2 citations · 2 across the 3 of their papers we have counts for
4 papers
Prompted Identity Degrades Cooperation in Multi-Agent LLM Systems
Xavier Del Giudice, Alessio Palma, Matteo Migliarini +2
Multi-agent LLM systems increasingly mix models from several providers, yet exposing each agent's underlying model identity to its peers significantly impairs cooperation. We show…
Bimanual Robot Manipulation via Multi-Agent In-Context Learning
Alessio Palma, Indro Spinelli, Vignesh Prasad +4
Large Language Models (LLMs) have emerged as powerful reasoning engines for embodied control. In particular, In-Context Learning (ICL) enables off-the-shelf, text-only LLMs to pred…
Describe-Then-Act: Proactive Agent Steering via Distilled Language-Action World Models
Massimiliano Pappa, Luca Romani, Valentino Sacco +5
Deploying safety-critical agents requires anticipating the consequences of actions before they are executed. While world models offer a paradigm for this proactive foresight, curre…
Length-Aware Motion Synthesis via Latent Diffusion
Alessio Sampieri, Alessio Palma, Indro Spinelli +1
The target duration of a synthesized human motion is a critical attribute that requires modeling control over the motion dynamics and style. Speeding up an action performance is no…