The paper introduces Multimodal Embodied Agents (MMEAs), goal‑directed systems that combine multimodal task reasoning with physical action and adapt decisions based on feedback. It proposes the PAPAV framework, which defines five core capabilities—Perceive, Anticipate, Plan, Act, Verify—common to computer‑use agents, robotic systems, and MMEAs. The authors analyze 64 benchmarks, noting that most evaluations focus on Act while Anticipate and Verify are rarely assessed, highlighting gaps and open challenges in designing reliable physical agents.
arXiv:2610.10409v1 Announce Type: cross Abstract: General-purpose agents increasingly write code, use tools, and complete complex digital tasks, raising the question of how far these capabilities car...
General-purpose agents increasingly write code, use tools, and complete complex digital tasks, raising the question of how far these capabilities carry into the physical world. To investigate this, we...
arXiv:2610.10388v1 Announce Type: cross Abstract: Recent advances in multimodal foundation models have made them capable generalist physical agents for a range of manipulation tasks. However, success...
EmbodiedSkills is a unified framework that treats each skill decision as an execution proposal, checking prerequisites and verifying outcomes during long‑horizon vision‑language‑action tasks. It connects high‑level skill selection, bounded low‑level VLA execution, and post‑action verification through a fixed executable‑skill interface, enabling easy replacement of low‑level policies and recording of structured trajectories for supervision and adaptation. Instantiated with Qwen3‑VL and OpenPI/pi0.5 on RoboTwin 2.0 and LIBERO, the framework achieves high success rates (86.20% and 97.40% respectively) and demonstrates effective memory‑dependent task performance.
arXiv:2607. 03283v1 Announce Type: new Abstract: Embodied intelligence systems require not only end-to-end policy models, but also reusable functional modules that transform multimodal observations, robot states, human demonstrations, and task contexts into structured representations, decisions, trajectories, control references, and system services.
ReactHuman is a physics‑grounded benchmark that tests whether multimodal large language models (MLLMs) can make immediate, safety‑critical decisions in simulated humanoid scenarios involving sudden household hazards. The benchmark includes 17 event families, over 1,000 reproducible scenes generated from 240 Hz rigid‑body simulation, and a five‑metric suite evaluating reactions on reasonableness, safety, and physical grounding. Evaluation of seven MLLMs reveals that reactive safety remains unsolved, with models frequently mishandling hazards, relying on appearance over motion, and missing key interception points.
arXiv:2607. 11119v1 Announce Type: cross Abstract: Robot manipulation is a complex task that requires visual understanding, physical reasoning, planning, and closed-loop control.
arXiv:2609.24526v1 Announce Type: new Abstract: Physical AI requires models to ground visual and linguistic understanding in real-world environments while accounting for environmental constraints and...
arXiv:2609.24526v2 Announce Type: replace Abstract: Physical AI requires models to ground visual and linguistic understanding in real-world environments while accounting for environmental constraints...
arXiv:2608. 08523v1 Announce Type: new Abstract: Multimodal embodied agents are increasingly required to solve long-horizon tasks by integrating visual observations, textual goals, and interaction history into closed-loop decision making.
arXiv:2608. 06756v1 Announce Type: new Abstract: Vision-language models are increasingly serving as the reasoning core of embodied agents.
arXiv:2606. 17511v1 Announce Type: cross Abstract: Robot learning and embodied agents now require simulation to serve as a shared execution substrate linking control, skills, and planning, not only as a renderer, controller testbed, or fixed task environment.