10 papers
Shared Prefixes, Better Credit: Adaptive Routing for Multi-Agent Reasoning
Yiqing Liu, Zihao Wang, Hantao Yao +2
Multi-agent reasoning (MAR) improves reasoning reliability through iterative solution exchange and refinement. Existing adaptive MAR methods typically learn routing decisions from…
Modeling U.S. Attitudes Toward China via an Event-Steered Multi-Agent Simulator
Chenxu Zhu, Hantao Yao, Wu Liu +2
Understanding the dynamic evolution of opinions, such as U.S. public attitudes toward China, is essential for assessing geopolitical risks. However, existing LLM-based multiagent s…
GASim: A Graph-Accelerated Hybrid Framework for Social Simulation
Xuan Zhou, Yanhui Sun, Hantao Yao +3
Large-scale social simulators are essential for studying complex social patterns. Prior work explores hybrid methods to scale up simulations, combining large language models (LLM)-…
HCP-MAD:Heterogeneous Consensus-Progressive Reasoning for Efficient Multi-Agent Debate
Yiqing Liu, Hantao Yao, Wu Liu +2
Multi-Agent Debate (MAD) is a collaborative framework in which multiple agents iteratively refine solutions through the generation of reasoning and alternating critique cycles. Cur…
EMS: Multi-Agent Voting via Efficient Majority-then-Stopping
Yiqing Liu, Hantao Yao, Wu Liu +1
Majority voting is the standard for aggregating multi-agent responses into a final decision. However, traditional methods typically require all agents to complete their reasoning b…
Rel-Zero: Harnessing Patch-Pair Invariance for Robust Zero-Watermarking Against AI Editing
Pengzhen Chen, Yanwei Liu, Xiaoyan Gu +3
Recent advancements in diffusion-based image editing pose a significant threat to the authenticity of digital visual content. Traditional embedding-based watermarking methods often…
PopSim: Social Network Simulation for Social Media Popularity Prediction
Yijun Liu, Wu Liu, Xiaoyan Gu +3
Accurately predicting the popularity of user-generated content (UGC) is essential for advancing social media analytics and recommendation systems. Existing approaches typically fol…
RumorSphere: A Framework for Million-scale Agent-based Dynamic Simulation of Rumor Propagation
Yijun Liu, Wu Liu, Xiaoyan Gu +4
Rumor propagation modeling is critical for understanding and mitigating misinformation. Existing approaches combining rule-based regular agents with LLM-driven core agents provide…
DynamiX: Large-Scale Dynamic Social Network Simulator
Yanhui Sun, Wu Liu, Wentao Wang +3
Understanding the intrinsic mechanisms of social platforms is an urgent demand to maintain social stability. The rise of large language models provides significant potential for so…
Enhancing Federated Class-Incremental Learning via Spatial-Temporal Statistics Aggregation
Zenghao Guan, Guojun Zhu, Yucan Zhou +4
Federated Class-Incremental Learning (FCIL) enables Class-Incremental Learning (CIL) from distributed data. Existing FCIL methods typically integrate old knowledge preservation int…