei Wei

5 papers
LLM-Based Multi-Agent Systems are Scalable Graph Generative Models (2025.findings-acl)

Copied to clipboard

Challenge: Social graphs are mathematical structures stem from pairwise interactions between entities through nodes and edges.
Approach: They propose a framework for dynamic, text-attributed social graph generation that simulates the temporal node and edge generation processes for zero-shot social graphs.
Outcome: The proposed framework improves macroscopic graph structure metrics by 11% . the proposed model can generate graphs with up to 100,000 nodes or 10 million edges .
GRAPHIA: Harnessing Social Graph Data to Enhance LLM-Based Social Simulation (2026.acl-long)

Copied to clipboard

Challenge: Social graphs provide high-quality supervision signals that encode local interactions and global network structure, yet they remain underutilized for LLM training.
Approach: They propose a general LLM-based social graph simulation framework that leverages graph data as supervision for LLM training.
Outcome: The proposed framework improves micro-level alignment by 6.1% on three real-world networks compared to the strongest baseline.
Towards Effective and Efficient Continual Pre-training of Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Continual pre-training (CPT) has been an important approach for adapting language models to specific domains or tasks.
Approach: They propose a Continual pre-training method that can greatly improve Chinese language ability and scientific reasoning ability of LLMs.
Outcome: The proposed method can greatly improve Chinese language ability and scientific reasoning ability of LLMs.
SRAP-Agent: Simulating and Optimizing Scarce Resource Allocation Policy with LLM-based Agent (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing research on the allocation of public scarce resources has limitations due to data scarcity and data scariness.
Approach: They propose a framework that integrates Large Language Models into economic simulations . they conduct extensive policy simulation experiments to verify the framework's effectiveness .
Outcome: The proposed framework bridges the gap between theoretical models and real-world dynamics by integrating large language models into economic simulations.
MotifAgent: Learning Molecular Assembly through Multi-Agent Collaboration for Chemical Language Understanding (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to molecular understanding are limited to static motif recognition without understanding connection rules governing how motifs assemble into valid topological structures.
Approach: They propose a multi-agent reinforcement learning framework inspired by emergent collective intelligence to solve a problem where each motif is represented by an agent sharing a common LLM backbone.
Outcome: Extensive experiments show that the proposed framework surpasses specialized expert models in molecular understanding tasks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations