Home Knowledge Base Scaling Stateful AI Agents

Scaling Stateful AI Agents

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

DeltaBox: Scaling Stateful AI Agents with Millisecond-Level Sandbox Checkpoint/Rollback

arXiv:2605.22781v2 Announce Type: replace Abstract: LLM-powered AI agents require high-frequency state exploration (e.g., test-time tree search and reinforcement learning), relying on rapid checkpoint and rollback (C/R) of the complete sandbox state, including files and process state (e.g., memory, contexts, etc.). Existing mechanisms duplicate the entire state, causing hundreds of milliseconds to seconds of latency per C/R, which severely bottlenecks deep search and large-scale fan-outs....

arXiv CS 1d ago

Agyn: An Open-Source Platform for AI Agents with Scalable On-Demand Execution, Agent Definition as a Code, and Zero-Trust Access

arXiv:2605.27575v2 Announce Type: replace Abstract: As organizations move toward production deployments of AI agents, which execute non-deterministic workflows, maintain stateful sessions, and often operate with privileged access to internal services, the engineering challenge shifts from building individual agents to operating them at scale with proper isolation, governance, and security. In this paper we present Agyn, an open-source platform designed around three key principles tailored...

arXiv CS 8d ago

Experiments in Agentic AI for Science

arXiv:2605.26305v2 Announce Type: replace Abstract: This paper details two novel frameworks for developing autonomous, agentic AI in scientific workflows. Both systems leverage a hybrid Local Body, Remote Brain architecture via Google Colab, utilizing Python-based local orchestrators to invoke large language model (LLM) cloud backends. The first agent, DeepTS/DeepCollector, automates the large-scale curation, extraction, and deduplication of time-series datasets.

arXiv CS 8d ago

Morgan Stanley will soon open its trillion-dollar wealth management funnel to AI agents

Morgan Stanley will soon open a key wealth management funnel to artificial intelligence agents from thousands of corporations, CNBC has learned exclusively. It's one of the earliest instances of a major Wall Street bank opening its platforms to external AI tools. The move will allow clients' autonomous agents to pull data and insights directly from the firm's stock administration platforms, ShareWorks and Equity Edge, bypassing the traditional software interfaces built for human users,...

CNBC 7d ago

Ethical Hyper-Velocity (EHV): A Hardware-Rooted Zero-Trust Runtime Enforcement Architecture for Agentic AI Systems

arXiv:2605.17909v2 Announce Type: replace Abstract: As autonomous agentic systems scale across regulated critical infrastructures, the lack of mechanistic, hardware-rooted enforcement for high-frequency policy updates presents a fundamental safety gap. We present Ethical Hyper-Velocity (EHV), a governance-aware runtime enforcement architecture for agentic systems that combines Grammar-Constrained Decoding (GCD) for inline policy-constrained token generation, Causal Graph CRDT-based policy...

arXiv CS 8d ago

MetaWorld: Scaling Multi-Agent Video World Model from Single-view Video Data

arXiv:2606.02753v1 Announce Type: new Abstract: Video world models are a foundational generative technology for embodied AI and the Metaverse, yet existing approaches are inherently limited to a single agent observing from a single perspective. Extending these models to multi-agent settings introduces two critical challenges: data scarcity (coordinated multi-view recordings are prohibitively expensive to collect for general open-domain scenarios) and world state alignment (independently...

arXiv CS 7d ago

DPAgent-in-the-Middle: Agentic Defense and Repair Against AI-Groomed Deceptive Patterns

arXiv:2606.06914v1 Announce Type: new Abstract: Privacy deceptive patterns in web interfaces systematically manipulate users into disclosing personal data, yet existing defenses are fragmented, static, and increasingly vulnerable to manipulation by large language models. Moreover, data voids, areas of information scarcity within the web ecosystem, create fertile ground for adversaries to inject misleading content that can be scraped and learned by AI systems, thereby amplifying both...

arXiv CS 2d ago

Nvidia’s revenue blows past Wall Street expectations as AI boom accelerates

Nvidia has once again surpassed Wall Street's revenue expectations, signalling the continued strength of the global AI boom. The company's CEO stated that the expansion of AI infrastructure is accelerating rapidly, driven by the emergence of productive Agentic AI. This performance is being viewed by analysts as a key indicator of the ongoing investment in AI technology.

The Guardian Tech 20d ago

Building a LangGraph pipeline for production data engineering

LangGraph is becoming the default framework for teams building agentic AI workflows. That is both a good thing and a problem. The good part: it has real production pedigree, is actively maintained, and is used by teams doing serious work.

Hacker News 10d ago