Skip to main content
← Back to news

Envisioning Agentic Robotics: the roadmap for agentic robotics after GPT-6 Astra

Research
Frontier models with agentic harnesses matched or exceeded task-specific policies within weeks: the paper charts where robotics is heading, with an explicit focus on safety, shared evaluation, and the moment a robot must stop and ask.

Get the next local-AI briefing

Once a week, the top selection from iaLocale: articles, news and resources on local AI, and more.

After signing up you receive a confirmation email (double opt-in). Without confirmation we send nothing. No spam, we promise.

Related resources

Tools and resources from the iaLocale archive relevant to this content.

🤖

NVIDIA Cosmos3-Edge-Policy-DROID

Models

Post-trained 4B robot-policy checkpoint on the Cosmos3-Edge base: from natural-language instructions and visual observations of the DROID robot it generates action trajectories for manipulation tasks. Mixture-of-Transformers architecture (autoregressive tower + diffusion transformer), OpenMDW 1.1 license, commercial and non-commercial use.

🟠

Anthropic Claude

Inference

Inference API for Anthropic's Claude models (Claude 1 since 2023). Like OpenAI, you pay per token, input and output, with request limits per plan: the frontier path with no servers of your own.

NVIDIA ARDY-Core-RP-20FPS-Horizon40

Models

326M-parameter autoregressive diffusion model for interactive real-time humanoid motion: online text prompts, kinematic constraints (root trajectories, keyframes, sparse poses) and sequences up to 8 seconds. Trained on Bones Rigplay 1 (27-joint Core skeleton, 20 fps), optimized for NVIDIA Ampere, Hopper and Blackwell GPUs. NVIDIA Open Model Agreement license, commercial use allowed. On Hugging Face since October 7, 2026.

🩻

NVIDIA Cosmos3-H-Dreams

Models

Real-time, action-conditioned surgical world model for the CMR Surgical Versius system: autoregressively generates the endoscopic video of a robotic cholecystectomy from a frame and the two arms' commands. 15.17B MoT (Qwen3-VL-8B tower + latent-diffusion expert), causal 4-step student with KV cache. 30 FPS at 832x480 on RTX PRO 6000 Blackwell (40GB), 20.2 FPS on Max-Q (80GB) and 16.9 FPS at 512x288 on DGX Spark. NVIDIA Open Model license, released 2026-10-20.