ParallelWorld: Test-Time Scaling for Agentic Embodied Reasoning

arXiv:2608.22971 · cs.AI, cs.CV · Submitted 2026-08-24 · Read on arXiv

cs.AI, cs.CV

Submitted: 2026-08-24

Updated: 2026-10-13

Project page: https://chen-min-22.github.io/ParallelWorld-page

Terminology

• Test-time Scaling — 1× in this paper · explained in 2 episodes

Sources

• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• Thinking in Dynamics: How Multimodal Large Language Models Perceive, Track, and Reason Dynamics in Physical 4D World
• GPT-4o System Card
• SpatialCoT: Advancing Spatial Reasoning through Coordinate Alignment and Chain-of-Thought for Embodied Task Planning
• EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems