Yanzhe Chen, Ziyi Yang, Jifeng Zhu, Qiming Huang, Ruihe An, Peiyao Xu, Hesen Yang, Runda Liu · 2026 · arXiv
DOI: 10.48550/arXiv.2610.30108 · open-access PDF
Multimodale Agenten (MMAs) unterstützen die Interaktion durch Vernunft, Gedächtnis, Werkzeuge und Feedback, am sichtbarsten als Computer-Use-Agenten, während Robotersysteme (RSs) die Sension und Aktion unter physikalischer Dynamik paaren. Wir definieren multimodale verkörperte Agenten (MMEAs) als zielgerichtete Systeme, die multimodale Aufgabe-Rezensionen mit physischen Aktionen paaren und Entscheidungen aus dem resultierenden Feedback überarbeiten. Dies wirft eine zentrale Frage auf: Was ändert sich, wenn ein multimodaler Agent von Computer-Use zu Roboter-Use bewegt?
Machine translation (Meta M2M100); the English original follows.
Multimodal agents (MMAs) sustain interaction through reasoning, memory, tools, and feedback, most visibly as computer-use agents, while robotic systems (RSs) couple sensing and actuation under physical dynamics. We define multimodal embodied agents (MMEAs) as goal-directed systems that couple multimodal task reasoning with physical action and revise decisions from the resulting feedback. This raises a central question: what changes when a multimodal agent moves from computer-use to robot-use? We introduce PAPAV, a unified capability-centric framework of five recurring functions: Perceive the c
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.30108, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange