NUS Paper Proposes PAPAV: A Unified Capability Framework from Computer-Use to Robot-Use Agents

showlab · hf · 2026-10-22

Show Lab at NUS introduces PAPAV, a unified capability-centric framework for multimodal embodied agents (MMEAs) spanning computer-use and robot-use.

• Defines five recurring capabilities by function rather than architecture: Perceive, Anticipate, Plan, Act, Verify
• Central question: what changes when a multimodal agent moves from computer-use to robot-use?
• Identifies five physical constraints, from partial observability to unverifiable outcomes, that leave fewer choices fixed in advance and less room to reverse errors
• Analysis of 64 benchmarks shows evaluation centers on Act; only 5 assess Anticipate, exposing a major evaluation gap

Original post →

More from Embodied

• Robotics fashion is now an industry, observer says — micoolcho · 2026-10-22
• Close-up photos from a Chinese expo reveal a humanoid robot's joint and torso design — micoolcho · 2026-10-22
• Eric Jang: robots need open SDKs so the community can secure them at scale — ericjang11 · 2026-10-22
• Cambridge's Rika Antonova on co-evolving robot bodies and brains, Co-design Gym expansion — contactrika · 2026-10-22
• NVIDIA expands Cosmos with Data Factory blueprints and Cosmos 3 world models — NVIDIA Blog · 2026-10-22
• Musk: Optimus V3 demo video in 1-2 months, AI5 chip coming April 2027 — elonmusk · 2026-10-22

Embodied channel →