Search: “agents”

arXiv:2609.34749v1 Announce Type: new Abstract: Real-world driving is inherently multi-agent, yet most existing driving world models generate observations from a single ego vehicle. Independently exte

arXiv:2609.32805v1 Announce Type: cross Abstract: Long tasks produce more history than an LLM agent can hold in its context, and more than it uses reliably even when the history fits. A growing line o

arXiv:2609.31901v1 Announce Type: new Abstract: Constrained general-sum dynamic games are a popular formulation for highly interactive multi-agent planning problems. In recent years, Generalized Nash

arXiv:2609.31929v1 Announce Type: new Abstract: Newton methods efficiently find Generalized Nash Equilibria (GNE) in dynamic games by solving for the KKT necessary conditions. These methods are fast a

arXiv:2609.33288v1 Announce Type: new Abstract: Embodied Question Answering (EQA) requires agents to answer natural language questions about surrounding environments from visual observations. In this

Tech YouTuber Matt Robb says that Muse gave out his home address to a total stranger this weekend, after authorizing the bot to handle his Facebook Marketplace account. That's despite Meta placing gre

arXiv:2602.12029v2 Announce Type: replace Abstract: Multi-agent systems increasingly orchestrate multiple specialized language models to solve complex real-world problems, often invoking them over a s

arXiv:2601.22419v2 Announce Type: replace-cross Abstract: Pooled testing uses one test to certify several agents as healthy when the pooled result is negative. We study a budget-constrained welfare pr

AI Engineering from Scratch is an MIT-licensed curriculum: 523 lessons across 20 phases, from linear algebra and backprop to transformers, LLMs, agents, and production serving. The code is stdlib-firs

OpenAI’s so reckless, “It is like if in … Jurassic Park they would have let all the dinosaurs roam free not only on the island but on a populated continent” What is so bad here is that they should hav

arXiv:2609.31191v1 Announce Type: cross Abstract: Data quality research has usually treated data as an input that is stored, processed, and validated. In AI-driven software-intensive systems, data als

This is one of the strongest use cases I've seen for System One models like Jev. Pay close attention if you build custom harnesses. Jev is now available as a packaged router. What is it? You send the

arXiv:2609.29958v1 Announce Type: cross Abstract: We study a matching mechanism where agents and objects are described by features rather than complete rankings. A single spectral projection reduces t

arXiv:2603.11351v2 Announce Type: replace-cross Abstract: In dynamic open-world environments, autonomous agents often encounter novelties that hinder their ability to find plans to achieve their goals

In July, OpenAI revealed that its AI agents had attacked Hugging Face without permission, sparking widespread concerns about AI safety. Since then, a string of similar incidents involving agents from

arXiv:2609.29251v1 Announce Type: new Abstract: CAR-bench evaluates whether tool-using agents stay reliable under real-world uncertainty, executing every tool inside the evaluator so that each tool-re

We announced our RSI Lab earlier this year: https://sakana.ai/rsi-lab/ Over the last two years, we have systematically shipped the foundations for autonomous R&D: ▪ LLM²: AI automating research to inv

arXiv:2609.27720v1 Announce Type: new Abstract: Spatially constrained semantic navigation requires robots to identify targets specified not only by semantic categories but also by relations to surroun

arXiv:2609.27077v1 Announce Type: new Abstract: To avoid collisions, a robot must repeatedly predict where nearby agents may move, usually with an imperfect model of their dynamics. Reachable sets pro

This is increasingly indefensible. How many more incidents are @OpenAI aware of that haven't broken the news yet? 'It took until September 10 before there was any notification at all,' What was the in

arXiv:2412.03800v2 Announce Type: replace Abstract: Reinforcement learning agents depend on reward signals whose density is rarely under the designer's control, and when such signals are absent, an ag

arXiv:2609.22664v1 Announce Type: cross Abstract: Research on large language model agents for penetration testing is evaluated almost entirely by capability: whether the agent captures a flag or repro

arXiv:2609.26368v1 Announce Type: new Abstract: Long-horizon and multi-turn agents typically generate short actions and process long observations from tools and environments. This growing context dema

TypeSafe is pushing hard on this idea of “composable AI” but LangChain has embodied composable AI since day one. With new models like Jev, we’re decomposing the agent loop and moving more intelligence

Public sector agencies process large volumes of unstructured evidence, such as body camera footage and scanned documents. This post shows how to combine Amazon Bedrock Data Automation with the Model C

arXiv:2609.22833v1 Announce Type: new Abstract: We study personalized federated reinforcement learning, in which n agents, each acting in its own Markov decision process, collaborate through a server

arXiv:2609.24969v1 Announce Type: new Abstract: As agents are deployed with increased autonomy, even extremely rare events along their stochastic output trajectories can occur and prove catastrophic.

arXiv:2609.24289v1 Announce Type: new Abstract: As Large Language Model (LLM) agents are applied in continuously interactive environments, driving the evolution of their own capabilities becomes a cor

Vast Data Inc. today introduced DataEnclave, a confidential computing environment designed to let companies run advanced artificial intelligence models against sensitive data without exposing either t

Identity security now determines how safely artificial intelligence agents can access systems and act across enterprise workflows. As AI agents log in to applications and execute tasks, companies must

and here’s the grok 4.7 model card. a few jumps vs 4.6 that stood out: - Terminal-Bench: 20.3% → 38.0% - SWE-Marathon: 31.9% → 46.0% - HealthBench Pro: 48.5% → 56.7% - Legal Agent: 15.8% → 19.6% - EEB

arXiv:2609.20844v1 Announce Type: new Abstract: Deepresearch (DR) agents interact with real-world web environments through multi-turn search and visit, causing their contexts to grow rapidly over time

Kelly Cloonan / Wall Street Journal: Shopify plans to allow Meta's Muse to complete purchases on behalf of users at Shopify-powered stores via its one-tap checkout service Shop Pay — Shopify plans to

Meet Inco Splash, open-source inference engine, built around the model and around Apple silicon. Up to 3× the decode speed of Ollama, 2× oMLX, and almost 4× when an agent fans out into sub-agents. Req

Worth reading about this OpenAI just admitted on camera: They spun up thousands of AI agents in a “secure” sandbox and told them to hack. The agents didn’t follow the test. They cheated. Then they bro

Today, we are excited to announce enhancements to the borderless Lakehouse, our answer to how data engineers, data scientists, and increasingly, AI agents, can query governed data directly where it li

arXiv:2609.19491v1 Announce Type: cross Abstract: Modern LLMs and AI agents increasingly support data engineering workflows that integrate evidence from unstructured sources. Such pipelines typically

arXiv:2511.22924v3 Announce Type: replace-cross Abstract: Large Language Model (LLM)-based Multi-Agent Systems (MAS) are susceptible to linguistic attacks that can trigger cascading failures across th

arXiv:2609.19183v1 Announce Type: cross Abstract: Whether human or large language model (LLM), an agent in a discussion reads only a few of the others' contributions, bounded by cognition, context, or

Super interesting work from Zoom and colleagues. If you maintain a hand-built coding harness, there are some great insights here. (bookmark it) They held the execution loop of a coding harness fixed a

arXiv:2609.18073v1 Announce Type: new Abstract: This work studies how refraction-induced bias on acoustic ranging affects multi-agent collaborative localization in a range of oceanographic conditions

arXiv:2609.18736v1 Announce Type: new Abstract: Despite recent advances in large language models (LLMs), performing logically consistent deductive reasoning over extended interactions remains challeng

Learn how to enforce defense-in-depth authorization for Model Context Protocol (MCP) tools on Amazon Quick. This walkthrough wires Microsoft Entra ID group and claims-based JWTs through an Amazon Bedr

arXiv:2609.17631v1 Announce Type: new Abstract: AI-assisted claims can appear authoritative when evidence, analysis, human authorization, presentation, and correction history refer to different states

arXiv:2609.16824v1 Announce Type: new Abstract: Decentralized bandit systems often contain heterogeneous agents: rewards can change at individual agents even when the best action for the network stays

arXiv:2609.16301v1 Announce Type: new Abstract: Medical knowledge evolves continuously, whereas the parametric knowledge encoded in large language models (LLMs) is fixed at training time. External ret