2 papers
cs.AI2026
ProWorld: Progress-Aware Hyperbolic World Models for Long-Horizon Visual Goal Reaching
Zihan Liu, Yuzhe Zhuang, Yuanzu Li +4
JEPA-style visual world models offer an effective paradigm for visual goal planning by predicting future latent representations. Existing methods typically learn local transition c…
cs.MA2026
Dynamic Trust-Aware Sparse Communication Topology for LLM-Based Multi-Agent Consensus
Wanshuang Gou, Zihan Liu
Large language model-driven multi-agent systems enhance the reliability of complex reasoning tasks through multi-round deliberation, role specialization, and cross-validation. Howe…