AKV: Cache Engineering for Agents A new serving system that lets LLM agents directly manage their KV cache — dropping unused history and repositioning retained keys without rewriting or re-prefilling. Reduces average cost by 27.7% while improving task accuracy by 1.7 points. https://t.co/AjCQF5MVcT

1/7 🥥 New speculative decoding method! Introducing DCOCO: Contextual Correction of Parallel Drafts. Parallel drafters are fast, but lose context between predicted tokens. DCOCO restores it without giving up parallelism. Up to 6.6× faster than vanilla decoding. 🧵 https://t.co/gdgRcytlxD

Great paper from NVIDIA sharing an open midtraining recipe for agentic coding. NVIDIA kept SFT identical and added one midtraining stage. SWE-bench Multilingual went from 55.8 to 62.8 on Nemotron 3.5 Lightning. The stage sits between pretraining and post-training. It trains at 256K context on 500B tokens of natural software-engineering data, such as packed repositories, pull requests, commit histories and build logs, plus a small share of agent traces. On the same model, SWE-bench Verified rose from 60.7 to 64.5 and SWE-bench Pro from 32.0 to 35.5. On the larger Nemotron 3.5 Super, DeepSWE rose from 11.7 to 15.7. They also explain how they evaluated the recipe. Base-model proxy metrics did not predict post-training results, so every data choice was scored with short fixed SFT runs. If you train coding agents, the recipe and its ablations are published. https://t.co/SJ7JHdd1HY Chat with Paper: https://t.co/eCK8iUNIi0

I put Opus 5.5 and Kimi K3.1 Pro head-to-head with the exact same coding challenge. Build "Lantern Hour" in a single HTML file: 4 art styles, a full day/night cycle, dynamic lighting and shadows, and interactive controls. Canvas 2D only. No libraries or external assets. Which one did better?

Our quadruped HOUND just landed the 🥳cover🥳 of #ScienceRobotics 🐕🦿 @SciRobotics Trained only in sim. One policy. Onboard sensors only🖥️. Trotting, bounding, stairs, gaps, fallen logs: all in the wild.🌳 Paper: https://t.co/0UdKFoFDIU Arxiv: https://t.co/p5aoy76KVO Thread on how we built it 🧵👇 1/N

A steering-first neuron explorer for Qwen3.5-4B, open source on GitHub. Per the creator, a sweep pushes every MLP neuron in a layer up and down on a few prompts and keeps every rollout. The explorer then shows the results as a 3D map of neurons, with a ranked list, per-neuron pages and an embeddings view. Why it matters: seeing what each neuron does to a model's output makes interpretability work easier to inspect and reproduce. https://t.co/k2YKAllyIy Credit: @_lyraaaa_

"In zero-shot settings, preference following accuracy falls below 10% at merely 10 turns (~3k tokens) across most evaluated models. "Even with advanced prompting and retrieval methods, preference following still deteriorates in long-context conversations." 8/

Inverse IFEval establishes a benchmark for ability to follow out-of-distribution instructions, including inherently flawed questions, code without comments, not using bulleted lists, changing instructions within an interaction, & more. 2/

Cool eval. Simply ask an LLM “Land or Water?” and give it a latitude and longitude coordinate as text. Ask 16,200 times, plot as image. The models know. From compressing the internet.

Introducing Kimi K3.1 Pro: our most capable 3T-class open-weight model. 🔹 1M-token context, 2.8T total / 104B active params (MoE), Multimodal. 🔹 Full-project coding: games in Unreal, Unity & Godot. 🔹 Excels at parametric 3D modeling in Blender & CAD. 🔹 More reliable at finance work: Accurate modeling with hallucination down by 65%. 🔹 Matching the strongest proprietary models across coding, agentic and knowledge benchmarks. Kimi K3.1 Pro and K3.1 Pro Highspeed (2–3× faster) are now live on https://t.co/85jA71X9gw, Kimi Work, Kimi Code, and the Kimi API. Open weights by Nov 4, 2026. 🔗 API: https://t.co/XCrgjXAqMw 🔗 Tech blog: https://t.co/5iPP0MBej6