3 papers
cs.MA2026
SC-MAS: Constructing Cost-Efficient Multi-Agent Systems with Edge-Level Heterogeneous Collaboration
Di Zhao, Longhui Ma, Siwei Wang +2
Large Language Model (LLM)-based Multi-Agent Systems (MAS) enhance complex problem solving through multi-agent collaboration, but often incur substantially higher costs than single…
cs.HC2025
MapAgent: Trajectory-Constructed Memory-Augmented Planning for Mobile Task Automation
Yi Kong, Dianxi Shi, Guoli Yang +4
The recent advancement of autonomous agents powered by Large Language Models (LLMs) has demonstrated significant potential for automating tasks on mobile devices through graphical…
cs.CL2025
VisualPuzzles: Decoupling Multimodal Reasoning Evaluation from Domain Knowledge
Yueqi Song, Tianyue Ou, Yibo Kong +3
Current multimodal benchmarks often conflate reasoning with domain-specific knowledge, making it difficult to isolate and evaluate general reasoning abilities in non-expert setting…