AICoder

AI Coding Live News

First-hand AI coding updates from 𝕏/Twitter frontier labs and researchers, distilled by AI with entity benchmarks.

Explore live on 𝕏 ↗

AI Coding Live News

N
Nous Research@NousResearch·
👀282
🔥80

Nous Research opens the official Hermes Agent mobile beta: iOS via TestFlight, Android via Firebase, connecting your phone to your own gateway to approve tools and manage bots and routines

During NousCon 2026 in New York on Oct 30, Nous Research released an official mobile beta of Hermes Agent and put up a sign-up page at hermes-agent.nousresearch.com/mobile: iOS users join the "Hermes Agent - Mobile" beta through TestFlight, and Android users join through Firebase App Distribution. The TestFlight page says the app connects to your own Hermes gateway so you can chat with streaming, approve tool calls, and manage bots and routines from anywhere. Teknium, co-founder and lead engineer of Hermes Agent, confirmed on X that the iPhone and Android betas launched together. Nous has not announced a general release date or any benchmarks.

Key Takeaways

  • Entry point: the official page hermes-agent.nousresearch.com/mobile covers 2 platforms, iOS through TestFlight and Android through Firebase App Distribution
  • Positioning: the TestFlight description says the app connects to your own gateway for streaming chat, tool-call approval, and managing bots and routines; it is a client, not a separate agent running on the phone
  • Confirmation: Teknium, co-founder and lead engineer of Hermes Agent, confirmed in a reply on X that the iPhone and Android betas both launched on NousCon day
  • Watch for clones: several third-party Hermes phone clients already exist, so only use the links on the official page; Nous has not published a general release date or benchmarks
Read full story
Linked Models & Agents:
🤖 Hermes Agent🤖 Hermes Mobile🌐 Nous Research
#Nous Research#Hermes Agent#Hermes Mobile#NousCon#iOS#Android#TestFlight#mobile agent
T
Tibo (OpenAI, Codex & ChatGPT)@thsottiaux·
👀31
🔥80
View on 𝕏 ↗

ChatGPT adds account switching: stay signed in to up to 2 accounts, rolling out on iOS and Android, desktop coming soon

On October 31, Tibo (@thsottiaux), who works on Codex and ChatGPT at OpenAI, announced on X, as day 26 of his daily shipping posts, that ChatGPT mobile now supports switching between accounts, with desktop coming soon. OpenAI's updated Help Center article says users can stay signed in to up to 2 accounts with one active at a time; chats, memory, files, subscriptions, billing and workspaces stay separate, and switching never moves or merges data. The post drew about 10,000 likes and 1.36M views.

ChatGPT adds account switching: stay signed in to up to 2 accounts, rolling out on iOS and Android, desktop coming soon

Key Takeaways

  • Limit: up to 2 signed-in accounts, one active at a time; with 2 signed in you must log out of one before adding another, per the OpenAI Help Center
  • Platforms: the Help Center says web plus the iOS and Android apps, with mobile rolling out gradually (Settings, then Switch account); Tibo says the desktop app is coming soon
  • Isolation: chats, memory, files, subscriptions, billing and workspaces are not shared, and switching never moves chats or merges accounts; a newly created second account starts on the Free plan
  • Notifications: mobile can show notifications for both accounts, and tapping one for the other account switches to it, so check the active account before pasting work context
  • Reach: Tibo's post had about 10,120 likes and 1.36M views (public X metrics as of Oct 31, 12:00 UTC); he also teased banked usage resets over the next two days
Read full story
Linked Models & Agents:
🤖 chatgpt🤖 codex🌐 OpenAI
#ChatGPT#account switching#Multi account#OpenAI#iOS#Android#Tibo
C
CapCut@capcutapp·
👀192
🔥80
View on 𝕏 ↗

CapCut announces a ChatGPT plugin is coming soon, bringing its video generation and editing tools inside ChatGPT with drafts that move to the CapCut web editor

At 18:34 UTC on 2026-10-24, during its CapCut World event in Los Angeles, ByteDance's CapCut announced from its official account (@capcutapp) that a new CapCut plugin is coming soon to ChatGPT (post). According to CapCut, the plugin brings its video editing and generation tools inside ChatGPT: users can start with an idea in ChatGPT, create it with the plugin right in the chat, then move the draft to the CapCut web editor to refine and publish. When we pulled it, the post had about 3,646 likes, 319 reposts, 504 replies and 450K views. The event site lists OpenAI's Head of Partnerships Mahak Sharma and Head of Creator Product Sam Yam as speakers. Many creator posts on X say the plugin is already in early access on ChatGPT desktop with mobile and web around mid-November, but CapCut's own post still says coming soon, so timing and pricing should be taken from CapCut's later announcements.

Key Takeaways

  • Official source: CapCut's post on X, published 18:34 UTC on 10-24, with about 3,646 likes, 319 reposts, 216 quotes, 504 replies and 450K views when we pulled it
  • What it does: CapCut's video editing and generation tools inside ChatGPT, so a chat idea can become a video draft directly
  • Workflow: drafts made with the plugin can move to the CapCut web editor for further editing, sharing and publishing
  • OpenAI involvement: the CapCut World Los Angeles site lists OpenAI's Mahak Sharma (Head of Partnerships) and Sam Yam (Head of Creator Product) as speakers
  • Status: CapCut says coming soon; creator claims of desktop early access now and mobile and web in mid-November are not confirmed by CapCut, and pricing is not announced
Read full story
Linked Models & Agents:
🤖 ChatGPT🌐 ByteDance🌐 CapCut🌐 OpenAI
#CapCut#ChatGPT
H
Hugging Face Daily Papers@HuggingFace·
👀349
🔥98

Alibaba Tongyi-MAI Releases OpenGCUA and MAI-Gym: Full Open Stack for Generalist Computer Use Boosts OSWorld-v2 by +19.6 Points and Cuts Steps by 53%

Alibaba's Tongyi-MAI team has open-sourced two foundational frameworks for generalist computer-use agents: OpenGCUA (arXiv:2610.22200) and MAI-Gym (arXiv:2610.20939). By unifying GUI interaction with programmatic code execution and harness-to-model decision transfer, OpenGCUA elevates scores on OSWorld-v2 across all eight tested models—including GPT-6 Astra and Claude Opus 5—by +19.6 points while cutting steps by 53.0%. Meanwhile, MAI-Gym scales online RL to 20,000 parallel instances, training MAI-Gym-9B to 78.4% on MobileWorld and 76.2% on OSWorld-Verified.

Alibaba Tongyi-MAI Releases OpenGCUA and MAI-Gym: Full Open Stack for Generalist Computer Use Boosts OSWorld-v2 by +19.6 Points and Cuts Steps by 53%

Key Takeaways

  • OpenGCUA boosts OSWorld-v2 by +19.6 points: unifies GUI and code execution across 8 frontier models while cutting average steps per task by 53.0%
  • Uncovers 19.4x real-device token efficiency gap: real macOS harness testing shows Qwen3.8-Max uses 19.4x as many reasoning tokens as GPT-6 Astra
  • MAI-Gym scales GUI RL to 20,000 parallel instances: MAI-Gym-9B hits 78.4% on MobileWorld and 76.2% on OSWorld-Verified, transferring mocked-app RL to physical phones (28.8% -> 48.1%)
Read full story
Linked Models & Agents:
⚡ MAI-Gym-9B⚡ GPT-6 Astra⚡ Claude Opus 5⚡ Qwen3.8-Max🤖 OpenGCUA🤖 MAI-Gym🤖 Computer-Use Agents🌐 Alibaba Tongyi-MAI
#OpenGCUA#MAI-Gym#Computer Use#GUI Agents#OSWorld#GPT-6 Astra#Alibaba
ADSponsored
H
Hugging Face Daily Papers@HuggingFace·
👀136
🔥99

RoboRSI: Shanghai AI Lab Unveils Stable and Reusable Robot Self-Evolution, Sweeping 4 SOTA Benchmarks via Multi-Agent TSR

Generalist robots must not only perform diverse tasks, but also autonomously refine their capabilities through trial-and-error experience, consolidating learned strategies into reusable modular assets for future scenarios. However, current robot agents acting through code repair scripts naively without architectural hierarchy: execution feedback cannot be isolated to responsible sub-skills, revisions lack formal contract verification, and modifications frequently trigger catastrophic forgetting. Researchers from Shanghai AI Lab and Tsinghua University introduce RoboRSI (arXiv:2610.12424, code: github.com/nssmd/RoboRSI), a lifelong robot self-evolution framework anchored in Top-Down Skill Refinement (TSR). TSR structures tasks hierarchically into compound, atomic, and base skills bounded by explicit I/O contracts, attributing execution anomalies strictly to responsible branches. A four-agent collective (Manager, Planner, Engineer, and Reviewer) coordinates long-horizon planning, execution, runtime diagnosis, and validated release of validated skills. Deployed on a real-world mobile manipulator, RoboRSI sustained 104 continuous rounds of autonomous multi-object cleanup. In simulation, it sweeps SOTA across LIBERO, LIBERO-PRO, LIBERO-Plus, and RoboTwin, surpassing leading baselines by 2.7 to 11.0 percentage points, with code fully open-sourced.

Key Takeaways

  • Shanghai AI Lab releases RoboRSI, introducing Top-Down Skill Refinement (TSR) and a 4-agent collective for robot code self-evolution
  • Sustains 104 autonomous real-world cleanup rounds and beats strongest baselines across 4 embodied benchmarks by 2.7 to 11.0 points
  • Contract isolation elevates bug attribution accuracy to 95.8%, enabling lifelong accumulation of reusable robot software skills
Read full story
Linked Models & Agents:
⚡ RoboRSI⚡ TSR⚡ LIBERO⚡ RoboTwin🤖 RoboRSI-Manager🤖 RoboRSI-Engineer🤖 RoboRSI-Reviewer🌐 Shanghai AI Lab🌐 Tsinghua University🌐 Hugging Face
#RoboRSI#Robot Self-Evolution#Recursive Self-Improvement#Embodied AI#Shanghai AI Lab#Open Source
C
CrowdStrike Intelligence@CrowdStrike·
👀143
🔥82

CrowdStrike: attacker used open-source AI pentest agent ARTEX plus Claude Code to breach South Korean financial firms

CrowdStrike Intelligence found Claude Code session histories, ARTEX configs and a CLAUDE.md in attacker open directories, showing a likely Chinese-speaking, financially motivated actor used the China-built open-source agentic pentest framework ARTEX (DeepSeek v4.1-flash primary, plus GLM-5.3 and Grok 4.6) to breach loan-inquiry and employee mobile systems at South Korean financial institutions from late September to early October 2026.

Key Takeaways

  • Window: late Sep to early Oct 2026; CrowdStrike attribution is moderate confidence, no named adversary
  • Model stack: DeepSeek v4.1-flash as ARTEX primary backend via likely reseller xcai[.]pro; GLM-5.3 and Grok 4.6 in Claude Code sessions
  • IOCs: 1 actor-controlled IP (38.244.50[.]120) plus 9 proxy IPs, with MITRE ATT&CK mapping
  • Reported impact: Shinhan 25,729 customers, Hana 89, Yegaram ~40,000 (press reports)
  • The upstream Autumn-27/ARTEX GitHub repo now returns 404
Read full story
Linked Models & Agents:
⚡ DeepSeek-V4.1-Flash⚡ GLM-5.3⚡ Grok 4.6🤖 Claude Code🤖 ARTEX🌐 CrowdStrike🌐 Anthropic🌐 DeepSeek
#Security#AI Agent#Claude Code
S
SpaceX@SpaceX·
👀82
🔥88
View on 𝕏 ↗

SpaceX to buy Grain's nationwide 800 MHz spectrum, adding an indoor coverage layer to Starlink Mobile

On 2026-10-08 SpaceX agreed to buy 100% of Grain Management's nationwide 800 MHz portfolio (reported 14 MHz paired), pending FCC approval, terms undisclosed. Low-band adds indoor coverage alongside 2 GHz mid-band and Gen2 satellites, positioning Starlink Mobile as a satellite plus terrestrial carrier. It follows the Oct 6 FCC D2D grant; carrier stocks fell after hours.

SpaceX to buy Grain's nationwide 800 MHz spectrum, adding an indoor coverage layer to Starlink Mobile

Key Takeaways

  • Official: SpaceX update + Grain press release; SpaceX acquires 100% of Grain's nationwide 800 MHz portfolio
  • Size: ~14 MHz paired (reported by Via Satellite); terms undisclosed; subject to FCC approval
  • Role: 800 MHz coverage layer for indoor service, 2 GHz for capacity, plus Gen2 Starlink Mobile satellites
  • Context: Grain got it from T-Mobile in Aug 2026; follows the Oct 6 FCC D2D grant
  • Reuters: after-hours T-Mobile −2.7%, Verizon −3%, AT&T −3.6%; no speed or coverage data
Read full story
Linked Models & Agents:
🌐 spacex🌐 starlink🌐 grain-management🌐 t-mobile
#SpaceX#Starlink Mobile#800 MHz#Spectrum#D2D#Grain Management#FCC
N
Nous Research@NousResearch·
👀108
🔥88
View on 𝕏 ↗

Nous Research raises $90M Series B at $1.5B to take MIT-licensed Hermes Agent into businesses

On Oct 7 Nous Research, maker of the open-source Hermes Agent, confirmed a $90M Series B at a $1.5B valuation led by Robot Ventures, with NVIDIA, Microsoft's M12, Samsung, USV, Y Combinator and Menlo among backers, bringing total funding to $158M. Nous says Hermes Agent has been cloned over 24M times and drives about 2.5% of global token usage (internal estimate). The money funds Hermes for Businesses: a team tier with shared balance and skill library, and an Enterprise edition on customer-controlled infrastructure with SSO and SLAs, plus a mobile app.

Nous Research raises $90M Series B at $1.5B to take MIT-licensed Hermes Agent into businesses

Key Takeaways

  • Round: $90M Series B at $1.5B, led by Robot Ventures; $158M raised in total (TechCrunch)
  • Scale: Hermes Agent cloned 24M+ times, ~2.5% of global token usage per Nous's internal estimate (Nous note)
  • GitHub: NousResearch/hermes-agent has ~252K stars and ~54K forks, MIT, latest release v2026.9.24 (GitHub, checked 2026-10-08)
  • Revenue: ~$36M annualized by mid-September, targeting $100M+ by year-end, per WSJ
  • Business tier: shared balance, per-member caps, team skill library; Enterprise runs on customer infrastructure with SSO and SLAs (Hermes Business)
Read full story
Linked Models & Agents:
🤖 Hermes Agent🌐 nous-research
#Nous Research#Hermes Agent#Series B#Enterprise#MIT
X
X FreezeXFreeze·
👀132
🔥92
View on 𝕏 ↗

FCC clears SpaceX Starlink Mobile next-gen D2D constellation: up to 15,000 VLEO sats, spectrum-lease waiver

On 2026-10-06 the FCC granted-in-part SpaceX’s D2D Constellation (S00735) under DA-26-1078: up to 15,000 sats at 326–335 km, with a §25.125 lease waiver plus PCS G and EchoStar-assigned bands. Milestone: 50% by 2032-10-07. ~150 Mbps/user is a company target, not an FCC measurement.

FCC clears SpaceX Starlink Mobile next-gen D2D constellation: up to 15,000 VLEO sats, spectrum-lease waiver

Key Takeaways

  • Primary: FCC DA-26-1078 (released 2026-10-06) authorizes SpaceX D2D Constellation (S00735) for up to 15,000 NGSO satellites
  • Orbits: nine shells at 326–335 km VLEO; US MSS+SCS, ex-US Direct-to-Cell, plus Ka/V/E/W feeder & TT&C
  • Key waiver: §25.125(a)/(b) — SCS on AWS-3/AWS-H without a terrestrial spectrum lease; also PCS G Block + EchoStar-assigned bands (full ops after Step Two)
  • Milestones: surety bond by 2026-11-04; 50% by 2032-10-07, remainder by 2035-10-07; 2020–2025 MHz and parts of ex-US bands deferred
  • Speeds: no Mbps table in the Order; ~150 Mbps/user peak and ~650 sats/~4 Mbps V1 are company/press figures, not FCC measurements
Read full story
Linked Models & Agents:
🌐 spacex🌐 starlink🌐 t-mobile🌐 echostar
#SpaceX#Starlink Mobile#FCC#DA-26-1078#Direct to device#D2D#VLEO#SCS#EchoStar#T-Mobile#Satellite
T
TesterArmy@tester-army·
👀207
🔥90

TesterArmy's open-source e2e tops GitHub daily trending: natural-language agent steps for web and mobile tests, replayed with zero model calls

e2e (tester-army/e2e), an Apache-2.0 AI end-to-end testing framework, gained 1,430 stars today to top GitHub Trending (3,828 total; 60,933 npm downloads last week). Tests mix natural-language agent.act/agent.assert steps with locator assertions; verified agent steps are recorded and replayed with no model calls until the app changes. v0.17.0 adds Copilot Responses-API models, OpenCode Console sign-in, and a decision-model executor for bounded actions.

TesterArmy's open-source e2e tops GitHub daily trending: natural-language agent steps for web and mobile tests, replayed with zero model calls

Key Takeaways

  • #1 on GitHub daily trending: +1,430 stars today, 3,828 total (Apache-2.0)
  • npm package e2e: 60,933 weekly downloads (Sep 28–Oct 4); latest 0.17.0 released Oct 4
  • Record & replay: verified agent steps rerun with zero model calls until the app changes
  • v0.16.0 cut install footprint from 117 to 29 packages (~36MB to ~31MB)
  • 7 packages: Playwright (Chromium/Firefox/WebKit), iOS/Android, PR reporter, hosted browsers/simulators, decision-model executor
Read full story
Linked Models & Agents:
🤖 Claude Code🤖 Codex🤖 GitHub Copilot🤖 OpenCode🌐 tester-army
#E2e#AI Testing#E2E Testing#Playwright#Mobile Testing#GitHub Trending#Decision Models#MCP
ADSponsored
S
Stably AI@stablyai·
👀140
🔥97

Orca (stablyai) leads open-source ADEs: ★84,136 MIT; parallel worktrees for Claude Code/Codex/Pi; Android companion 0.0.52

stablyai/orca positions itself as an Agent Development Environment (ADE): parallel CLI coding agents (Claude Code, Codex, OpenCode, Pi, …) each in an isolated git worktree, with desktop, mobile companion, and remote hosts. Verified now: ★84,136 / 5,424 forks; MIT; desktop v1.4.219 (2026-10-02); Android mobile-android-v0.0.52 (2026-10-03). Site onOrca.dev. No official SWE leaderboard—no invented scores.

Orca (stablyai) leads open-source ADEs: ★84,136 MIT; parallel worktrees for Claude Code/Codex/Pi; Android companion 0.0.52

Key Takeaways

  • Repo stablyai/orca (MIT): ★84,136 / 5,424 forks via GitHub API; site onOrca.dev
  • Desktop v1.4.219 published 2026-10-02T20:59:25Z; Android mobile-android-v0.0.52 on 2026-10-03T00:39:14Z; iOS via App Store
  • Pitch: parallel worktrees, Ghostty-class terminal, embedded Chromium design mode, SSH remotes, BYO agent subscriptions
  • Mobile companion is beta: monitor/reply/SCM/account switch while desktop remains source of truth
  • Install: onorca.dev/download; docs: onorca.dev/docs
Read full story
Linked Models & Agents:
🤖 Claude Code🤖 Codex🤖 OpenCode🤖 Pi🤖 oh-my-pi🤖 Orca🌐 Stably AI
#Orca#Ade#Agent IDE#Parallel agents#Worktrees#Claude code#Codex#Open source
O
OpenAI@OpenAI·
👀126
🔥98

OpenAI Codex Cloud reusable environments: keep tasks running after you close the laptop; one project setup across desktop, web, and mobile

At DevDay (2026-09-29) OpenAI shipped reusable Codex Cloud environments: publish a project setup (repos, deps, tools, network secrets), then each task runs in its own VM workspace and can continue while your laptop sleeps. Docs: learn.chatgpt.com/docs/cloud and Help Center. Rolling out to Plus/Pro and workspace plans; saved VM state recoverable ~7 days by default. No invented SWE scores.

OpenAI Codex Cloud reusable environments: keep tasks running after you close the laptop; one project setup across desktop, web, and mobile

Key Takeaways

  • Official: learn.chatgpt.com/docs/cloud; Help: Using Codex Cloud (recently updated)
  • Flow: create/publish environment on web/desktop → Codex inspects GitHub repos & installs deps → start tasks from any supported surface including mobile; each task is isolated
  • SiliconANGLE (Sep 29): Plus VMs are half the CPU/RAM of Pro/Business/Enterprise; no GitLab/self-hosted GHES yet; no computer/browser use in cloud environments
  • Saved VM state recoverable ~7 days after last start/resume by default; Enterprise sharing covers setup, not other people’s tasks
  • Legacy Code Review / Linear / GitHub integrations stay on Codex Cloud (Legacy); migration is opt-in
Read full story
Linked Models & Agents:
⚡ GPT-6 Sol⚡ GPT-6.1 Sol🤖 Codex🤖 Codex Cloud🌐 OpenAI
#OpenAI#Codex#Codex cloud#Cloud agents#Devday#Agent harness
T
T3 Code / pingdotgg@t3dotgg·
👀1.3k
🔥97

T3 Code Orchestrator V2 first nightly: cross-provider delegate_task, durable server queue; Pi 1.0 & OpenCode 2

pingdotgg/t3code shipped nightly v0.0.46-nightly.20261003.2610 at 2026-10-03T01:10:51Z — the first Orchestrator V2 build. It rebuilds turn lifecycle, queues/resume, subagent lineage, cross-provider threads, and history. Headline: delegate_task (spawn child agents on any provider/model and await results — the recommended multi-harness path, e.g. Claude plans / Codex implements), plus T3 Code MCP, ACP Registry, Cursor official SDK, restart-durable server queue, usage-limit auto-resume, scheduled tasks. At ingest: 24355★. Caveats: one-way DB copy from V1; mobile needs V2 beta; OpenCode 2.0.18+.

Key Takeaways

  • Release v0.0.46-nightly.20261003.2610 at 2026-10-03T01:10:51Z; site t3.codes
  • At ingest: 24355★; migration notes in issue #14871
  • V2: delegate_task, T3 Code MCP, ACP Registry, Cursor SDK, durable server queue, usage-limit auto-resume, scheduled tasks
  • New: Pi (incl. 1.0) + OpenCode 2 (≥2.0.18); mins Codex 0.159+ / Claude Code 2.1.280+ / Grok 1.0.13+ / Pi 0.80.5+
  • Caveats: one-way V1→V2 DB copy; V2 clients only on mobile beta; prefer delegate_task over lossy mid-thread provider switches
Read full story
Linked Models & Agents:
🤖 t3-code🤖 Claude Code (Anthropic)🤖 codex🤖 opencode🤖 pi🤖 cursor🤖 grok🤖 Google Antigravity (AGY)🌐 pingdotgg🌐 t3
#T3 Code#Orchestrator V2#delegate_task#Pi#OpenCode 2#Claude Code#Codex#Cursor SDK#ACP Registry#agent orchestration#Pingdotgg
A
Alibaba Qwen@Alibaba_Qwen·
👀89
🔥95

Alibaba Tongyi Unveils Qwen-Planner-Agent: A Closed-Loop AI-for-AI Architecture for Real-World Mobile Planning Agents

Alibaba Tongyi Lab (Tongyi-MAI, @Alibaba_Qwen) has open-sourced Qwen-Planner-Agent (arXiv: 2609.29892, Project: tongyi-mai.github.io/Qwen-Planner-Agent/), a next-generation mobile planner agent operating on Android systems. Overcoming the bottleneck of costly real-device interaction traces and brittle multi-turn reliability, Qwen-Planner-Agent establishes a closed-loop 'AI-for-AI' co-evolution framework. Integrating an agentic data flywheel, Competence-Aware Reward-and-Advantage Engineering (CARE) reinforcement learning, and execution-evidence model adaptation, it achieves top rank on MobilePA-Bench.

Alibaba Tongyi Unveils Qwen-Planner-Agent: A Closed-Loop AI-for-AI Architecture for Real-World Mobile Planning Agents

Key Takeaways

  • Pioneers a closed-loop AI-for-AI mobile agent lifecycle connecting automated trajectory synthesis, RL, and deployment.
  • Introduces Competence-Aware Reward-and-Advantage Engineering (CARE) to curtail token reasoning costs while boosting tool precision.
  • Orchestrates dynamic model-harness co-evolution, harmonizing runtime memory, skills, and hierarchical sub-agents.
  • Secures top overall performance on the MobilePA-Bench suite, outperforming prior proprietary and open mobile agents.
  • Interactive project website, evaluation suite, and behavioral action traces released openly on GitHub.
Read full story
Linked Models & Agents:
⚡ Qwen 2.5 72B⚡ Qwen Planner🤖 mobile-planner-agent🤖 qwen-agent🌐 alibaba🌐 Qwen (通义千问)
#Qwen#Mobile Agent#AI-for-AI#Alibaba#Android#Reinforcement Learning#Hugging Face
A
Alibaba Qwen@Alibaba_Qwen·
👀67
🔥91
View on 𝕏 ↗

Qwen Intelligence launches three mobile agents and opens MobileWorld benchmark suite

Alibaba Qwen (@Alibaba_Qwen) launched Qwen Intelligence with three SOTA mobile agents: Mobile Planner (plans/decomposes/orchestrates; #1 on MobilePA-Bench and related boards), Mobile-Use (API-first with GUI fallback; MobileWorld 82.1, MobileWorld-Real 92.2, ~90% end-to-end success), and Mobile Creative (~3s image generation). The team also opened MobilePA-Bench, MobileWorld, MobileWorld-Real, and MobileWorld-Safety covering planning, cross-app execution, on-device performance, and safety.

Qwen Intelligence launches three mobile agents and opens MobileWorld benchmark suite

Key Takeaways

  • Ships Planner, Use, and Creative mobile agents for planning, execution, and creation.
  • Mobile-Use reports MobileWorld 82.1, MobileWorld-Real 92.2, ~90% end-to-end success.
  • Opens MobilePA-Bench and MobileWorld suite with public leaderboards.
Read full story
Linked Models & Agents:
🌐 Qwen (通义千问)
#Qwen Intelligence#Mobile Planner#Mobile-Use#MobileWorld#MobilePA-Bench#Agents