AI Coding Live News

arXiv paper 2611.03233 by Yuqi Jia, Yunjie Tian and five co-authors introduces Axion 1.0, an agent foundation model that is open beyond its weights. It uses just two lightweight SFT stages plus reinforcement learning, with no dedicated mid-training, DPO or on-policy distillation, and about 18K SFT trajectories in total. Training code is hosted under the bytedance GitHub organization, and the training data and an Axion 1.0-35B reproduction checkpoint (Qwen3.6-35B-A3B base, 35B total / 3B active, Apache 2.0) are on Hugging Face; weights for the paper's 122B model are listed as coming soon.

Zoom

On Oct 29 Mistral released an improved Mistral Large 4 (Le Chonk) with open weights on Hugging Face (plus an NVFP4 quantized checkpoint), served on its API as mistral-large-4. After about three more weeks of reinforcement learning since the early-October preview, Mistral reports 19.7% on FrontierCode 2.0, Terminal-Bench 4.0 up from 28% to 41%, and new low/medium/high reasoning modes. The license is a modified MIT that allows commercial use, but running a model-as-a-service business needs a separate commercial license.

Zoom

Microsoft Research (MSRA) researchers published and open-sourced WildAWM (arXiv:2610.26828, GitHub: MSR-Orchard/WildAWM), a generalist agent world model designed for open-ended 'in the wild' digital environments. Traditional computer-use agents rely on slow, brittle, and expensive live web/OS sandboxes for training and evaluation. WildAWM establishes a scalable multimodal world model that accurately predicts visual screen transitions and DOM mutations conditioned on agent actions (click, type, scroll). By replacing live execution environments with a high-fidelity neural simulator, WildAWM unlocks safe, accelerated offline reinforcement learning for GUI agents.

Zoom

On Oct 19 (UTC) fal released FLUX 3 Max, a video model built by fal Research with Black Forest Labs through post-training, reinforcement learning and inference optimization on top of the FLUX 3 foundation model. It handles text-to-video, image-to-video and keyframes, up to 20 seconds, at 720p or 1080p, with audio on by default. On Artificial Analysis's preliminary image-to-video arena it scores 1,139 Elo, level with Seedance 2.5 and within the confidence interval of leader MiniMax H3 (1,141), and fal says a 10-second clip takes about 12.45 seconds. A 75% launch discount runs until Nov 7, putting 720p at $0.0425 per second.

Zoom

Researchers from the Technical University of Munich (TUM) introduced TabWM (Tabular World Model) and the WorldRel benchmark generator in arXiv:2610.16763. Moving beyond traditional relational learning that only performs static prediction on database rows, TabWM formulates operational database environments as relational world models capable of simulating state transitions and downstream consequences under arbitrary business actions, unlocking offline reinforcement learning for enterprise decision agents.

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

Meta officially disclosed its gigawatt-scale AI supercluster Prometheus in New Albany, Ohio, housing hundreds of thousands of frontier GPUs with 85%+ pretraining goodput and 90%+ in reinforcement learning. Powered by this infrastructure, Meta's latest coding flagship Muse Wonder Full surged to #6 globally on LMSYS Code Arena: WebDev with 1726 Elo points (surpassing Claude Sonnet 5.5 and Gemini 4 Argon), lifting Meta to the #3 AI research lab worldwide.

Zoom

Meta's engineering blog on October 19 gave the first detailed look at Prometheus, the New Albany, Ohio supercluster that trained the Muse family, including Muse Wonder. Phase one is complete with hundreds of thousands of GPUs, and the full build targets about 1 million. Muse Wonder training reached more than 85% goodput in pretraining and more than 90% in reinforcement learning, with a mean time between interruptions of about 47K GPU hours, since raised above 54K by firmware fixes. It runs GB200 NVL72 and GB300 NVL72 platforms, with Vera Rubin NVL72 arriving soon.

Zoom

Modal said in an October 19 blog post that it will add NVIDIA's Arm-based Vera CPU to power Modal Sandboxes, its first step beyond an all-x86 fleet. Using Agentless Agent Bench, a 50-task suite built from Terminal-Bench, Modal measured up to 2x the task throughput of a comparable x86 GNR machine under heavy concurrency, with per-task latency equal or lower (vendor figures). On an idle host running tasks serially, Vera's edge was small. The capacity targets background coding agents and reinforcement learning rollouts.

Zoom

Researchers from Stanford University and UC Berkeley introduced Librarian Agents (arXiv:2610.22273). To overcome the bottleneck of reactive RAG methods struggling with complex cross-document reasoning at query time, the framework uses reinforcement learning to train LLMs to perform anticipatory directed curation on messy long-context workspaces into structured synthetic filesystems. On BrowseComp+, it hits 55.86% accuracy while reducing navigation token consumption by 33.8% to 51%.

Zoom

Addressing rollout homogenization and zero-variance advantage collapse in group-relative reinforcement learning (GRPO), SERO (arXiv:2610.19397) restores learner-visited states to execute multi-step oracle continuations with policy-reachability weighting—boosting 7B ALFWorld OOD success by +11.20 points to 87.50%—while UNSW's EDEN (arXiv:2610.16105) appends a single anchored Gaussian-perturbed embedding position to a fraction of rollouts, lifting Qwen2.5-Math-7B AIME 2025 Pass@256 by +13.33 points (to 66.67%) without increasing rollout budgets.

Zoom

Standard agentic reinforcement learning assumes single-session trajectories with continuously accumulated context, clashing with production agent techniques like context compaction and subagent forking. Researchers introduce Mosaic (arXiv:2610.22174), a critic-free hierarchical optimization framework for Multi-Session Agentic RL. By incorporating session-usage signals at the trajectory level and shaping per-session advantages by marginal contribution, Mosaic outperforms trajectory-level broadcasting on BrowseComp across both compaction and subagent scenarios while using fewer sessions.

Zoom