AI Coding Live News

On October 30, Microsoft's Mage team released Mage-VL-Cowork on Hugging Face under Apache-2.0: a 4B multimodal computer-use agent in which a single model decides at every step whether to act through screenshots and GUI clicks (computer_use) or through bash and Python in a terminal, with no external orchestrator. Microsoft reports a two-run average of 66.0% on OSWorld-Verified (361 tasks, 50-step budget), above Qwen3.6-27B at 63.9% but below the 9B SCALECUA-Qwen3.5-9B at 68.7%.

Zoom

On October 31, Chris Tate of Vercel Labs, creator of agent-browser, announced agent-desktop on X as "agent-browser, for your whole computer". It is an Apache-2.0 Rust CLI and C library that reads a desktop app's OS accessibility tree and returns every actionable element as a JSON ref; the agent clicks or types on a ref and snapshots again to verify, with no pixel matching, headless by default. Version 1.0.0 shipped on October 27 and added Linux support; the current npm release is 1.0.2.

Zoom

On Oct 26 Tencent Hunyuan (Tencent Hy) open-sourced Hy-SimulMT, a real-time simultaneous interpreting model for bidirectional Chinese-English speech-to-speech translation. It translates while the speaker talks, outputs both translated text and speech, and can clone the speaker's voice in real time. Six checkpoints landed on Hugging Face (30B-A3B translation-only and source-plus-translation Interleave variants, each in BF16, FP8 and GGUF), with the model card listing Apache-2.0; GitHub ships the SimulInfer serving stack and SimulTrain training tools. Vendor-reported: about 3s StreamLAAL on RealSI long-form audio, the lowest among compared systems.

Zoom

Alibaba Tongyi Labs (Tongyi-MAI) has published and open-sourced OpenGCUA (arXiv:2610.22200), establishing a fully open software stack for Generalist Computer Use Agents. Moving beyond brittle single-click GUI paradigms, OpenGCUA introduces a 'Code-Execution-as-Action' framework combining visual screen perception, accessibility trees, bash scripts, and Playwright APIs into unified programmatic execution blocks. Evaluated across eight frontier models on OSWorld-v2, OpenGCUA boosted mean scores by +19.6 points while cutting task steps by 53.0%, releasing an Apache-2.0 macOS menu-bar harness and Cross-Device SDK.

Zoom

On Oct 16 Tencent Hunyuan open-sourced Hy Memory 2.0 in three layers: the Apache-2.0 memory-writer model Hy-Memory-30B-A3B (~3B active, HF weights plus arXiv report), a Python SDK covering Chat, Working and Coding scenes (PyPI hy-memory 2.0.x), and local-first MemHub (CLI + macOS, preview). Per Tencent, swapping it in as the writer across Mem0, MemOS, Hy-Memory and held-out EverMemOS yields a 55.49 average vs 54.62 for Claude Opus 5, measured on fixed 20% subsamples; it still trails Opus 5 on several individual metrics.

Zoom

On 2026-10-15, MBZUAI’s Institute of Foundation Models (IFM) and Inception42 released Jais 3—the first language adaptation of the open K2 Horizon fleet. Six open-weight sizes run from a 0.9B dense phone model to a 375B-A23B sparse MoE (≈23B active), plus Jais Speech for Arabic ASR. Models share one training recipe and agent stack, with up to 512K context (128K on 0.9B), Apache-2.0 weights and stage checkpoints on Hugging Face, and day-0 vLLM support.

Zoom

An LLM agent's practical capabilities depend as much on its execution harness as on its underlying model. Deploying recursive self-improvement (RSI) in open worlds is hampered by the absence of ground-truth verifiers and poor generalization across novel domains. Google Cloud AI Research introduced Harness², a two-level recursive framework: task-level recursion refines task-specific harnesses via a contrastive Propose-Probe-Compose step without ground-truth verifiers, while harnessing-level recursion extracts continual adaptation experience. Harness² delivers up to +11.8% on LAB, +11.5 points on WorkBuddy-Bench, and +4.5 points on JobBench on GLM-5 and Gemini 3.5 Flash. Code is open-sourced on GitHub under Apache-2.0 (google-research/harness2), supporting OpenCode and Codex executors plus JobBench, LAB and WorkBuddy-Bench.

Zoom

On Oct 13 Physical Intelligence opened a beta of the Pi API: teams upload robot demonstrations, fine-tune Pi's latest robot foundation model on Pi-managed compute, and serve the result to their robots through a hosted inference gateway. Showcased deployments range from an operator-less wheel loader to strawberry harvesting and server assembly; early-access customer Almond got a deburring policy for its Axol dual-arm robot after four days of iteration. Access is by application and pricing/API parameters are not published; self-hosters can still use the Apache-2.0 openpi repo (π0/π0.5 base checkpoints).

Zoom

On 2026-10-12 LightOn AI released ColGrep-Agent-2B (fine-tuned from MiniCPM5-2B, Apache-2.0): a local 2B code-localization agent that searches with ColGrep multi-vector retrieval plus a read-only terminal, then returns file paths and line ranges to a frontier coding agent. On 52 code-search questions across 13 unseen repos (624 Claude Code / Sonnet 5.5 sessions), delegating search cut API tokens ~34.3% and cache-aware cost ~40% vs grep, with 80.8% vs 83.3% accuracy (not statistically significant). On SWE-bench Lite localization it posted 19.92 line F1—best among models evaluated in the same ColGrep harness, including several >10× larger. Ships brew/cargo/GGUF installers and hooks for Claude Code, Codex, and OpenCode.

Zoom

On 2026-10-12 OpenBMB released MiniCPM-V 4.7, an Apache-2.0 open multimodal family with a 35B-A3B variant (the series' first MoE) and a 1B variant. Its Lookahead Expert Scheduling (LES) prefetches experts across layers and, combined with layer-wise mixed-precision quantization and DSpark speculative sampling, lifts SSD-offloaded decoding on an iPad Pro M4 (16GB) from 2.97 to 17.39 tokens/s (5.86x), per OpenBMB. Weights are on Hugging Face, ModelScope and Ollama, with vLLM, SGLang, llama.cpp and iOS/Android/HarmonyOS support.

Zoom

On Oct 11 the vLLM Semantic Router (vllm-sr) team released the Decision 3.0 family (d3, d3-flash, d3-mini, d3-nano, d3-lite, d3-edge) on Hugging Face under Apache-2.0. Built on Qwen3.5/3.8, the models take text, images and video and return probabilities for choice, yes/no and score questions in one call without generating text. Vendor-reported: the 27B d3 scores 64.7 on Jev Decision Index 0.3.1, ahead of Perplexity Decider v1.1 (62.8) and Decision 2.0 (55.9), with a 55 ms median text latency on one AMD MI325X.

Zoom

Perplexity released pplx-decider-v1.1-27b (Apache-2.0, fine-tuned from Qwen3.8-27B) on Hugging Face. It returns typed, probability-calibrated answers instead of text. Overall Decision Index is 61.56 vs 56.4 for v1 and 57.9 for Jev, and it is served via the Perplexity Decisions API.

Zoom

FeSens/openTPU (Apache-2.0) hit the Hacker News front page (250+ points, 300+ comments). Reusing the AI-driven method from auto-arch-tournament (AI-designed RISC-V cores), the author had AI agents iterate on an inference accelerator; one repo holds SystemVerilog RTL, the ISA, a bit-exact simulator, a kernel language/compiler and a profiler. On a Kintex-7 xc7k480t PCIe card it runs Qwen3, Qwen3.5, Gemma 4, Phi-4-mini and others with real weights, token-for-token identical to the simulator; LFM2.5-230M decodes at 85.8 tok/s in 4-bit and Qwen3.5-35B-A3B reaches 3.95 tok/s with host-streamed experts.

Zoom

On 2026-10-06 OpenAI published Sharing AI progress in mathematics and released openai/math (Apache-2.0): 722 manuscripts in 372 result families produced by an unreleased internal frontier model, drawn from an evaluation of ~4,000 open problems at an average of ~3 hours of ChatGPT Pro thinking compute per result, with 10 abridged reasoning summaries and Lean formalizations for many results. OpenAI notes unformalized results may have issues; none are peer reviewed yet.

Zoom