5 papers
CoMem: Collective-Individual Memory Synergy for Evolutionary Multi-Agent Systems
Chengxin Yu, Zhaoxin Fan, Faguo Wu +3
Designing effective memory mechanisms is crucial for advancing LLM-driven Multi-Agent Systems (MAS), helping agents learn together and perform better over time. While recent work h…
Distribution-Aware Robust Bilevel Optimization: Quantile-Guided Huber Updates in Two-Timescale Stochastic Approximation
Zhiyu Li, Xi Xuan, Davide Carbone
Bilevel optimization (BLO) is fundamental to hierarchical decision-making but suffers from critical instability under heavy-tailed stochastic noise. Existing variance-reduction tec…
Escaping the Variance Trap: Jacobian-Free Dynamics for Root-Finding Bilevel Optimization
Zhiyu Li, Xi Xuan, Davide Carbone
Many central machine learning tasks, from entropy tuning in reinforcement learning to equilibrating generative adversarial networks, are fundamentally stochastic root-finding probl…
TRIDENT: Breaking the Hybrid-Safety-Physics Coupling for Provably Safe Multi-Agent Reinforcement Learning
Zijie Meng, Ziwei Li, Yufei Liu +5
Safe coordination in networked cyber-physical systems forces learning algorithms to simultaneously handle hybrid discrete-continuous actions, hard training-time safety constraints,…
OmniDrive: An LLM-Choreographed Multi-Agent World Model with Unified Latent Co-Compression for Multi-View Driving Video Generation
Zijie Meng, Yufei Liu, Chengqian Ma +8
Generative world models for autonomous driving face two unresolved tensions: heterogeneous control injection, where free-form language, HD-maps, trajectories, and camera poses resi…