MultiWorld is a scalable framework for multi-agent multi-view video world models that improves controllability and consistency over single-agent baselines in game and robot tasks.
hub Canonical reference
Multi-agent embodied ai: Advances and future directions
Canonical reference. 80% of citing Pith papers cite this work as background.
13
Pith papers citing it
Background
80% of classified citations
hub tools
citation-role summary
background 4
method 1
citation-polarity summary
representative citing papers
The work develops an iterative safe planner that adjusts conformal prediction bounds across policy updates via sensitivity analysis to maintain distribution-free safety guarantees despite interaction-induced distribution shifts.
VLA-ATTC equips VLA models with adaptive test-time compute via an uncertainty clutch and relative action critic, cutting failure rates by over 50% on LIBERO-LONG.
Sentinel-VLA adds metacognitive status monitoring to VLA models for on-demand reasoning and error recovery, reporting over 30% higher real-world task success than prior SOTA.
AgentComm achieves nearly 50% bandwidth reduction in embodied agent communication via LLM semantic processing, importance-aware transmission, and a task knowledge base, with negligible impact on task completion.
MorphoQuant proposes DABC and MDQFO for 4-bit quantization of omni-modal LLMs, claiming superior performance over SOTA W4A4 methods and even W4A16 baselines on benchmarks like ScienceQA.
EmbodiedClaw automates embodied AI development workflows through conversation, reducing manual effort and improving consistency and reproducibility.
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.
Pre-VLA is a multimodal runtime verifier that predicts safety confidence and advantage scores for action chunks, raising closed-loop success rates on the LIBERO benchmark from 30.79% to 37.62%.
Proposes Physical-AI architecture integrating radio-based perception, world modeling, and decision-making for environment-aware 6G networking, with simulations claiming reduced outage and latency versus ISAC.
Embodied AI requires treating privacy as a lifecycle architectural constraint rather than a stage-local feature, addressed via the proposed SPINE framework with a multi-criterion privacy classification matrix.
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.
A comprehensive survey on low-altitude wireless network (LAWN) systems covering fundamentals, evolution of designs, performance metrics, privacy and security concerns, and airspace structuring for practical deployment.
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.