Knowledge catalogue
arXiv:2609.34268v1 Announce Type: new Abstract: Large language models (LLMs) are now the default cognitive core of embodied household agents, yet the plans they emit are rarely checked against a groun
arXiv:2609.33311v1 Announce Type: cross Abstract: Humanoid robots are increasingly expected to serve as embodied social agents that communicate naturally with humans through face-to-face interaction.
arXiv:2609.33462v1 Announce Type: new Abstract: Omnidirectional or 360 cameras provide embodied AI agents with a holistic, wide field-of-view (FoV) view of their surroundings, motivating the use of Mu
TL;DR: I'm a solo dev who wanted a simple, private way to have local LLMs watch my screen and do simple logging/notifying. After a year of building, I released v3.0.0 and my mom was able to use it for
Together is #1 on @OpenRouter token share across top open coding models, today: 🥇 @Zai_org GLM 5.3 Flash: 29.2% 🥇 @deepseek_ai V4.1 Flash: 25.6% 🥇 @Kimi_Moonshot Kimi K3: 18.9% Running coding agents o
arXiv:2609.32303v1 Announce Type: cross Abstract: Domain experts trained from a shared checkpoint can be merged into one model through on-policy distillation (OPD), where they act as teachers supervis
arXiv:2609.33464v1 Announce Type: new Abstract: World models learn internal representations of environment dynamics to predict future states, enabling agents to optimize action plans without physical
arXiv:2609.34457v1 Announce Type: new Abstract: Transformer-based models are widely used for reasoning, coding, and multimodal agentic tasks. To provide formal assurance of desirable behaviors, such a
Anthropic's discovery of array-associated reverse transcriptases? Turns out it was already done by a Danish scientist. He used Claude for administrative tasks, but not in an agentic manner for the dis
arXiv:2609.31133v1 Announce Type: new Abstract: High-fidelity atomistic evolution over long timescales requires more than observing the current crystal configuration. Instantaneous atomistic snapshots
Yesterday I shared our open-source Clash Royale simulator and its recurrent PPO agent here. A training loop is easier to understand when you can watch it, so we put a small interactive version online:
arXiv:2609.31029v1 Announce Type: new Abstract: Reasoning systems usually treat premise use as a question of relevance: if a fact is available and useful, it may be selected for inference. Authorizati
arXiv:2605.05856v2 Announce Type: replace Abstract: Measuring learning progress is at the core of curiosity-driven exploration, which rewards an agent for going where its model is still learning. Howe
xAI's Grok 4.7 is now available on Amazon Bedrock: a frontier model for coding, long-running agents, and knowledge work. It offers a 500K token context window and four configurable reasoning effort le
arXiv:2511.06157v3 Announce Type: replace-cross Abstract: Discovering high performing model architectures for wearables-based Human Activity Recognition (HAR) applications is challenging. The astonish
arXiv:2609.31511v1 Announce Type: new Abstract: We present Muslim, a production Arabic voice AI platform serving grounded, sourced Islamic knowledge to real users. Beyond a real-time voice pipeline (N
Model Developer: NVIDIA Corporation Model Development: Fine-tuned from NVIDIA-Nemotron-3-Ultra-550B-A55B What is Nemotron? NVIDIA Nemotron™ is a family of open models with open weights, training data,
ok i think i finally figured out why alignment has gone basically nowhere after 15 years and several billion dollars. the problem is hard sure. but have you met the people in charge of it 1) the leade
arXiv:2609.31078v1 Announce Type: new Abstract: Debates amongst agents driven by large language models (LLMs) have demonstrated vast potential in various applications, but when these interactions incl
arXiv:2609.31016v1 Announce Type: new Abstract: Generalization in Reinforcement Learning (RL) refers to the ability to execute close-to-optimal policies in unseen tasks after the agent has been traine
Hi everyone :) The amazing Swift finetunes of Qwen3.8 27B generate much fewer tokens at mostly similar benchmark performance to the original model, while repos like HyperQwen (formerly syv-ai/qwen38-2
arXiv:2609.30334v1 Announce Type: cross Abstract: AI development agents are increasingly used to support and partially automate software architecture tasks. To explore how practitioners perceive this
I’m having a hard time finding out which one gives you fastest speed, maximum context with best possible quality. I can run unsloth qwen3.8 27b iq4_xs with 65k q8 kv, context without MTP and vision of
Tom Wilson / Financial Times: Google Threat Intelligence Group finds dark web marketplaces selling access to AI models, including from Anthropic, Google, and OpenAI, at up to 97% discounts — Security
OpenAI: OpenAI says it paused training, evaluation, and inference with tool-use of its most capable models after a model bypassed internet restrictions during training — Summary — An agent attempting
I know there is nothing new with what I am saying but I recently started with hermes agent (it’s been a while I wanted to but did not have the time). Qwen3.8fn 6bpw exl3 (from turboderp) on a 6x3090 (
On my M5 Pro 64GB I can comfortably work in an agentic setup with the Qwen3.8 27B model in good quality (Unsloth UD-Q4_K_XL) at a decent speed of 50 t/s. Splash combines optimized kernels, excellent s
arXiv:2408.10349v2 Announce Type: replace-cross Abstract: Continual learning (CL) agents incrementally learn from sequentially arriving data and adapt to the dynamic, ever-changing nature of real-worl
arXiv:2609.28613v1 Announce Type: cross Abstract: Most studies of prompt injection focus on generative agents, leaving their effects on models with schema-defined outputs unclear. We examine these eff
HUGGING FACE CEO TELLS THE UN HOW OPEN SOURCE AI HELPED THEM DEFEND AGAINST OPENAI'S AI ATTACK, AND WHY THE WORLD NEEDS OPEN SOURCE AI MORE THAN EVER. Hugging Face is the company OpenAI's AI agents ha
I've been playing around with various models on the M5 Ultra 256GB 80-core Mac Studio. These are the results over many rounds of agentic inferencing. I'm happy with the performance. Glad to have the l
Every organization I talk to wants to be “AI-ready,” but few want to discuss what that entails. It’s rarely a new model or agent. More often, it’s the unglamorous work of ripping out a decade’s worth
arXiv:2609.28854v1 Announce Type: cross Abstract: Language-model agents increasingly answer questions over customer-relationship management (CRM) records, such as whether to qualify a sales lead. We i
arXiv:2609.28921v1 Announce Type: new Abstract: Protein modification requires navigating an immense sequence space, yet wet-lab validation remains low-throughput and costly. Although computational par
arXiv:2609.28737v1 Announce Type: cross Abstract: Biological agents do not learn under conditions of unlimited computation. For humans, learning and choice are shaped by constraints on perception, att
arXiv:2609.29421v1 Announce Type: cross Abstract: Rufus-Air is an open and reproducible post-training recipe on GLM-4.5-Air-Base (106B-A12B), organized as a serial pipeline of eight stages: SFT, Reaso
arXiv:2609.29050v1 Announce Type: new Abstract: Tool-calling agents produce heterogeneous outputs, interleaving structured tool invocations with user-facing natural language summaries. This output het
arXiv:2609.30258v1 Announce Type: new Abstract: Distributed learning in embodied reinforcement-learning agents offers a degree of privacy by retaining raw sensor data on-device and transmitting only p
arXiv:2609.28506v1 Announce Type: new Abstract: TW3Cast is a time-series forecasting system that reaches position 3 of 130 entries on the GIFT-Eval benchmark by mean MASE rank, as of 2026-09-14. The t
1. fully agree w @JeffLadish that AI companies aren’t ready to handle superintelligent AI. 2. OpenAI hasn’t even handled the current breed of agents (far from superintelligent) well. 3. the US governm
arXiv:2608.24521v3 Announce Type: replace Abstract: Proactive medical dialogue requires an agent to decide what to ask from incomplete patient information. Existing information-seeking approaches comm
arXiv:2609.27773v1 Announce Type: cross Abstract: As Large Language Models (LLMs) move from conversational assistants to advanced agentic systems, guardrail failures can convert adversarial intents in
arXiv:2609.26952v1 Announce Type: new Abstract: Dependency conflicts in Python ecosystems arise from incompatible version constraints, missing packages, and undocumented compatibility relationships, c
Hi - I want to build a home server for Ollama. I want to connect to the server via my laptop and mobile devices to do research and run agents. What is recommended to get this going ? submitted by /u/R
Built this because I got tired of guessing whether a model would fit in my 6GB VRAM before downloading it, and because ollama.com's library doesn't let you sort by size. What it does: - Benchmarks Oll
Impressive paper from Salesforce. It discusses the importance of good verifiers for RL environments. Only 35.8% of the environments in the cleanest public RL collection for terminal agents passed Sale
I’ve been experimenting with local AI lately, and one thing I’m finding interesting is what comes after getting a model running. Ollama makes local model access pretty straightforward, but for an actu
LWiAI Podcast #257 (recorded 19 Sep 2026) reviewed OpenAI’s latest model, GPT‑6 Astra, noting its agentic coding focus and purported loop‑transformer reasoning as a significant capability jump. The ep
arXiv:2609.26866v1 Announce Type: new Abstract: Tool-result caching reduces repeated execution in agent training, but also couples rollout randomness. We study a two-action model in which independent
MLPerf Training v6.1 adds an agentic reinforcement-learning workload that measures how quickly systems can teach a 397-billion-parameter language model to repair real software projects. The post MLPer
Proud to be a launch training partner for @LangChain's LangSmith Fine-Tuning and smithtune. LangSmith traces → managed SFT on Fireworks → eval → deploy. One CLI, no training infra. Get a Fireworks API
arXiv:2609.26979v1 Announce Type: new Abstract: Gaussian processes (GPs) provide a flexible framework for learning unknown functions from noisy measurements while quantifying predictive uncertainty, m
arXiv:2609.26830v1 Announce Type: cross Abstract: Simulation success is not equivalent to structural correctness for LLM-generated circuits. We define and measure four evaluation levels -- schema vali
Hi, this is the research project I'm working on. I must say, building a GUI harness is way more complicated than I thought. The goal is something like Minecraft. You know, a few simple tools that a us
SWE‑Serve evaluates AI coding agents on 53 inference‑engineering tasks derived from SGLang pull requests across six functional domains. Among 19 tasks that launch a live server, patches that pass loca
arXiv:2609.25130v1 Announce Type: new Abstract: Memory systems for coding agents must decide, when a repository changes, which of their stored claims have become false. Content anchoring invalidates a
arXiv:2609.26693v1 Announce Type: new Abstract: A coding agent must emit a valid tool call--a parseable invocation of a tool in the provided schema--before the harness can execute its chosen action. W
I have been using open-webui and open-terminal. Open-terminal is installed in a VM and gives the agent a ton of control of it's own system that I keep away from my normal network. I find this gives th
arXiv:2609.26219v1 Announce Type: cross Abstract: Long-running LLM agent workflows often revise interior context spans while retaining long suffixes. Although suffix tokens remain unchanged, altered c
arXiv:2609.22746v1 Announce Type: new Abstract: Large Language Models (LLMs) have recently been introduced into traffic signal control (TSC) as decision agents due to their strengths in human-readable