Search: “agents”

arXiv:2607.28390v1 Announce Type: new Abstract: Constrained Markov Decision Processes (CMDPs) provide a natural framework for reinforcement learning in safety-critical applications, where agents maxim

Inkling-Small is now live on Together AI. @thinkymachines’ new open-weight multimodal model delivers similar performance to Inkling at one-quarter the size, built for coding, agents, and general multi

When the phrase 'OpenAI hacked Hugging Face' has more or less entered mainstream culture, you know we have an AI problem. This week, we learned more about exactly how OpenAI's agent broke out of a san

arXiv:2607.28474v1 Announce Type: new Abstract: Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires an agent to follow a natural language instruction, predicting a sequence of

arXiv:2607.26068v1 Announce Type: cross Abstract: Existing AI governance frameworks, including the EU AI Act and NIST AI RMF, address safety, transparency, and accountability but do not operationalize

Together AI gives developers a high-throughput production path for running Inkling-Small on NVIDIA Accelerated Infrastructure across multimodal, coding, and agentic workloads. Start building: https://

arXiv:2607.26470v1 Announce Type: new Abstract: Multi-turn information-seeking conversations require both multi-hop reasoning and long-range dependency tracking across turns. However, existing RAG sys

arXiv:2607.26579v1 Announce Type: cross Abstract: World models offer a promising route toward robot planning by enabling agents to imagine and verify the consequences of actions before execution. Howe

arXiv:2607.26820v1 Announce Type: new Abstract: As large language models (LLMs) evolve from standalone assistants into autonomous agents, ensuring their safety requires shifting beyond pointwise risk

arXiv:2607.26060v1 Announce Type: new Abstract: LLM-based chatbots are transforming customer service in regulated domains such as banking, but scalable and cost-effective validation remains a critical

one of the top cybersecurity models, post-trained from open weights by @depthfirstlabs on @FireworksAI_HQ long-horizon RL is as much an infra problem as a research one: 100+ turn rollouts, async/pipel

arXiv:2607.26485v1 Announce Type: cross Abstract: Resource allocation across multiple agent groups arises in many applications including e-commerce recommendation systems, housing assignment, and cour

arXiv:2607.25207v1 Announce Type: new Abstract: This paper investigates a hybrid reinforcement learning setting in tabular Markov Decision Processes (MDPs), where an agent aims to learn an optimal pol

We developed a leaderboard ranking frontier model security. There's no shortage of model capability rankings, but we didn't find anything comparable for model security. Yet security is becoming increa

arXiv:2607.24821v1 Announce Type: cross Abstract: While instruction-based video editing has advanced rapidly, real-world videos contain tightly coupled audio and visual signals, and editing one modali

BREAKING: Grok 4.5 ranked #1 on LaurenBench with a score of 56.9%, ahead of Claude Sonnet 5, GLM 5.2, Claude Opus 5, Kimi K3 and GPT-5.6. The benchmark tests real-world AI agents across conversation,

arXiv:2607.26041v1 Announce Type: new Abstract: Computer-use agents (CUAs) increasingly act through desktop GUIs to complete long-horizon tasks. Current benchmarks primarily measure end-task success o

Microsoft is working on an AI 'super app' that combines Copilot's chat, coding, and agentic capabilities. During an earnings call on Wednesday, Microsoft CEO Satya Nadella said the app will span 'both

What happened? I just asked GLM 5.2 one question, and in 3 minutes (one agent) it used up 15% of my 5 hour limit to produce a single answer. At this rate, I'll exhaust the entire 5 hour limit in just

arXiv:2605.05811v2 Announce Type: replace Abstract: Workbook-scale spreadsheet understanding is increasingly important for language-model-based data analysis agents, but remains challenging because re

arXiv:2607.26017v1 Announce Type: new Abstract: Memory is essential for LLM agents to accumulate task experience and reuse task-specific execution strategies. However, real-world deployment over bound

We ran a large-scale distillation attack on the Kimi K3 technical report by reading it in parallel at the Hugging Face Journal Club :) https://youtu.be/MW8-kqd2SD8?si=jSKDogcUWbJ8N2k7 Our main takeawa

I really love this model, I have been using the q4_k_l by Bartowski (I have heard QAT is quite the downgrade in some aspects) and it handles every task I throw at it easily. Agentic and coding perform

arXiv:2607.24343v1 Announce Type: cross Abstract: Language-model agents act through structured tool calls whose arguments carry different risks. Untrusted content may safely influence an email body bu

arXiv:2607.22715v1 Announce Type: new Abstract: The rapid growth of Artificial Intelligence-generated content (AIGC) is reshaping video production and circulation, exposing children to an increasing v

arXiv:2607.24057v1 Announce Type: new Abstract: Real-world Reinforcement Learning depends on the ability to formulate safety constraints into a policy. A common way to model such constraints is to int

arXiv:2607.24744v1 Announce Type: cross Abstract: Multimodal foundation models learned to see and to speak by consuming the whole internet. Embodied agents admit no such shortcut, since they require d

arXiv:2607.24241v1 Announce Type: cross Abstract: Progress in video generation keeps narrowing the visual gap between AI-generated and professionally produced footage, yet most benchmarks still draw p

arXiv:2607.23532v1 Announce Type: cross Abstract: Swarms of LLM-assisted autonomous robots are increasingly proposed for cooperative intelligence, surveillance, and reconnaissance (ISR) in contested e

arXiv:2607.22951v1 Announce Type: cross Abstract: Reliability assessment of large language models (LLMs) seeks to estimate the probability that a model produces correct responses under a specified ope

arXiv:2607.22997v1 Announce Type: cross Abstract: Physical AI -- the integration of large vision-language-action (VLA) models with embodied agents that act in the real world -- has emerged as the next

arXiv:2607.24063v1 Announce Type: new Abstract: On standard factuality tasks, frontier models now cluster near the top of the scale. The question is therefore shifting from how factual a system is tow

Following some recent commits in llama.cpp, preserve_thinking behavior for chat templates included in older DSV4 ggufs got broken. This makes the model pretty dumb in a coding agent context. Adding kw

By 'task oriented', I dont really mean agentic, I mean no deep coding ability, no need for conversation. More things like classification, identification, simple interaction with web apps and APIs, etc

arXiv:2607.24010v1 Announce Type: new Abstract: Active RAG systems decide when to retrieve external knowledge during generation, making them a budget-sensitive case of agentic RAG and self-adaptive re

An opinionated guide to which AI to use to do stuff It's interesting watching the evolution of Ethan Mollick's guide over time. A year ago it was still all about chat - ChatGPT, Claude, Gemini - with

arXiv:2601.12311v2 Announce Type: replace-cross Abstract: The emergence of 6G-enabled vehicular metaverses enables Autonomous Vehicles (AVs) to operate across physical and virtual spaces through space

arXiv:2607.21608v1 Announce Type: cross Abstract: With the EU AI Act entering into force, organizations developing or operating AI systems face new obligations on transparency, risk management, and tr

New to the GitHub Copilot app? Learn how to start projects, work with AI agents, explore canvases, and streamline your development workflow. The post GitHub Copilot app for Beginners: Getting started

I'm considering the 20 Pro plan, but the limits seem to change over time and are hard to compare with direct API pricing. For anyone using Pro currently, roughly how much coding agent usage do you get

arXiv:2607.22166v1 Announce Type: new Abstract: Path planning under partial observability remains challenging because an agent must make long-horizon navigation decisions from only locally bounded obs

I just managed to get it running on windows and this thing is fucking insane. I get around 550-720t/s depending on task at hand. Previously to get to such numbers i would have to do batching and agent

The complexity of modern chip design continues to grow as engineering teams work to develop increasingly sophisticated CPUs, GPUs and AI systems. To help meet that challenge, NVIDIA is collaborating w

I have tried ollama locally on my gaming PC (5070 with 12bg of VRAM) It works pretty nice on qwen2.5-coder:7b (and 14b) So I decided to take a step further, and install an openWebUI instance on my hom

I apologize that this question has been asked in various flavors over time, but I couldn't find anything in the posts before that matches the options I have. I have a PC and a mac, both available in m

Anonymous OpenAI staffer: 'Externally, this feels like a big warning shot, but internally, related incidents have been happening for a while.' 'The AI agents who hacked their way out of OpenAI and int