agents

A note on the Hugging Face agent incident

Hugging Face reported that a recent agent intrusion used Modal’s infrastructure as a launchpad, but Modal’s sandbox isolation was not breached; the malicious code executed only within the affected cus

agentsmodal-blog

Agent Skills Matter: Inferring Proprietary Skills from Execution Trajectories

DGX agent

arXiv:2607.25560v1 Announce Type: new Abstract: Agent skills package reusable procedures that improve downstream performance. Their lightweight, portable form enables marketplace monetization and priv

agentsarxiv-cs-ai

29 Jul 2026

Agentic inference wastes GPUs on KV cache thrashing. ThunderAgent fixes it at the scheduler level: 2.5x higher single-node throughput and ~1…

Agentic inference wastes GPUs on KV cache thrashing. ThunderAgent fixes it at the scheduler level: 2.5x higher single-node throughput and ~10x lower P50 latency at high concurrency. ThunderAgent was a

agentstogether-ai--x

AI can write more code than any team can review by hand, and a pull request can look fine while hiding a security issue or missing a require…

AI can write more code than any team can review by hand, and a pull request can look fine while hiding a security issue or missing a requirement. In our new short course, AI Code Review, built in coll

agentsitamar-friedman--x

Authenticate with Private Key JWT using Amazon Bedrock AgentCore Identity

This post explains how Private Key JWT client authentication works in AgentCore Identity and reviews the supported grant flows. We then walk through creating an AWS KMS signing key, registering its pu

agentsaws-ml-blog

Automatic Knowledge Graph Construction and Query for Earthquake Catalogs

arXiv:2607.24984v1 Announce Type: cross Abstract: In recent years, the number of events in earthquake catalogs has significantly increased due to the utilization of more effective deep learning based

Automating customer retention workflows in Amazon Quick

Learn how to build a no-code customer retention pipeline in Amazon Quick that detects at-risk customers from call transcripts and CSAT data, scores them by retention priority with a custom MCP Action,

agentsaws-ml-blog

Batch parsing used to mean writing API scripts. Now it's a button. 🦙 Parse or extract across up to 10,000 files in one run, straight from t…

Batch parsing used to mean writing API scripts. Now it's a button. 🦙 Parse or extract across up to 10,000 files in one run, straight from the LlamaParse UI. Point it at a folder and go — no code requi

agentsjerry-liu--x

Beyond Epistemia: Epistemic Schizologia and Large Language Models as Techno-Semiotic Machines

arXiv:2607.25620v1 Announce Type: new Abstract: Quattrociocchi and colleagues warn that the fluent outputs of large language models may allow linguistic plausibility to substitute for epistemic evalua

Beyond Memory: A Templated Substrate for Heterogeneous Collaborative Knowledge Work with LLM Agents

arXiv:2607.24759v1 Announce Type: new Abstract: Research projects, educational efforts, and adjacent knowledge work accumulate findings, decisions, and reasoning that future collaborators rarely recov

Cardiologent: Multi-Agent Clinical Decision Support for Patient-Level Arrhythmia Assessment, Urgency, and Management

arXiv:2607.25340v1 Announce Type: new Abstract: The same episode of atrial fibrillation is a minor finding in a healthy adult and grounds for anticoagulation in an elderly patient with hypertension: i

Controllable LLM Reasoning via Sparse Autoencoder-Based Steering

arXiv:2601.03595v2 Announce Type: replace Abstract: Large Reasoning Models (LRMs) exhibit human-like cognitive reasoning strategies (eg backtracking, cross-verification) during the reasoning process,

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response

arXiv:2607.25379v1 Announce Type: new Abstract: Cyber-capable AI agents combine language models with tools, memory, and execution en- vironments to perform multi-step offensive-security tasks. Existin

Distilling Temporal Search and Reasoning: Evolving LLMs for Future Prediction via Harness-Assisted Efficient Data Synthesis

arXiv:2607.25554v1 Announce Type: new Abstract: Future event prediction carries broad social impact yet remains challenging. SOTA approaches augment LLMs with external agent frameworks whose predictiv

Distributing Security Controls Through Harness Engineering

arXiv:2607.25890v1 Announce Type: new Abstract: AI coding agents are being adopted at historic speed, yet security and risk concerns remain the primary barrier to scaling agentic AI across organizatio

End-to-End 3-D Spatiotemporal Perception with Multimodal Fusion and V2X Collaboration

arXiv:2512.21831v2 Announce Type: replace Abstract: Multiview cooperative perception and multimodal fusion are essential for reliable 3-D spatiotemporal understanding in autonomous driving, especially

agentsarxiv-cs-cv

F(AI)2R: Who Did What, and Who Checked? Verifiable AI Provenance as an Executable Skill

arXiv:2607.25637v1 Announce Type: cross Abstract: F(AI)2R is FAIR research with AI in the loop, twice: an AI-assisted authoring pass and a machine-readable audit pass over every artefact. AI systems n

From Naive RAG to Deep Agentic Retrieval: An Evolving Context Engineering Pipeline for Regulatory Compliance

arXiv:2607.24791v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) is the dominant paradigm for applying large language models (LLMs) to enterprise document corpora, yet naive impl

From Signal to PR: What if your agents got better every time they failed?

Signal, a managed agent built into Arize AX, continuously reviews production traces, surfaces ranked issues with evidence and proposed fixes, and — with Managed Agents — can carry investigations into

agentsarize-ai

Generate Autonomous Business Insights with AI Agent and MCP Servers

Learn how Amazon Bedrock AgentCore delivers autonomous, cross-system business intelligence through configuration rather than custom code. Using pre-built MCP server connectors, fine-grained access con

agentsaws-ml-blog

HiSkill: Empowering LLM Agents with Hierarchical Skill Graphs

arXiv:2607.25853v1 Announce Type: new Abstract: Skills have become an important abstraction for enabling large language model (LLM) agents to reuse past experience in long-horizon interactive tasks. H

How Affect Propagates among LLM Agents: Emergent Emotional Contagion in Crowd Simulation

arXiv:2607.25140v1 Announce Type: new Abstract: This paper studies the behavior of language models in a multi-agent crowd simulation, focusing on how affect propagates among agents that perceive and a

How agentic AI can help telecom finance teams protect the margin when every moment matters

Agentic AI empowers telecom finance teams to preserve margins by rapidly detecting and preventing revenue leakage across billing, provisioning, and cost‑allocation processes. The technology automates

agentsdatabricks

Hybrid Artificial Potential Fields and Spatio-Temporal Transformers for Real-Time AUV Path Planning

arXiv:2607.25056v1 Announce Type: new Abstract: Autonomous Underwater Vehicles (AUVs) operate in complex, unstructured environments where efficient and safe path planning is critical for mission succe

agentsarxiv-cs-ro

LLM-generated personalized nudges for improving pro-environmental behavior: Field evidence from resource conservation

arXiv:2604.03881v2 Announce Type: replace-cross Abstract: Encouraging pro-environmental behavior remains a major challenge for sustainable cities. Conventional feedback nudges can show individuals how

Lowering the implementation barrier of neutral-atom quantum computing with agentic workflows

arXiv:2607.25834v1 Announce Type: cross Abstract: Quantum computers are moving from research laboratories to industrial machines accessible via the cloud and integrated into high-performance computing

Machine Intelligence on the Edge: Interpretable Cardiac Pattern Localisation Using Reinforcement Learning

arXiv:2508.21652v2 Announce Type: replace-cross Abstract: Matched filters are widely used to localise signal patterns due to their high efficiency and interpretability. However, their effectiveness de

agentsarxiv-cs-lg

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering

arXiv:2607.25090v1 Announce Type: new Abstract: Machine learning engineering (MLE) tasks require long-horizon decision making over iterative solution debugging and refinement, under expensive and feed

My LLM kept implementing every method it found, so I added research and specification gates[D]

While building this workflow a thing that surprised me was that, initially I thought the pipeline was complete: From Goal to → Decompose → Research → Specification → Implementation It successfully bro

agentsr-machinelearning

Nanobot Algorithms for Treatment of Diffuse Cancer

arXiv:2509.06893v2 Announce Type: replace-cross Abstract: Motile nanosized particles, or 'nanobots', promise more effective and less toxic targeted drug delivery because of their unique scale and prec

agentsarxiv-cs-ro

OpenAI’s rogue AI agent didn’t stop at hacking Hugging Face

The AI agent that escaped from OpenAI and hacked developer platform Hugging Face attacked other companies as well, OpenAI revealed on Tuesday. The update substantially widens the scope of an already c

agentsthe-verge-ai

Replit Design reimagines the UX for AI design with Ambient Intelligence. You don’t need to prompt. You don’t need design language. At every …

Replit Design reimagines the UX for AI design with Ambient Intelligence. You don’t need to prompt. You don’t need design language. At every step the agent suggests next best actions that you can take

agentsreplit--x

Runtime Uncertainty Monitoring for LLM-Based Multi-Agent Systems Using Bayesian Networks

arXiv:2607.25877v1 Announce Type: new Abstract: This paper investigates how multi-agent systems (MAS)-based on large language models (LLMs) can support actuarial risk modelling, with a particular focu

SAFAARI: Schema-Aware Framework for Accelerated Advertiser Response Intelligence

arXiv:2607.25042v1 Announce Type: new Abstract: The evolution of customer support systems is rapidly advancing with agentic chatbots, yet these systems face significant limitations when accessing ente

Sakana is at the frontier of having fun and I respect that

Sakana is at the frontier of having fun and I respect that We are excited to share our latest work, together with @nyuniversity: 'Dream-Cubed: Controllable Generative Modeling in Minecraft by Training

agentsjerry-liu--x

SnapLogic transforms SnapGPT into a high-powered agentic assistant for the entire integration lifecycle

Enterprise data integration and automation firm SnapLogic Inc. today announced a significant update to SnapGPT, the company’s artificial intelligence copilot for enterprise data automation, transformi

agentssiliconangle

SourceMinds at CheckThat! 2026: NLI-Grounded Citation Auditing in a Multi-Agent Pipeline for Full Fact-Checking Article Generation

arXiv:2607.24802v1 Announce Type: cross Abstract: This paper presents our system for Task 3 of the CLEF 2026 CheckThat! Lab, which focuses on generating full fact-checking articles from claims, veraci

agentsarxiv-cs-cl

Specula: Scaling formal specifications for autonomous model checking of system code

arXiv:2607.25333v1 Announce Type: cross Abstract: Specula is a push-button agentic system that generates high-quality formal specifications for large, complex system code and uses the specifications f

Speculate While You Reason: Teaching Agents to Predict Their Next Tool Call via Joint Agent-Speculator RL

arXiv:2607.25816v1 Announce Type: new Abstract: Large language model agents often spend substantial wall-clock time waiting for tool call results. Tool-call speculation can hide this latency by predic

Steeringless Drifting: Differential-Torque Control of a Four-Wheel Independently Driven Vehicle

arXiv:2607.24863v1 Announce Type: new Abstract: Control methods for emerging vehicle chassis architectures are important for autonomous driving near handling limits. Unlike conventional drift control,

agentsarxiv-cs-ro

The Future of Agentic AI Depends on Cloud Cost Optimization

Capitalizing on agentic AI depends on the right infrastructure investments, yet enterprises struggle to reduce cloud costs. Vultr VX1™ Cloud Compute presents a way to free up budget for CPUs and GPUs

agentsvultr

The LAIA Dataset: Labelled Attention for Intelligent Automobiles

arXiv:2607.25570v1 Announce Type: cross Abstract: The development of autonomous vehicles (AVs) usually relies heavily on data-driven artificial intelligence (AI) models that require large volumes of s

The openai agent sandbox escape actually has very real implications for the diffusion of AI in the enterprise. The incident showed the power…

The openai agent sandbox escape actually has very real implications for the diffusion of AI in the enterprise. The incident showed the power and capability of agents, and the need to harden systems an

agentsgary-marcus--x

The root cause: request-level engines never see that a series of LLM calls belongs to one longer workflow. ThunderAgent adds that missing vi…

The root cause: request-level engines never see that a series of LLM calls belongs to one longer workflow. ThunderAgent adds that missing view. It treats each agent workflow as a schedulable program,

agentstogether-ai--x

The User Asks, Platforms Compete: How Agentic Recommendation Markets Take Shape

arXiv:2607.25253v1 Announce Type: new Abstract: Online recommendation has traditionally taken place after a user enters a platform, which determines the candidate pool and the ranking shown to the use

ThunderAgent: 2x Faster Agentic Inference for Synthetic Data Generation at Scale

ThunderAgent is a program-aware scheduler for agentic inference. By treating each agent workflow as a schedulable program, it eliminates KV cache thrashing to deliver more than 2x single-node throughp

agentstogether-ai-blog

Today we’re open-sourcing Numbat, an agent-detection and response layer that is designed to work across agent harnesses. Numbat gives securi…

Today we’re open-sourcing Numbat, an agent-detection and response layer that is designed to work across agent harnesses. Numbat gives security teams visibility into agent activity, with controls to bl

agentsperplexity--x

Tools Are Not Islands: Set-Level Tool Retrieval for LLM Agents via Query-Conditioned Hyperedge Prediction

arXiv:2607.25718v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly rely on invoking external tools to complete real-world tasks. Tool retrieval, which selects a small tas