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.
11
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.
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.
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%.
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
-
MultiWorld: Scalable Multi-Agent Multi-View Video World Models
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.
-
Safe Planning in Interactive Environments via Iterative Policy Updates and Adversarially Robust Conformal Prediction
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: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model
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.
-
AgentComm: Semantic Communication for Embodied Agents
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.
-
EmbodiedClaw: Conversational Workflow Execution for Embodied AI Development
EmbodiedClaw automates embodied AI development workflows through conversation, reducing manual effort and improving consistency and reproducibility.
-
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.
-
Pre-VLA: Preemptive Runtime Verification for Reliable Vision-Language-Action and World-Model Rollouts
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%.
-
Position: Embodied AI Requires a Privacy-Utility Trade-off
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.
-
Multi-Agent Systems: From Classical Paradigms to Large Foundation Model-Enabled Futures
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.
-
Low-Altitude Wireless Networks: A Comprehensive Survey
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.
- Sentinel-VLA: A Metacognitive VLA Model with Active Status Monitoring for Dynamic Reasoning and Error Recovery