Tooling32d ago
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.
Benchmark13d ago
Artificial Analysis launches AA-Robotics v0.1: coding agents drive a real robot arm, GPT-6 Astra leads at 69.4
Artificial Analysis released AA-Robotics v0.1 on 2026-10-14, a research preview in which frontier models running inside coding-agent harnesses (Codex, Claude Code, Antigravity) control a 6-axis robot arm over an HTTP API across eight tabletop tasks. GPT-6 Astra scores 69.4, ahead of GPT-6.1 Sol (64.6), Gemini 4 Argon (55.3), Claude Opus 5.5 (48.8) and Claude Fable 5.1 (46.3). Models take about 30 minutes per task versus roughly 20 seconds for a human.
Tooling36d ago
Beacon open-sources cross-harness self-improving memory: Jev scores runs into reusable skills
@_avichawla covered Beacon by Asymptote Labs (github.com/Asymptote-Labs/agent-beacon): a cross-harness memory layer for Claude Code, Codex, Cursor, OpenCode, and 20+ more. It captures full session history, uses Jev to score evidence/reuse/human-correction signal, and promotes high-signal workflows into reusable skills so lessons transfer across harnesses.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.