Embodied AI2026
Train robot reinforcement-learning agents with a heterogeneous runtime that streams CPU-parallel physics simulations (MuJoCo / Motrix) via shared memory into GPU/accelerator policy learners; provides a unified CLI, cross-platform backend support and demo checkpoints.
AI Agent2026
A TypeScript framework for building programmable, headless autonomous agents with a harness-centric runtime. Includes an SDK and CLI, virtual sandboxes (just-bash) with optional full container sandboxes, provider-agnostic model settings, and connectors for CI/Daytona/MCP—suited for deployable agent runtimes.
AI Agent2026
Framework for running agents inside real applications — it exposes shared actions, SQL-backed state, tools, skills, jobs and UI surfaces so agents can act on app state instead of just chatting. Backend-agnostic TypeScript stack with cloneable app templates and visual planning/recap features.
AI Agent2026
Runs an autonomous self-improvement loop where a meta agent crafts a task-specific agent, a target agent executes trials, and a feedback agent updates both harness (code) and model weights—provider-agnostic profiles with reproducible runs and a live dashboard.
AI Model2026
Delivers image and video generation, editing, and understanding inside a single 3B-parameter multimodal model trained from scratch with a multi-task recipe. Notable for strong unified benchmarks at 3B scale; inference requires large GPU memory (≈40GB+ VRAM).
AI Train2026
End-to-end Python framework for training and serving NVIDIA's Cosmos world models (Cosmos3), integrating distributed training (FSDP/TP/CP/PP), DCP/safetensors checkpoints, dataset adapters, multiple inference backends, online serving, and agent skills.
AI Agent Papers2026
Zimu Wang, Xiaobo Wang +12University of California, Berkeley, University of Science and Technology of China +5
Builds and compares agent-evolution strategies on shared infrastructure, keeping mutable agent resources separate from protected evaluation. The best observed overall pass@1 gain was 13.5 percentage points, but results varied by setting and did not always transfer to held-out tasks.
AI Agent Papers2026
Haibo Jin, Peng Kuang +12University of Illinois Urbana-Champaign, Georgia Institute of Technology +1
Equips reusable resources with resident LLMs so agents can apply them in context. HEELO composes the needed units into task-specific workflows, checks results against environmental evidence, and revises only the work implicated by failures.
AI Agent2023
Memory layer that lets AI agents remember users and context across sessions.