AI Coding Live News

The Ornith AI team officially released Ornith-1.5-122B under the permissive MIT license, a 122-billion parameter mixture-of-experts (MoE) reasoning model optimized to execute on a single GPU node (such as a single DGX). The model is immediately available across vLLM (0.19.1+), SGLang (0.5.9+), Hugging Face, and Ollama (ornith-1.5:122b) with native FP8, GGUF, and MLX quantization. Across independent agentic evaluations in the OpenHands harness, Ornith-1.5-122B registered 84.5 on SWE-bench Verified, 76.9 on SWE-bench Pro (surpassing Qwen3.8-Flash-Next's 43.9 by 33 points), 81.2 on TerminalBench 2.1, and 74.6 on MCP-Atlas.

Zoom

Researchers from Amazon Web Services (AWS) and UIUC unveiled Lean4AgenticRL (arXiv:2610.22448). Tackling the limitations of conventional agentic reinforcement learning relying on sparse, binary outcome rewards, the framework grounds multi-level process rewards within a formal Lean4 verification schema. Utilizing workflow-stage-normalized GRPO, the resulting LAR-27B model reaches 77.3% on TerminalBench-2.1, outperforming base models by 9.89% and surpassing comparable open models by 5.07%.

Zoom

Terminal agents execute stochastic model outputs directly in real bash environments, where an erroneous command (e.g., misconfigured dependency install, file deletion) irreversibly corrupts system state and derails downstream progress. Researchers introduce Mid-Harness, a paradigm that allocates test-time compute precisely at the boundary between model generation and the evaluation harness. By sampling and verifying candidate actions before sending them to the terminal—rather than expensively generating multiple full rollout trajectories—Mid-Harness elevates Pass@1 on TerminalBench-Lite from 50.00% to 68.03% under action scaling, achieving vastly higher reliability at substantially lower token cost.

Zoom

On 3 Oct 2026, Aleph Alpha released open-weight Kolibri-1 (HF, Apache-2.0): 78B MoE / ~3.46B active, bilingual DE/EN, 262k native context (1M extrapolated), reasoning effort + tools. Official card: LiveCodeBench v6 85.9, SWE-Bench Verified 66.4, TerminalBench 2.1 27.7. Serve via aleph-alpha-inference + vLLM.

Zoom

Terminal agents operate through stochastic model generations, but a single errant command can irreversibly degrade sandbox environments. Mid-Harness introduces test-time compute scaling at the boundary between model and harness. By sampling and verifying candidate actions before terminal dispatch without modifying the underlying generator or harness, Mid-Harness boosts Pass@1 on TerminalBench-Lite from 50.00% to 68.03% under a GPT-5.6 Sol verifier, outperforming whole-trajectory scaling at lower token expenditure.

Zoom

Meta released Muse Glimmer in August, a 30B open-weight local agent model under Apache 2.0 whose quantized weights fit under 20 GB for consumer Macs and single-GPU PCs. On October 19 Meta published its technical report: a ~29.6B dense design distilled from Muse Spark that, by Meta's figures, beats Gemma4-31B and Qwen3.6-27B on tool-use and agent benchmarks such as MCPAtlas, tau3-Banking and SWE-Bench Pro, while still trailing Qwen3.6-27B on SWE-Bench Verified, TerminalBench 2.1 and OSWorld.

Zoom