Search: “agents”

We wrote a 36-page ArXiv whitepaper on ExtractBench 🧑‍🔬 , our effort to create the most comprehensive, schema-guided, real-world document extraction benchmark. It’s extremely detailed and covers every

We’re excited to announce DiG-bench, a new benchmark for discovery! Over the last few weeks we’ve been testing frontier AI models on our novel discovery games and seeing how they score. Each game is a

arXiv:2608.10703v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly act in interactive settings where their behavioral styles affect user experience, safety, and downstream dec

arXiv:2607.10180v2 Announce Type: replace-cross Abstract: We introduce ActiveFly-Bench, the first benchmark to bridge cyberspace reasoning and physical-world interaction for UAV embodied perception. T

arXiv:2608.07557v1 Announce Type: cross Abstract: Vision-Language Navigation for Unmanned Aerial Vehicles (UAV-VLN) requires rapid and reactive control in complex 3D environments. Recent minimalist en

I just heard of this model. Seems to be a competitor to DeepSeek V4 Flash. About the same size and active parameters. Anyone tested it compared to V4 Flash? Link: https://huggingface.co/upstage/Solar-

arXiv:2608.07873v1 Announce Type: new Abstract: We introduce the workbook time machine, a pipeline that automatically creates benchmarks evaluating the ability of language models to create derived obj

Security operations platform startup Blumira Inc. today launched Hearth, a vendor-agnostic artificial intelligence command center that lets security teams investigate and act across their existing too

arXiv:2608.08061v1 Announce Type: new Abstract: The key question in moral judgement is not simply whether someone chooses the 'right' answer, but how they decide what matters most when moral principle

Spent two nights getting deepseek-ai/DeepSeek-V4-Flash-0731 (284B MoE, 13B active, native FP4/FP8, 1M context) running production-grade on two DGX Sparks connected by one QSFP DAC cable. Everything —

arXiv:2608.08691v1 Announce Type: new Abstract: Residential virtual power plants (VPPs) can provide grid flexibility by shifting household demand, but physical flexibility becomes dependable capacity

arXiv:2608.09516v1 Announce Type: new Abstract: World Action Models (WAMs) jointly learn environmental dynamics and robot actions, introducing priors over physical evolution into embodied control. How

I wanted to find out whether a huge text-only MoE could be given basic vision without retraining the language model itself. The short answer is yes. I froze DeepSeek V4 Flash and a 417M-parameter Moon

arXiv:2608.08210v1 Announce Type: new Abstract: Collaborative dialogue can end with apparent agreement while participants still differ on goals, assumptions, or execution plans, creating an extbf{illu

Introducing ExtractBench, the most comprehensive benchmark for information extraction from complex enterprise documents. The latest models are pushing the frontier of coding and knowledge work, but su

arXiv:2608.09343v1 Announce Type: new Abstract: Simulation-based optimization (SBO) evaluates executable policies under stochastic dynamics, but most methods treat the simulator as a black box: aggreg

arXiv:2608.08804v1 Announce Type: cross Abstract: With advancements in long-distance wireless power transfer (WPT) and space-based energy technologies, integrating WPT into non-terrestrial networks (N

Just downloaded the model, UD-Q5_K_XL quant, asked it to generate a long story to test out reasoning and speed with dflash (super fast btw, ~ 90 to 160 tok/s on a 5090 depending on task) and was surpr

Open source is so back. Zuck just announced Meta is opening the weights for Muse Glimmer, with Muse Spark 1.2 coming soon But a year ago, everyone doubted Meta's position in the AI race In an intervie

OpenWALDO, a new open-source artificial intelligence project sponsored by Ctrl IQ Inc., launched today, led by Gregory Kutzer, the founder of Rocky Linux, CentOS and Apptainer. The project aims to bui

River AI Inc., a startup that helps enterprises customize open-source artificial intelligence models, has raised 1.1 billion in early-stage funding. The company stated in today’s announcement that it

arXiv:2608.07808v1 Announce Type: cross Abstract: Four years after prompt injection was first identified in 2022, attacks are still predominantly documented as verbatim strings rather than structured

💡The world needs an open-source platform, and that’s exactly what we’re building to give our customers more choice and the flexibility to choose the right model for the right task. As part of this, we

Whoa, Meta released a new open-weight LLM yesterday, something that hasn't happened since the good old Llama days. Their Meta Muse Glimmer model is a 30B multimodal reasoning model with a Gemma-like a

arXiv:2608.07439v1 Announce Type: new Abstract: Quantum natural language processing (QNLP) provides a grammar-aware framework for text modeling, and Distributional Compositional Categorical (DisCoCat)

arXiv:2608.07038v1 Announce Type: cross Abstract: Human-Oriented Binary Reverse Engineering (HOBRE) aims to transform decompiled pseudocode into a more human-friendly representation, thereby reducing

I've been running Gemma 4 E4B with oMLX and I can't find any chat interfaces that directly send the audio file to the model instead of running the audio through a separate STT layer. I can confirm the

arXiv:2608.07424v1 Announce Type: new Abstract: Test-time scaling is often implemented by spending more compute along one axis: sampling more solutions, extending a chain of thought, or applying a str

Defensive cybersecurity startup Corma Labs Ltd. today announced it has raised 60 million in seed funding to build a foundation model purpose-built for security defense. Founded in 2025, Corma runs off

arXiv:2608.07067v1 Announce Type: new Abstract: Long-document understanding requires locating sparse and heterogeneous evidence across hundreds of pages, yet existing systems remain limited by static

arXiv:2608.07400v1 Announce Type: new Abstract: Financial question answering is typically evaluated by answer correctness, yet in SEC filings a plausible and even numerically correct answer can be gro

arXiv:2608.07411v1 Announce Type: new Abstract: In the context of geodata, existing Large Language Models have often been studied in a homogeneous setting, which has considerably limited insights into

Got Meta's new Muse Glimmer 30B running on my MacBook (M3 Max, 96GG) and tested the serving options available so far. Fastest right now: Ollama's MLX engine (DFlash included) at ~29 tok/s. Tuned llama

What’s the best way to recommend products to little-known users? We’ve spent our careers trying to solve this problem for major companies like Spotify and Priceline, and it’s why Sidd founded Malachyt

Between chaotic levels of market fragmentation and economic volatility, marketing and communications agencies can no longer rely on the human intuition they’ve traditionally used to win clients and op

arXiv:2608.07091v1 Announce Type: cross Abstract: Edge Artificial Intelligence (Edge AI) enables the deployment of AI models directly on local edge devices, while such deployments are subject to stric

arXiv:2608.07370v1 Announce Type: new Abstract: Scientific literature is increasingly used as a knowledge source for language models, retrieval-augmented generation systems, and research assistants, b

arXiv:2608.06867v1 Announce Type: new Abstract: No single large language model (LLM) is optimal across all queries and budget constraints, making model routing essential for cost-effective deployment.

arXiv:2608.06929v1 Announce Type: cross Abstract: Regional image editing has attracted considerable attention for its spatial controllability. Although instruction-based and mask-reference-based editi

Meta released Muse Glimmer 30B: multimodal model for your Claw/Pi setups 🔥 we tested and fine-tuned the model for you, and shipped day-0 support in transformers and llama.cpp, including DFlash for 2-4

Meta Platforms Inc. today released Muse Glimmer, an open-source language model that can run on personal computers. The company also published a lengthy essay penned by Chief Executive Officer Mark Zuc

arXiv:2608.06713v1 Announce Type: new Abstract: Biomedical knowledge graphs (KGs) accelerate drug discovery, but standard pipelines assume query molecules already exist as graph entities, leaving unre

I did some testing this morning, and I was surprised to find that Muse Glimmer actually comfortably fits on a single RTX 3090 with full context + DFlash + mmproj at Q4_K_XL, unlike Qwen3.6-27B and Gem

Muse Glimmer, the new 30B model, is available on Hugging Face right now - here's the GGUF version: https://huggingface.co/meta-models/Muse-Glimmer-30B-GGUF 1/ big announcement today: we will be releas

arXiv:2608.07040v1 Announce Type: new Abstract: Solving combinatorial optimization problems (COPs) requires not only efficient algorithms but also carefully crafted formulations. While recent works ha

arXiv:2608.06690v1 Announce Type: cross Abstract: Most language-model access controls regulate behavior while leaving the same computation available to every request. We study a different systems ques