6 papers
Phase Transition for Budgeted Multi-Agent Synergy
Bang Liu, Linglong Kong, Jian Pei
Multi-agent systems can improve reliability, yet under a fixed inference budget they often help, saturate, or even collapse. We develop a minimal and calibratable theory that predi…
Sparsity-Aware Evolution for Model Merging
Huan Zhang, Yanjian Zhang, Guillaume Wisniewski +2
We propose a sparsity-aware evolutionary (SAE) framework for model merging that involves iterative pruning-merging cycles to act as a novel mutation operator. We incorporate the sp…
Towards Agentic Intelligence for Materials Science
Huan Zhang, Yizhan Li, Wenhao Huang +18
The convergence of artificial intelligence and materials science presents a transformative opportunity, but achieving true acceleration in discovery requires moving beyond task-iso…
Can Test-Time Scaling Improve World Foundation Model?
Wenyan Cong, Hanqing Zhu, Peihao Wang +7
World foundation models, which simulate the physical world by predicting future states from current observations and inputs, have become central to many applications in physical in…
IndoorWorld: Integrating Physical Task Solving and Social Simulation in A Heterogeneous Multi-Agent Environment
Dekun Wu, Frederik Brudy, Bang Liu +1
Virtual environments are essential to AI agent research. Existing environments for LLM agent research typically focus on either physical task solving or social simulation, with the…
Accelerated Inorganic Materials Design with Generative AI Agents
Izumi Takahara, Teruyasu Mizoguchi, Bang Liu
Designing inorganic crystalline materials with tailored properties is critical to technological innovation, yet current generative computational methods often struggle to efficient…