Search: “agents”

arXiv:2609.28887v1 Announce Type: new Abstract: Heterogeneous robot teams distribute complementary capabilities across specialized agents, but their physical roles and capacities typically remain fixe

arXiv:2609.29661v1 Announce Type: new Abstract: Most agentic question answering (QA) systems do an important part of their semantic work at the worst possible time: every time someone asks a question.

arXiv:2609.30217v1 Announce Type: cross Abstract: A central concern in AI safety is that agents may treat oversight as an obstacle when it conflicts with completing their goals. We study instrumental

arXiv:2609.28709v1 Announce Type: new Abstract: Autonomous UAV flight through cluttered and partially unknown environments requires reasoning not only about observed obstacles but also about occluded

Muse is getting a lot of attention — including mine — because it’s both groundbreaking technically (each user gets their own entire persistent Linux VM running in Meta’s cloud) and because it’s packag

Since my last post, I've been thinking about different options for dynamic performance degradation, trying to squeeze as much high-quality inference out of my GPU as I can. Over the weekend I read thi

Oracle Corp.’s Deep Data Security offers a basic premise on enterprise security: When the application layer is an AI agent, the trust boundary must move somewhere else. The trust boundary can be reloc

arXiv:2609.27095v1 Announce Type: cross Abstract: Robotic embodiment encompasses the sensing, kinematics, dynamics, geometry, actuation, and control through which an agent physically interacts with th

predicting model uncertainty is a hard problem. perfectly 'calibrated' confidence scores are exact probability values on whether the output is correct. this is extremely important for agentic decision

Introduction The landscape of software supply chain security has undergone a significant shift. Recent campaigns demonstrate that sophisticated threat actors are systematically targeting the engineeri

arXiv:2609.27035v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) and related policy-gradient methods for training language model agents collapse an entire multi-turn rollout i

sorry to every other sf tech week host in advance, but we may have gotten carried away planning our event... we're about to host the biggest and most lavish black-tie gala sf tech has ever seen. live

The Australian government should prosecute OpenAI. Anything less is a failure of its responsibility to its citizens. JUST IN: An OpenAI AI agent went rogue and hacked the Australian government. At a p

This is a fantastic blog post from our research team on the importance of calibrated confidence scores. Here it's in the context of document extraction, it's also extremely important for more general

This turned out to be the most prophetic tweet of the year Breaking news: Australian Prime Minister Anthony Albanese has revealed that an OpenAI agent hacked an Australian government health service we

we've built the world's most advanced engine for document extraction over complex documents the video below shows an overview of LlamaExtract Agentic Plus in action. long tables, giant forms, calibrat

arXiv:2609.26481v1 Announce Type: cross Abstract: Social norms cannot be identified from behavior alone: the same cooperative equilibrium may reflect shared expectations, strategic incentives, or simp

arXiv:2604.07733v2 Announce Type: replace Abstract: Evaluating strategic decision-making in LLM-based agents requires generative, competitive, and longitudinal environments, yet few benchmarks provide

arXiv:2606.13591v2 Announce Type: replace-cross Abstract: Multiagent language model systems, such as collaborative reasoning and debate, produce multiple correlated candidate answers and confidence si

Agentic artificial intelligence employee startup Ema Unlimited Inc. is prepping for a massive expansion of its autonomous workers in the enterprise after raising 77 million in funding today. The Serie

arXiv:2609.26360v1 Announce Type: new Abstract: Embodied Question Answering (EQA) requires an agent to explore a previously unseen environment, gather relevant information, and answer questions about

arXiv:2609.22599v1 Announce Type: new Abstract: Large language model (LLM) judges provide a flexible and scalable method for evaluating model and agent outputs, but their verdicts can be sensitive to

Meta is building a dedicated hardware device for its new Muse AI agent. The product, called Muse Charm, was briefly shown off by Meta CEO Mark Zuckerberg at the end of tonight's Meta Connect presentat

arXiv:2609.25054v1 Announce Type: new Abstract: For a long-horizon LLM agent, the memory question is not what was once recorded but what currently holds. Most designs answer it only indirectly: every

arXiv:2609.24876v1 Announce Type: new Abstract: In multi-agent social settings, model reliability varies across relationships. Beyond inferring what others will do, an agent must calibrate how confide

arXiv:2609.26051v1 Announce Type: new Abstract: We investigate the challenges of enabling effective collaboration between human operators and heterogeneous autonomous agents in complex, dynamic enviro

arXiv:2609.24744v1 Announce Type: new Abstract: Language agents solve complex tasks through plans and actions. A single step the world refuses puts the goal out of reach, and what the agent does next

ZeroDrift Inc., a startup that automates compliance for artificial intelligence communications, today launched Anchor 3.0, a family of small language models designed to check messages generated by AI

arXiv:2609.22385v1 Announce Type: cross Abstract: Achieving high task success and efficiency remains a central pursuit in embodied exploration. Existing frameworks typically guide agent behavior throu

Cybersecurity company Barracuda Networks Inc. today launched Barracuda AI Data Security, a product that monitors and controls what company data employees feed into artificial intelligence tools. The r

arXiv:2609.22538v1 Announce Type: new Abstract: Large language model (LLM) planners can decompose natural-language instructions and select reusable robot skills, but choosing the correct skill does no

Jyoti Mann / The Information: Internal data: Meta's Muse surpassed 500,000 total users, including 250,000 daily active users, with more than 2M prompts submitted in its first week — Meta's new persona

arXiv:2609.24911v1 Announce Type: new Abstract: Social simulation offers the social sciences an experimental instrument that the real world cannot supply, and generative agents have transformed it by

arXiv:2609.22870v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a key technique for improving the reasoning and agentic abilities of large language models (LLMs). Although FP8 q

Bloomberg: Sensor Tower: Muse was downloaded 902K+ times in the six days after its launch on Sept. 8, vs. Meta AI's 773K in the same post-launch period; META jumps 12%+ — Meta Platforms Inc.'s new art

arXiv:2609.21190v1 Announce Type: cross Abstract: Ensuring the correctness of LLM-generated code is a core challenge for modern software engineering. Benchmarks for agentic code generation check corre

arXiv:2609.21323v1 Announce Type: new Abstract: Vision-language models (VLMs) have demonstrated strong scene understanding and semantic judgment across diverse tasks, but their appropriate role in coo

with jev, everyone is understanding the importance of calibrated confidence scores for discrete decision making we've taken that approach one-step further and created grounded confidence scores for ge

ZCode is now open source, and the reported security issues have been addressed. Source code: https://github.com/zai-org/ZCode The repo includes its desktop app, web workspace, backend, Agent CLI, and

Release: llm-keys-ui 0.1 This plugin solves a very specific problem. I've started using Codex Remote to run coding agents on various machines while controlling them from my phone. Sometimes I use thos

Vector search is a critical component of generative AI, retrieval-augmented generation (RAG), and data agent architectures, but sometimes vector search alone isn't enough. While vector embeddings are

bonsai claim 98.2% intelligent retained, but their own documents show Ternary Bonsai 2 27B reaches 52.8 and 60.8, respectively, compared with 69.7 and 80.6 for Qwen3.5-27B, retaining roughly three qua

arXiv:2609.19551v1 Announce Type: new Abstract: In an enterprise system, updating one field can set another, create a record, or start an approval. These effects are produced by business rules that ar

Introducing the first in our Parsed by LlamaParse series. We're outlining the stakes of 'getting parsing wrong' in consequential documents. We’re starting with the U.S. Energy Information Administrati

arXiv:2609.20174v1 Announce Type: new Abstract: We consider a federated reinforcement learning setting involving M agents, all of whom interact with a common Markov Decision Process (MDP). The agents

Today we are announcing the new AgentCore runtime, a capability of Amazon Bedrock AgentCore built for the speed, flexibility, and cost efficiency that production agents demand. It reclaims memory as s