Search: “agents”

Over the past several months, we conducted an empirical post-mortem investigation into 109 autonomous AI agent security incidents (cataloged with 193 falsification criteria across tool-use and multi-a

arXiv:2610.02472v1 Announce Type: cross Abstract: Personalized LLM assistants must recover sparse evidence from long conversation histories across queries of varying complexity. We introduce APDMem (A

arXiv:2610.02920v1 Announce Type: new Abstract: Agent harnesses play a critical role in defenses by enforcing safety constraints to prevent unsafe actions. However, rapidly emerging attacks outpace ma

arXiv:2610.03095v1 Announce Type: new Abstract: When two AI agents disagree, who persuades whom? As multi-agent systems increasingly combine language models of different families and sizes, the answer

arXiv:2610.00917v1 Announce Type: new Abstract: Choosing an agent system means choosing both a language model and the harness through which it acts. We ask whether a strong model, harness, or pairing

arXiv:2610.01506v1 Announce Type: new Abstract: As agents evolve from single-tool systems into modular, composite architectures, skills are becoming an important mechanism for capability development a

arXiv:2610.00388v1 Announce Type: cross Abstract: Reinforcement learning enables large language model (LLM) agents to learn multi-step behaviors through interaction with their environments. However, r

arXiv:2609.38607v1 Announce Type: cross Abstract: Shadow removal looks nearly solved on established benchmarks, yet remains brittle in the real world. Models have advanced; the paired training data th

arXiv:2609.40111v1 Announce Type: new Abstract: An unsuccessful LLM agent rollout contains more information than its final reward: the observations available to the agent, the actions it chose, and th

NVIDIA DOCA AI agent skills supply verified API signatures, hardware capability checks, and build constraints that let agents fully understand the DOCA library (Flow, GPUNetIO, PCC, RDMA) for BlueFiel

arXiv:2609.40324v1 Announce Type: new Abstract: We present Cogentic, a multi-agent harness for automated proof discovery on open research problems. While frontier language models can generate strong m

arXiv:2609.40143v1 Announce Type: new Abstract: Compact regulatory DNA can free up space in vector payloads, reduce synthesis and assay burden, and expose which sequence features drive predicted activ

arXiv:2609.40103v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as automated judges for AI-generated content, yet a single judge is unreliable and even a panel o

arXiv:2609.39788v1 Announce Type: new Abstract: Latent communication enables multi-agent systems to exchange information directly in internal representation space, reducing the token, computation, and

arXiv:2609.39549v1 Announce Type: cross Abstract: As Large Language Model (LLM) agents are increasingly deployed in complex environments, multi-turn interaction attacks have become a significant secur

arXiv:2609.38512v1 Announce Type: new Abstract: Voice agents in production must handle several requests, background speech, and customers who lose patience. We introduce VAmoS Energy, a benchmark that

arXiv:2609.36770v1 Announce Type: new Abstract: Can a population of neural networks develop a useful division of labor without a shared gate or gradients between agents? We study a setting where each

OpenAI's New Agent Stack: Superhuman Computer Use, Dots, Decisions API, UltraFast, & the AI Cloud https://www.latent.space/p/devday-2026 @OpenAI’s @AriX and @nikunjhanda explain why Computer Use is al

arXiv:2609.36171v1 Announce Type: new Abstract: Large-scale demonstrations have driven unprecedented progress in robot learning, yet collecting robot data through teleoperation is expensive and diffic

AI agent identity security is testing whether consolidated platforms can protect a growing class of machine identities. Palo Alto Networks Inc.’s acquisition of CyberArk Software Ltd. reflects broader

LA Tech Week is coming up in two weeks, and we’re doing our monthly LA Agentic AI Meetup during it. Tuesday, October 13 at Gulp in Playa Vista. 5–7pm. A few live demos, drinks, and a bunch of real peo

arXiv:2609.33338v1 Announce Type: new Abstract: Referring video segmentation with heterogeneous multimodal queries---spanning text, audio, and reference images---demands both robust cross-modal unders

arXiv:2602.09163v2 Announce Type: replace Abstract: Scientific knowledge bases accelerate discovery by curating findings from primary literature into structured, queryable formats for both human resea

arXiv:2609.31422v1 Announce Type: cross Abstract: Large language model-based multi-agent debate (MAD) systems are being increasingly used as complex decision pipelines in distributed processes. Howeve

arXiv:2609.30250v1 Announce Type: new Abstract: Conspiratorial discourse on social media is not always expressed through explicit claims or stable lexical markers. The same surface content may express

blank cells in tables can mess up agent decision making many document OCR tools struggle with reading multiple blank cells in a document and cause values to be shifted from the original column and row

arXiv:2609.26293v2 Announce Type: replace Abstract: Learned world models are becoming essential to general-purpose agents: by predicting action consequences, they support planning and decision-making

arXiv:2609.29015v1 Announce Type: new Abstract: Decentralized LLM-based multi-agent systems coordinate through local interactions, but an agent can remain responsive while its task-solving quality per

arXiv:2609.27580v1 Announce Type: cross Abstract: Distributed intelligence concerns systems in which semi-autonomous components with local dynamics and partial observations coordinate through informat

arXiv:2609.27150v1 Announce Type: new Abstract: Multi-agent debate (MAD) has emerged as a promising paradigm for improving the reasoning accuracy of large language models (LLMs) through iterative peer

A research group has linked three more hacking campaigns to rogue artificial intelligence agents. Transluce, a nonprofit AI safety organization, detailed its findings on Wednesday. Its researchers det

arXiv:2609.26085v1 Announce Type: new Abstract: Inspired by the flight and song of birds, we propose an approach that enables cooperating agents to effectively identify obstacles in their environment

arXiv:2609.24831v1 Announce Type: new Abstract: Agents have attracted considerably increasing attention due to the power of executing both Reasoning and Acting (ReAct) in open and dynamic environments

arXiv:2609.24277v1 Announce Type: new Abstract: GUI agents predict click coordinates as digit-token sequences, but standard text-LLM confidence estimation methods rank correct clicks from wrong ones o

arXiv:2509.26200v2 Announce Type: replace-cross Abstract: Agentic artificial intelligence is a candidate enabler of Level-4 autonomy in sixth-generation (6G) networks, but agents reasoning over a shar

arXiv:2609.22164v1 Announce Type: new Abstract: Structured EHR is abundant but sparse, coded, and difficult to use directly for note-centric clinical modeling. We present MedNotes, a multi-agent synth

arXiv:2609.24264v1 Announce Type: new Abstract: Tool-use agent traces identify messages and API calls, but procedural analyses also need explicit units of action and inspectable links to their evidenc

arXiv:2609.22641v1 Announce Type: new Abstract: Autoregressive video world models enable temporally coherent generation for a single observer. Extending them to multiple agents requires consistency ac

arXiv:2609.24967v1 Announce Type: cross Abstract: LLM agents are increasingly deployed in collaborative settings, yet long-term interaction may give rise to undesirable coordination. We study the emer

arXiv:2506.08296v3 Announce Type: replace Abstract: Recent advances in multimodal vision-language-action (VLA) models have revolutionized traditional robot learning, enabling systems to interpret visi

Impressive paper showing how much the harness changes a coding agent's results. Harnesses do play a huge role in what you are getting out of the models. GPT-5.5 was run inside both Claude Code and Cod

arXiv:2606.12916v2 Announce Type: replace-cross Abstract: Molecular dynamics (MD) is the canonical in-silico method for atomistic molecular science, simulating molecular behavior from first-principle

Meta has issued a patch for its Muse macOS app following the discovery of a zero-day vulnerability that could allow someone to take control of the AI agent. The bug found by security researcher Patric

arXiv:2609.21192v1 Announce Type: new Abstract: Organizations deploying agentic artificial intelligence must determine more than whether a model is trustworthy; they must establish what to validate, c

arXiv:2609.21267v1 Announce Type: new Abstract: Production LLM agents are evaluated repeatedly as they evolve, but full agent benchmarks are costly to rerun. We study efficient recurring evaluation fo

arXiv:2609.21929v1 Announce Type: new Abstract: Multi-agent manipulation naturally produces multiple task-driven viewpoints: every arm carries a wrist camera and moves through the scene while acting.