QuadAgent uses an asynchronous multi-agent architecture with an Impression Graph for scene memory and vision-based avoidance to enable training-free vision-language guided agile quadrotor flight, outperforming baselines in simulations and achieving real-world speeds up to 5 m/s.
arXiv preprint arXiv:2505.03673 (2025)
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 2
method 1
citation-polarity summary
years
2026 11representative citing papers
Proposes a structured concept-centric memory system for embodied agents that connects object, scene, transition, and skill memories to support coarse-to-fine retrieval and improve task performance over baselines.
A systematic study of hierarchical VLA agents identifies design principles that improve robot manipulation performance over flat and naive hierarchical baselines in simulation and real-world experiments.
Benchmark Agent is an autonomous agentic system that constructs benchmarks for LLMs and MLLMs via query analysis, subtask design, annotation and quality control, yielding 15 benchmarks with minimal human input.
OneVLA is a unified VLA model using a shared action head and multi-stage progressive training with CoT fine-tuning that reports state-of-the-art results on both navigation and manipulation in simulation and real-world settings.
BrainMem equips LLM-based embodied planners with working, episodic, and semantic memory that evolves interaction histories into retrievable knowledge graphs and guidelines, raising success rates on long-horizon 3D benchmarks.
HoloAgent-0 is a unified embodied agent framework with Embodied AgentOS, 3D spatial memory, and embodied skills, deployed and evaluated on real robot hardware for navigation and manipulation tasks.
IMPACT decouples forceful manipulation into task-planning and internal-model predictive control, claiming higher success rates, better generalization to unseen weights, and improved safety and energy efficiency in simulation and real-world tests.
A governed upgrade framework with interface, policy, behavioral, and recovery checks keeps unsafe activations at zero across multi-round AI capability upgrades on a PyBullet/ROS 2 manipulation testbed while retaining task success near naive upgrades.
CoEnv introduces a compositional environment that integrates real and simulated spaces for multi-agent robotic collaboration, using real-to-sim reconstruction, VLM action synthesis, and validated sim-to-real transfer to achieve high success rates on multi-arm manipulation tasks.
A survey comparing classical multi-agent systems with large foundation model-enabled multi-agent systems, showing how the latter enables semantic-level collaboration and greater adaptability.
citing papers explorer
-
CoEnv: Driving Embodied Multi-Agent Collaboration via Compositional Environment
CoEnv introduces a compositional environment that integrates real and simulated spaces for multi-agent robotic collaboration, using real-to-sim reconstruction, VLM action synthesis, and validated sim-to-real transfer to achieve high success rates on multi-arm manipulation tasks.