Run fast, private agents on-device with LFM2.5-24B-A2B

Designing the hf CLI as an agent-optimized way to work with the Hub

Holo3.1: Fast & Local Computer Use Agents

BlueLM-GUI Technical Report: A Real-Device-Centric Flywheel for Self-Improving Mobile GUI Agents

arXiv:2609.12394v2 Announce Type: replace Abstract: Mobile GUI agents are shifting from multi-module frameworks to native models trained end-to-end, yet industrial deployment faces three persistent g...

Holotron-12B - High Throughput Computer Use Agent

DevicesWorld: Benchmarking Cross-Device Agents in Heterogeneous Environments

arXiv:2607. 13465v1 Announce Type: cross Abstract: LLM-based agents have rapidly improved at operating individual digital environments such as mobile applications, desktop systems, and smart homes.

The next evolution of the Agents SDK

OpenAI updates the Agents SDK with native sandbox execution and a model-native harness, helping developers build secure, long-running agents across files and tools.

A Deterministic Security Runtime for LLM Agents on MPI and Batch-Scheduled HPC Systems: Consensus-Governed, Hardware-Rooted Supervision of Every Rank

The paper introduces Enclawed, a deterministic security runtime that protects large language model agents running on high‑performance computing (HPC) systems. It provides hardware‑rooted supervision for every rank, preventing compromised hosts from causing catastrophic failures, and enforces launch policies, lease‑based heartbeats, and automatic eviction or killing of tampered jobs. Enclawed operates without administrator privileges, integrates via Secure Shell, and adds minimal startup overhead while successfully blocking a wide range of simulated attacks.

SchemaWeaver: Accelerating On-Device Mobile Agentic AI via Schema-Guided Parallel LLM Decoding

arXiv:2610.17436v1 Announce Type: new Abstract: Large language models (LLMs) on mobile devices can act as agents that call external software tools to complete complex tasks, but the major challenge o...

Tracekit Box: Running AI Agents in Micro-VMs Where Every Way Out Is Decided and Signed

Tracekit Box is an open‑source system that runs AI agents inside isolated Firecracker micro‑VMs with no network card, ensuring that every possible exit point—commands, outbound connections, secrets, model calls, and workspace patches—is controlled by a host‑side signer. The signer authorizes and signs each action, preventing unauthorized data leakage or code changes, and the VM’s final state is packaged into a verifiable .tkb bundle. The system has passed 13 end‑to‑end checks, 15 fuzz targets, and a demo run with 102 signed records, demonstrating robust isolation and auditability.

Tiny Agents: an MCP-powered agent in 50 lines of code

Agent libOS: A Library-OS-Inspired Runtime for Long-Running, Capability-Controlled LLM Agents

arXiv:2606. 03895v1 Announce Type: cross Abstract: Large language model (LLM) agents are evolving from request-response assistants into long-running software actors: they maintain state across model calls, fork subtasks, wait for external events, request human authority, generate tools, and perform side effects that must be resumed and audited.

Introducing AgentKit, new Evals, and RFT for agents

Today, we’re releasing new tools to help developers go from prototype to production faster: AgentKit, expanded evals capabilities, and reinforcement fine-tuning for agents.