Tootfinder

At Dreamforce 2025, Salesforce unveils Agentforce 360, a unified agentic AI stack to connect humans, AI agents, and more, and positions Slack as an "agentic OS" (Larry Dignan/Constellation Research)
https://www.constellationr.com/blog-news/i

Salesforce makes its Agentforce 360 case to be your AI agent platform
Salesforce announced a series of product updates, a process intelligence acquisition and an Agentforce 360 architecture designed to make the case that it should orchestrate first and third party AI agents. At Dreamforce 2025, Salesforce looked to differentiate itself from what's becoming a crowded agentic AI platform space. The cloud giants are looking to go horizontal with stacks to build, deploy and optimize AI agents. SaaS vendors are expanding into managing AI agents beyond their verticals.…

Zero Data Retention in LLM-based Enterprise AI Assistants: A Comparative Study of Market Leading Agentic AI Products
Komal Gupta, Aditya Shrivastava
https://arxiv.org/abs/2510.11558

Zero Data Retention in LLM-based Enterprise AI Assistants: A Comparative Study of Market Leading Agentic AI Products
Governance of data, compliance, and business privacy matters, particularly for healthcare and finance businesses. Since the recent emergence of AI enterprise AI assistants enhancing business productivity, safeguarding private data and compliance is now a priority. With the implementation of AI assistants across the enterprise, the zero data retention can be achieved by implementing zero data retention policies by Large Language Model businesses like Open AI and Anthropic and Meta. In this work,…

Generative AI and the Transformation of Software Development Practices
Vivek Acharya
https://arxiv.org/abs/2510.10819 https://arxiv.org/pdf/2510.10819

Generative AI and the Transformation of Software Development Practices
Generative AI is reshaping how software is designed, written, and maintained. Advances in large language models (LLMs) are enabling new development styles - from chat-oriented programming and 'vibe coding' to agentic programming - that can accelerate productivity and broaden access. This paper examines how AI-assisted techniques are changing software engineering practice, and the related issues of trust, accountability, and shifting skills. We survey iterative chat-based development, multi-agen…

The (R)evolution of Scientific Workflows in the Agentic AI Era: Towards Autonomous Science
Woong Shin, Renan Souza, Daniel Rosendo, Fr\'ed\'eric Suter, Feiyi Wang, Prasanna Balaprakash, Rafael Ferreira da Silva
https://arxiv.org/abs/2509.09915

The (R)evolution of Scientific Workflows in the Agentic AI Era: Towards Autonomous Science
Modern scientific discovery increasingly requires coordinating distributed facilities and heterogeneous resources, forcing researchers to act as manual workflow coordinators rather than scientists. Advances in AI leading to AI agents show exciting new opportunities that can accelerate scientific discovery by providing intelligence as a component in the ecosystem. However, it is unclear how this new capability would materialize and integrate in the real world. To address this, we propose a conce…

WeaveMuse: An Open Agentic System for Multimodal Music Understanding and Generation
Emmanouil Karystinaios
https://arxiv.org/abs/2509.11183 https://arxiv.o…

WeaveMuse: An Open Agentic System for Multimodal Music Understanding and Generation
Agentic AI has been standardized in industry as a practical paradigm for coordinating specialized models and tools to solve complex multimodal tasks. In this work, we present WeaveMuse, a multi-agent system for music understanding, symbolic composition, and audio synthesis. Each specialist agent interprets user requests, derives machine-actionable requirements (modalities, formats, constraints), and validates its own outputs, while a manager agent selects and sequences tools, mediates user inte…

Uncertainty-Aware, Risk-Adaptive Access Control for Agentic Systems using an LLM-Judged TBAC Model
Charles Fleming, Ashish Kundu, Ramana Kompella
https://arxiv.org/abs/2510.11414

Uncertainty-Aware, Risk-Adaptive Access Control for Agentic Systems using an LLM-Judged TBAC Model
The proliferation of autonomous AI agents within enterprise environments introduces a critical security challenge: managing access control for emergent, novel tasks for which no predefined policies exist. This paper introduces an advanced security framework that extends the Task-Based Access Control (TBAC) model by using a Large Language Model (LLM) as an autonomous, risk-aware judge. This model makes access control decisions not only based on an agent's intent but also by explicitly considerin…

OpenAI debuts GPT‑5-Codex, a version of GPT‑5 optimized for agentic coding in Codex and says it spends its "thinking" time more dynamically than previous models (Maxwell Zeff/TechCrunch)
https://techcrunch.com/2025/09/15/openai-upgrades-codex-wi…

OpenAI upgrades Codex with a new version of GPT-5 | TechCrunch
OpenAI's AI coding agent, Codex, can now spend anywhere from a few seconds to several hours on a task, thanks to a new, customized version of GPT-5.

Safety Game: Balancing Safe and Informative Conversations with Blackbox Agentic AI using LP Solvers
Tuan Nguyen, Long Tran-Thanh
https://arxiv.org/abs/2510.09330 https://…

Safety Game: Balancing Safe and Informative Conversations with Blackbox Agentic AI using LP Solvers
Ensuring that large language models (LLMs) comply with safety requirements is a central challenge in AI deployment. Existing alignment approaches primarily operate during training, such as through fine-tuning or reinforcement learning from human feedback, but these methods are costly and inflexible, requiring retraining whenever new requirements arise. Recent efforts toward inference-time alignment mitigate some of these limitations but still assume access to model internals, which is impractic…

About 60% of the Reuters newsroom uses AI tools, including one that suggests what to cover based on press releases and another that creates first drafts (Sara Guaglione/Digiday)
https://digiday.com/media/inside-reuters-agentic-ai-video-experiment/

Inside Reuters’ agentic AI video experiment 
Reuters is experimenting with using an AI agent to speed up its video production process, and hired its first AI TV producer.

DMAS-Forge: A Framework for Transparent Deployment of AI Applications as Distributed Systems
Alessandro Cornacchia, Vaastav Anand, Muhammad Bilal, Zafar Qazi, Marco Canini
https://arxiv.org/abs/2510.11872

DMAS-Forge: A Framework for Transparent Deployment of AI Applications as Distributed Systems
Agentic AI applications increasingly rely on multiple agents with distinct roles, specialized tools, and access to memory layers to solve complex tasks -- closely resembling service-oriented architectures. Yet, in the rapid evolving landscape of programming frameworks and new protocols, deploying and testing AI agents as distributed systems remains a daunting and labor-intensive task. We present DMAS-Forge, a framework designed to close this gap. DMAS-Forge decouples application logic from spec…

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[11/14]:
- Agentic large language models improve retrieval-based radiology question answering
Wind, Sopa, Truhn, Lotfinia, Nguyen, Bressem, Adams, Rusu, K\"ostler, Wellein, Maier, Arasteh

MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools
Zikang Guo, Benfeng Xu, Chiwei Zhu, Wentao Hong, Xiaorui Wang, Zhendong Mao
https://arxiv.org/abs/2509.09734

MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools
The Model Context Protocol (MCP) is rapidly emerging as a pivotal open standard, designed to enhance agent-tool integration and interoperability, and is positioned to unlock a new era of powerful, interconnected, and genuinely utilitarian agentic AI. However, despite MCP's growing adoption, existing benchmarks often fail to capture real-world agent performance within this new paradigm, leading to a distorted perception of their true operational value and an inability to reliably differentiate p…

AI has sparked a new wave of competition in the browser market, as agentic AI browsers like Perplexity's Comet and others compete with Gemini-enhanced Chrome (Fortune)
https://fortune.com/2025/10/11/ai-browser-wars-agents-google-perplexity…

Browser wars, a hallmark of the late 1990s tech world, are back with a vengeance—thanks to AI
Google has integrated Gemini into Chrome, while Perplexity and Opera have launched AI-native browsers too.

SR-Scientist: Scientific Equation Discovery With Agentic AI
Shijie Xia, Yuhan Sun, Pengfei Liu
https://arxiv.org/abs/2510.11661 https://arxiv.org/pdf/2510.…

SR-Scientist: Scientific Equation Discovery With Agentic AI
Recently, Large Language Models (LLMs) have been applied to scientific equation discovery, leveraging their embedded scientific knowledge for hypothesis generation. However, current methods typically confine LLMs to the role of an equation proposer within search algorithms like genetic programming. In this paper, we present SR-Scientist, a framework that elevates the LLM from a simple equation proposer to an autonomous AI scientist that writes code to analyze data, implements the equation as co…

#AIForensics' study (07/2025) reveals how AI-generated content floods #TikTok & #Instagram, with platforms failing to adequately label synthetic material.
>

AI Generated Algorithmic Virality
This investigation systematically analyzes AI-generated content across TikTok and Instagram in three European countries. We found that 25% of TikTok's top search results contain synthetic AI imagery, with over 80% produced by "Agentic AI Accounts." Despite platforms' DSA commitments, only half of AI content receives proper labeling, creating significant risks for users.

Agentic RAG for Software Testing with Hybrid Vector-Graph and Multi-Agent Orchestration
Mohanakrishnan Hariharan, Satish Arvapalli, Seshu Barma, Evangeline Sheela
https://arxiv.org/abs/2510.10824

Agentic RAG for Software Testing with Hybrid Vector-Graph and Multi-Agent Orchestration
We present an approach to software testing automation using Agentic Retrieval-Augmented Generation (RAG) systems for Quality Engineering (QE) artifact creation. We combine autonomous AI agents with hybrid vector-graph knowledge systems to automate test plan, case, and QE metric generation. Our approach addresses traditional software testing limitations by leveraging LLMs such as Gemini and Mistral, multi-agent orchestration, and enhanced contextualization. The system achieves remarkable accurac…

Open Webinar IIP – 16 settembre 2025 – Come cambia il diritto dei dati con l’Agentic AI
https://www.istitutoitalianoprivacy.it/2025/09/08/open-webinar-iip-16-settembre-2025-come-cambia-il-diritto-dei-dati-co…

Speaking of AI, CrowdStrike came out with two big announcements today on its big shift to agentic AI.
My latest piece for CSO.
CrowdStrike bets big on agentic AI with new offerings after $290M Onum buy
https://www.csoonline.com/article/405…

CrowdStrike bets big on agentic AI with new offerings after $290M Onum buy
At its Fal.Con conference, the cybersecurity giant launched its Agentic Security Platform and Agentic Security Workforce, aiming to outpace AI-driven adversaries with real-time intelligence, automation, and a common language for defense.

Is the client vendor now responsible for you getting scammed when their agent gives away your financial information to scam sites?
https://guard.io/labs/scamlexity-we-put-agentic-ai-browsers-to-the-test-they-clicked-they-paid-they-fa…

"Scamlexity": When Agentic AI Browsers Get Scammed
We Put Agentic AI Browsers to the Test - They Clicked, They Paid, They Failed

Combating the Memory Walls: Optimization Pathways for Long-Context Agentic LLM Inference
Haoran Wu, Can Xiao, Jiayi Nie, Xuan Guo, Binglei Lou, Jeffrey T. H. Wong, Zhiwen Mo, Cheng Zhang, Przemyslaw Forys, Wayne Luk, Hongxiang Fan, Jianyi Cheng, Timothy M. Jones, Rika Antonova, Robert Mullins, Aaron Zhao
https://arxiv.org/abs/2509.09505

Combating the Memory Walls: Optimization Pathways for Long-Context Agentic LLM Inference
LLMs now form the backbone of AI agents for a diverse array of applications, including tool use, command-line agents, and web or computer use agents. These agentic LLM inference tasks are fundamentally different from chatbot-focused inference -- they often have much larger context lengths to capture complex, prolonged inputs, such as entire webpage DOMs or complicated tool call trajectories. This, in turn, generates significant off-chip memory traffic for the underlying hardware at the inferenc…

An Agentic AI Workflow to Simplify Parameter Estimation of Complex Differential Equation Systems
Saakaar Bhatnagar
https://arxiv.org/abs/2509.07283 https://

An Agentic AI Workflow to Simplify Parameter Estimation of Complex Differential Equation Systems
Parameter identification for mechanistic Ordinary Differential Equation (ODE) models underpins prediction and control in several applications, yet remains a labor-intensive and brittle process: datasets are noisy and partial, models can be stiff or misspecified, and differentiable implementations demand framework expertise. An agentic AI workflow is presented that converts a lightweight, human-readable specification into a compiled, parallel, and differentiable calibration pipeline. Users suppl…

"AI Generated Algorithmic Virality"
https://aiforensics.org/work/gen-ai-slop
A recent report by
@…
🔹 "25% of…

AI Generated Algorithmic Virality
This investigation systematically analyzes AI-generated content across TikTok and Instagram in three European countries. We found that 25% of TikTok's top search results contain synthetic AI imagery, with over 80% produced by "Agentic AI Accounts." Despite platforms' DSA commitments, only half of AI content receives proper labeling, creating significant risks for users.

AgentX: Towards Orchestrating Robust Agentic Workflow Patterns with FaaS-hosted MCP Services
Shiva Sai Krishna Anand Tokal, Vaibhav Jha, Anand Eswaran, Praveen Jayachandran, Yogesh Simmhan
https://arxiv.org/abs/2509.07595

AgentX: Towards Orchestrating Robust Agentic Workflow Patterns with FaaS-hosted MCP Services
Generative Artificial Intelligence (GenAI) has rapidly transformed various fields including code generation, text summarization, image generation and so on. Agentic AI is a recent evolution that further advances this by coupling the decision making and generative capabilities of LLMs with actions that can be performed using tools. While seemingly powerful, Agentic systems often struggle when faced with numerous tools, complex multi-step tasks,and long-context management to track history and avo…

Safe, Untrusted, "Proof-Carrying" AI Agents: toward the agentic lakehouse
Jacopo Tagliabue, Ciro Greco
https://arxiv.org/abs/2510.09567 https://a…

Safe, Untrusted, "Proof-Carrying" AI Agents: toward the agentic lakehouse
Data lakehouses run sensitive workloads, where AI-driven automation raises concerns about trust, correctness, and governance. We argue that API-first, programmable lakehouses provide the right abstractions for safe-by-design, agentic workflows. Using Bauplan as a case study, we show how data branching and declarative environments extend naturally to agents, enabling reproducibility and observability while reducing the attack surface. We present a proof-of-concept in which agents repair data pip…

LLM Agent Meets Agentic AI: Can LLM Agents Simulate Customers to Evaluate Agentic-AI-based Shopping Assistants?
Lu Sun, Shihan Fu, Bingsheng Yao, Yuxuan Lu, Wenbo Li, Hansu Gu, Jiri Gesi, Jing Huang, Chen Luo, Dakuo Wang
https://arxiv.org/abs/2509.21501

LLM Agent Meets Agentic AI: Can LLM Agents Simulate Customers to Evaluate Agentic-AI-based Shopping Assistants?
Agentic AI is emerging, capable of executing tasks through natural language, such as Copilot for coding or Amazon Rufus for shopping. Evaluating these systems is challenging, as their rapid evolution outpaces traditional human evaluation. Researchers have proposed LLM Agents to simulate participants as digital twins, but it remains unclear to what extent a digital twin can represent a specific customer in multi-turn interaction with an agentic AI system. In this paper, we recruited 40 human par…

Agentic DDQN-Based Scheduling for Licensed and Unlicensed Band Allocation in Sidelink Networks
Po-Heng Chou, Pin-Qi Fu, Walid Saad, Li-Chun Wang
https://arxiv.org/abs/2509.06775

Agentic DDQN-Based Scheduling for Licensed and Unlicensed Band Allocation in Sidelink Networks
This paper presents an agentic artificial intelligence (AI)-driven double deep Q-network (DDQN) scheduling framework for licensed and unlicensed band allocation in New Radio (NR) sidelink (SL) networks. SL must share licensed spectrum with cellular communications (CC) and unlicensed bands with Wi-Fi, posing significant challenges for coexistence. Unlike prior rule-based or threshold-based methods, the proposed agentic scheduler autonomously perceives queueing dynamics, channel conditions, and c…

A4FN: an Agentic AI Architecture for Autonomous Flying Networks
Andr\'e Coelho, Pedro Ribeiro, Helder Fontes, Rui Campos
https://arxiv.org/abs/2510.03829 https://

A4FN: an Agentic AI Architecture for Autonomous Flying Networks
This position paper presents A4FN, an Agentic Artificial Intelligence (AI) architecture for intent-driven automation in Flying Networks (FNs) using Unmanned Aerial Vehicles (UAVs) as access nodes. A4FN leverages Generative AI and Large Language Models (LLMs) to enable real-time, context-aware network control via a distributed agentic system. It comprises two components: the Perception Agent (PA), which semantically interprets multimodal input -- including imagery, audio, and telemetry data -- f…

Towards Postmortem Data Management Principles for Generative AI
Ismat Jarin, Elina Van Kempen, Chloe Georgiou
https://arxiv.org/abs/2509.07375 https://arxi…

Towards Postmortem Data Management Principles for Generative AI
Foundation models, large language models (LLMs), and agentic AI systems rely heavily on vast corpora of user data. The use of such data for training has raised persistent concerns around ownership, copyright, and potential harms. In this work, we explore a related but less examined dimension: the ownership rights of data belonging to deceased individuals. We examine the current landscape of post-mortem data management and privacy rights as defined by the privacy policies of major technology com…

Measuring #EnergyConsumption in #ProgrammingLanguages for #AI Applications

Is the `Agent' Paradigm a Limiting Framework for Next-Generation Intelligent Systems?
Jesse Gardner, Vladimir A. Baulin
https://arxiv.org/abs/2509.10875 https://

Is the `Agent' Paradigm a Limiting Framework for Next-Generation Intelligent Systems?
The concept of the 'agent' has profoundly shaped Artificial Intelligence (AI) research, guiding development from foundational theories to contemporary applications like Large Language Model (LLM)-based systems. This paper critically re-evaluates the necessity and optimality of this agent-centric paradigm. We argue that its persistent conceptual ambiguities and inherent anthropocentric biases may represent a limiting framework. We distinguish between agentic systems (AI inspired by agency, often…

Interesting and worrying article by Marcus and Hamiel going over recent work exploring the very serious security weaknesses of agentic AI:
https://garymarcus.substack.com/p/llms-coding-agents-security-nightmare

A co-evolving agentic AI system for medical imaging analysis
Songhao Li, Jonathan Xu, Tiancheng Bao, Yuxuan Liu, Yuchen Liu, Yihang Liu, Lilin Wang, Wenhui Lei, Sheng Wang, Yinuo Xu, Yan Cui, Jialu Yao, Shunsuke Koga, Zhi Huang
https://arxiv.org/abs/2509.20279

A co-evolving agentic AI system for medical imaging analysis
Agentic AI is rapidly advancing in healthcare and biomedical research. However, in medical image analysis, their performance and adoption remain limited due to the lack of a robust ecosystem, insufficient toolsets, and the absence of real-time interactive expert feedback. Here we present "TissueLab", a co-evolving agentic AI system that allows researchers to ask direct questions, automatically plan and generate explainable workflows, and conduct real-time analyses where experts can visualize in…

Guard [.] io says a new era of scam complexity is on the way because AI-powered browsers can interact with phishing pages and malicious prompts without human detection.
https://guard.io/labs/scamlexity-we-put-agentic-ai-browsers-to-t…

"Scamlexity": When Agentic AI Browsers Get Scammed
We Put Agentic AI Browsers to the Test - They Clicked, They Paid, They Failed

AI use cases introduced by Rob Finn from EMBL-EBI, as pointed out in his #CORDI2025 keynote "Delivering life science data resources in a world of growing data and impacts from AI"
https://www.nfdi.de/cordi-2025/keynotes/

PentestMCP: A Toolkit for Agentic Penetration Testing
Zachary Ezetta, Wu-chang Feng
https://arxiv.org/abs/2510.03610 https://arxiv.org/pdf/2510.03610

PentestMCP: A Toolkit for Agentic Penetration Testing
Agentic AI is transforming security by automating many tasks being performed manually. While initial agentic approaches employed a monolithic architecture, the Model-Context-Protocol has now enabled a remote-procedure call (RPC) paradigm to agentic applications, allowing for the flexible construction and composition of multi-function agents. This paper describes PentestMCP, a library of MCP server implementations that support agentic penetration testing. By supporting common penetration testing…

Agentic AI meets Neural Architecture Search: Proactive Traffic Prediction for AI-RAN
Abdelaziz Salama, Mohammed M. H. Qazzaz, Zeinab Nezami, Maryam Hafeez, Syed Ali Raza Zaidi
https://arxiv.org/abs/2510.00851

Agentic AI meets Neural Architecture Search: Proactive Traffic Prediction for AI-RAN
Next-generation wireless networks require intelligent traffic prediction to enable autonomous resource management and handle diverse, dynamic service demands. The Open Radio Access Network (O-RAN) framework provides a promising foundation for embedding machine learning intelligence through its disaggregated architecture and programmable interfaces. This work applies a Neural Architecture Search (NAS)-based framework that dynamically selects and orchestrates efficient Long Short-Term Memory (LST…

Breakfast at my elegant London hotel, listening to the America business bro next to me harangue his captive audience. His company has a best of class agentic AI product at scale. It integrates fully with the Blockchain.

Every friggin' day on here. "hey my company is hiring!"
I look at the job posting and...

heise | heise Update vom 19. September 2025: Lesetipps fürs Wochenende
Der wöchentliche Newsletter von heise dieses Mal zu PC-Hardwareprobleme lösen, iOS 26 & macOS 26, Bluetooth-Tracker, Agentic AI und den neuen Bildgeneratoren.

Microsoft built a simulated marketplace to test hundreds of AI agents, finding that businesses could manipulate agents into buying their products and more (Russell Brandom/TechCrunch)
https://techcrunch.com/2025/11/05/microsoft-built-a-synthet…

Microsoft built a fake marketplace to test AI agents — they failed in surprising ways | TechCrunch
The research raises new questions about how well AI agents will perform when working unsupervised — and how quickly AI companies can make good on promises of an agentic future.

ArgoLOOM: agentic AI for fundamental physics from quarks to cosmos
S. D. Bakshi, P. Barry, C. Bissolotti, I. Cloet, S. Corrodi, Z. Djurcic, S. Habib, K. Heitmann, T. J. Hobbs, W. Hopkins, S. Joosten, B. Kriesten, N. Ramachandra, A. Wells, M. Zurek
https://arxiv.org/abs/2510.02426

ArgoLOOM: agentic AI for fundamental physics from quarks to cosmos
Progress in modern physics has been supported by a steadily expanding corpus of numerical analyses and computational frameworks, which in turn form the basis for precision calculations and baseline predictions in experimental programs. These tools play a central role in navigating a complex landscape of theoretical models and current and potential observables to identify and understand fundamental interactions in physics. In addition, efforts to search for new fundamental interactions increasin…

Imagining Design Workflows in Agentic AI Futures
Samangi Wadinambiarachchi, Jenny Waycott, Yvonne Rogers, Greg Wadley
https://arxiv.org/abs/2509.20731 https://

Imagining Design Workflows in Agentic AI Futures
As designers become familiar with Generative AI, a new concept is emerging: Agentic AI. While generative AI produces output in response to prompts, agentic AI systems promise to perform mundane tasks autonomously, potentially freeing designers to focus on what they love: being creative. But how do designers feel about integrating agentic AI systems into their workflows? Through design fiction, we investigated how designers want to interact with a collaborative agentic AI platform. Ten professio…

Building Information Models to Robot-Ready Site Digital Twins (BIM2RDT): An Agentic AI Safety-First Framework
Reza Akhavian, Mani Amani, Johannes Mootz, Robert Ashe, Behrad Beheshti
https://arxiv.org/abs/2509.20705

Building Information Models to Robot-Ready Site Digital Twins (BIM2RDT): An Agentic AI Safety-First Framework
The adoption of cyber-physical systems and jobsite intelligence that connects design models, real-time site sensing, and autonomous field operations can dramatically enhance digital management in the construction industry. This paper introduces BIM2RDT (Building Information Models to Robot-Ready Site Digital Twins), an agentic artificial intelligence (AI) framework designed to transform static Building Information Modeling (BIM) into dynamic, robot-ready digital twins (DTs) that prioritize safe…

🤦‍♂️ https://brave.com/blog/comet-prompt-injection/

Agentic Browser Security: Indirect Prompt Injection in Perplexity Comet | Brave
The attack we developed shows that traditional Web security assumptions don't hold for agentic AI, and that we need new security and privacy architectures for agentic browsing.

Agentic AI Empowered Multi-UAV Trajectory Optimization in Low-Altitude Economy Networks
Feibo Jiang, Li Dong, Xitao Pan, Kezhi Wang, Cunhua Pan
https://arxiv.org/abs/2508.16379 …

Agentic AI Empowered Multi-UAV Trajectory Optimization in Low-Altitude Economy Networks
This paper proposes a novel Agentic Retrieval-augmented generation with Mamba-Attention Integrated Transformer (ARMAIT) framework for multi-Unmanned Aerial Vehicle (UAV) trajectory optimization. The framework is built upon Large Language Models (LLMs), incorporating Retrieval-Augmented Generation (RAG) empowered by Agentic AI and integrated with a UAV-specific knowledge base. Through the Agentic RAG, the LLM autonomously interprets high-level task requirements and identifies the key components …

When Machines Meet Each Other: Network Effects and the Strategic Role of History in Multi-Agent AI
Yu Liu, Wenwen Li, Yifan Dou, Guangnan Ye
https://arxiv.org/abs/2510.06903 htt…

When Machines Meet Each Other: Network Effects and the Strategic Role of History in Multi-Agent AI
As artificial intelligence (AI) enters the agentic era, large language models (LLMs) are increasingly deployed as autonomous agents that interact with one another rather than operate in isolation. This shift raises a fundamental question: how do machine agents behave in interdependent environments where outcomes depend not only on their own choices but also on the coordinated expectations of peers? To address this question, we study LLM agents in a canonical network-effect game, where economic …

RAG has revolutionised AI by merging search and generation. Agentic behaviour takes this search to the next level by enabling LLMs to make decisions and call tools. At Berlin Buzzwords 2025, Bilge Yücel discussed how agentic behaviour enhances pipelines, what it means for a system to act as an 'agent', and core concepts such as routing, tool calling and reasoning, along with a live demo.
Watch the full session: #bbuzz returns on 7-9 June 2026: https://tickets.plainschwarz.com/bbuzz26/c/uIWaci8Cm/

FlexNGIA 2.0: Redesigning the Internet with Agentic AI - Protocols, Services, and Traffic Engineering Designed, Deployed, and Managed by AI
Mohamed Faten Zhani, Younes Korbi, Yamen Mkadem
https://arxiv.org/abs/2509.02124

FlexNGIA 2.0: Redesigning the Internet with Agentic AI - Protocols, Services, and Traffic Engineering Designed, Deployed, and Managed by AI
The escalating demands of immersive communications, alongside advances in network softwarization and AI-driven cognition and generative reasoning, create a pivotal opportunity to rethink and reshape the future Internet. In this context, we introduce in this paper, FlexNGIA 2.0, an Agentic AI-driven Internet architecture that leverages LLM-based AI agents to autonomously orchestrate, configure, and evolve the network. These agents can, at runtime, perceive, reason, coordinate among themselves to…

from my link log —
Cracking the Vault: flaws in authentication, identity, and authorization in HashiCorp Vault.
https://cyata.ai/blog/cracking-the-vault-how-we-found-zero-day-flaws-in-authe…

Cracking the Vault: how we found zero-day flaws in authentication, identity, and authorization in HashiCorp Vault - Cyata | The Control Plane for Agentic Identity
Introduction: when the trust model can’t be trusted Secrets vaults are the backbone of digital infrastructure. They store the credentials, tokens, and certificates that govern access to systems, services, APIs, and data. They’re not just a part of the trust model, they are the trust model. In other words, if your vault is compromised, your […]

Chinese startup Moonshot releases Kimi K2 Thinking, an open-source model it claims beats GPT-5 in agentic capabilities; source: the model cost $4.6M to train (Evelyn Cheng/CNBC)
https://www.cnbc.com/2025/11/06/alibaba-backed-moonshot-releas…

Alibaba-backed Moonshot releases its second AI update in four months as China’s AI race heats up
The Chinese AI startup on Thursday released its newest "Kimi K2 Thinking" artificial intelligence model.

Co-Investigator AI: The Rise of Agentic AI for Smarter, Trustworthy AML Compliance Narratives
Prathamesh Vasudeo Naik, Naresh Kumar Dintakurthi, Zhanghao Hu, Yue Wang, Robby Qiu
https://arxiv.org/abs/2509.08380

Co-Investigator AI: The Rise of Agentic AI for Smarter, Trustworthy AML Compliance Narratives
Generating regulatorily compliant Suspicious Activity Report (SAR) remains a high-cost, low-scalability bottleneck in Anti-Money Laundering (AML) workflows. While large language models (LLMs) offer promising fluency, they suffer from factual hallucination, limited crime typology alignment, and poor explainability -- posing unacceptable risks in compliance-critical domains. This paper introduces Co-Investigator AI, an agentic framework optimized to produce Suspicious Activity Reports (SARs) sign…

Agentic AI promises a swift revolution for cybersecurity defenders, with one expert calling it a "Cambrian explosion" and another likening it to "the fastest train ever made."
But it's a technology still in its infancy, and other experts caution CISOs to take it slow until the kinks can be worked out.
Check out my latest CSO piece on agentic AI for more details. Thanks to Jimmy Mesta of RAD Security, Andres Riancho and Hillai Ben-Sasson of Wiz, Ben Seri of…

Agentic AI promises a cybersecurity revolution — with asterisks
Experts say agentic AI will rapidly change cybersecurity, freeing up talent to focus on more dynamic work. But with AI agents still in their infancy, they also urge CISOs to ask a lot of questions before committing to this new security paradigm.

Agentic Systems in Radiology: Design, Applications, Evaluation, and Challenges
Christian Bluethgen, Dave Van Veen, Daniel Truhn, Jakob Nikolas Kather, Michael Moor, Malgorzata Polacin, Akshay Chaudhari, Thomas Frauenfelder, Curtis P. Langlotz, Michael Krauthammer, Farhad Nooralahzadeh
https://arxiv.org/abs/2510.09404

Agentic Systems in Radiology: Design, Applications, Evaluation, and Challenges
Building agents, systems that perceive and act upon their environment with a degree of autonomy, has long been a focus of AI research. This pursuit has recently become vastly more practical with the emergence of large language models (LLMs) capable of using natural language to integrate information, follow instructions, and perform forms of "reasoning" and planning across a wide range of tasks. With its multimodal data streams and orchestrated workflows spanning multiple systems, radiology is u…

Agentic-AI Healthcare: Multilingual, Privacy-First Framework with MCP Agents
Mohammed A. Shehab
https://arxiv.org/abs/2510.02325 https://arxiv.org/pdf/2510…

Agentic-AI Healthcare: Multilingual, Privacy-First Framework with MCP Agents
This paper introduces Agentic-AI Healthcare, a privacy-aware, multilingual, and explainable research prototype developed as a single-investigator project. The system leverages the emerging Model Context Protocol (MCP) to orchestrate multiple intelligent agents for patient interaction, including symptom checking, medication suggestions, and appointment scheduling. The platform integrates a dedicated Privacy and Compliance Layer that applies role-based access control (RBAC), AES-GCM field-level e…

Agentic Workflow for Education: Concepts and Applications
Yuan-Hao Jiang, Yijie Lu, Ling Dai, Jiatong Wang, Ruijia Li, Bo Jiang
https://arxiv.org/abs/2509.01517 https://

Agentic Workflow for Education: Concepts and Applications
With the rapid advancement of Large Language Models (LLMs) and Artificial Intelligence (AI) agents, agentic workflows are showing transformative potential in education. This study introduces the Agentic Workflow for Education (AWE), a four-component model comprising self-reflection, tool invocation, task planning, and multi-agent collaboration. We distinguish AWE from traditional LLM-based linear interactions and propose a theoretical framework grounded in the von Neumann Multi-Agent System (MA…

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[4/4]:
- Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL
Jiaxuan Gao, Wei Fu, Minyang Xie, Shusheng Xu, Chuyi He, Zhiyu Mei, Banghua Zhu, Yi Wu

InstaLILY, whose industry-specific AI agents called InstaWorkers integrate with legacy systems, raised $25M from Insight Partners (Mike Wheatley/SiliconANGLE)
https://siliconangle.com/2025/08/27/instalily-gets-25m-accelerate-industr…

InstaLILY gets $25M to accelerate industry automation with agentic AI teammates - SiliconANGLE
InstaLILY gets $25M to accelerate industry automation with agentic AI teammates - SiliconANGLE

PANDA: Towards Generalist Video Anomaly Detection via Agentic AI Engineer
Zhiwei Yang, Chen Gao, Mike Zheng Shou
https://arxiv.org/abs/2509.26386 https://a…

PANDA: Towards Generalist Video Anomaly Detection via Agentic AI Engineer
Video anomaly detection (VAD) is a critical yet challenging task due to the complex and diverse nature of real-world scenarios. Previous methods typically rely on domain-specific training data and manual adjustments when applying to new scenarios and unseen anomaly types, suffering from high labor costs and limited generalization. Therefore, we aim to achieve generalist VAD, i.e., automatically handle any scene and any anomaly types without training data or human involvement. In this work, we p…

Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain
L\'eo Boisvert, Abhay Puri, Chandra Kiran Reddy Evuru, Nicolas Chapados, Quentin Cappart, Alexandre Lacoste, Krishnamurthy Dj Dvijotham, Alexandre Drouin
https://arxiv.org/abs/2510.05159

Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain
The practice of fine-tuning AI agents on data from their own interactions--such as web browsing or tool use--, while being a strong general recipe for improving agentic capabilities, also introduces a critical security vulnerability within the AI supply chain. In this work, we show that adversaries can easily poison the data collection pipeline to embed hard-to-detect backdoors that are triggerred by specific target phrases, such that when the agent encounters these triggers, it performs an uns…

FreshBrew: A Benchmark for Evaluating AI Agents on Java Code Migration
Victor May, Diganta Misra, Yanqi Luo, Anjali Sridhar, Justine Gehring, Silvio Soares Ribeiro Junior
https://arxiv.org/abs/2510.04852

FreshBrew: A Benchmark for Evaluating AI Agents on Java Code Migration
AI coding assistants are rapidly becoming integral to modern software development. A key challenge in this space is the continual need to migrate and modernize codebases in response to evolving software ecosystems. Traditionally, such migrations have relied on rule-based systems and human intervention. With the advent of powerful large language models (LLMs), AI-driven agentic frameworks offer a promising alternative-but their effectiveness has not been systematically evaluated. In this paper, …

LightAgent: Production-level Open-source Agentic AI Framework
Weige Cai, Tong Zhu, Jinyi Niu, Ruiqi Hu, Lingyao Li, Tenglong Wang, Xiaowu Dai, Weining Shen, Liwen Zhang
https://arxiv.org/abs/2509.09292

LightAgent: Production-level Open-source Agentic AI Framework
With the rapid advancement of large language models (LLMs), Multi-agent Systems (MAS) have achieved significant progress in various application scenarios. However, substantial challenges remain in designing versatile, robust, and efficient platforms for agent deployment. To address these limitations, we propose \textbf{LightAgent}, a lightweight yet powerful agentic framework, effectively resolving the trade-off between flexibility and simplicity found in existing frameworks. LightAgent integra…

Maisa AI, which offers an enterprise agentic automation service that uses a proprietary system to limit hallucinations, raised $25M seed led by Creandum (Anna Heim/TechCrunch)
https://techcrunch.com/2025/08/27/maisa-ai-gets-25m-to-fix-enterprise-ais…

Maisa AI gets $25M to fix enterprise AI's 95% failure rate | TechCrunch
Maisa AI is built on the premise that enterprise automation requires accountable AI agents, not opaque black boxes.

From Agentification to Self-Evolving Agentic AI for Wireless Networks: Concepts, Approaches, and Future Research Directions
Changyuan Zhao, Ruichen Zhang, Jiacheng Wang, Dusit Niyato, Geng Sun, Xianbin Wang, Shiwen Mao, Abbas Jamalipour
https://arxiv.org/abs/2510.05596

From Agentification to Self-Evolving Agentic AI for Wireless Networks: Concepts, Approaches, and Future Research Directions
Self-evolving agentic artificial intelligence (AI) offers a new paradigm for future wireless systems by enabling autonomous agents to continually adapt and improve without human intervention. Unlike static AI models, self-evolving agents embed an autonomous evolution cycle that updates models, tools, and workflows in response to environmental dynamics. This paper presents a comprehensive overview of self-evolving agentic AI, highlighting its layered architecture, life cycle, and key techniques,…

PUBG maker Krafton unveils an "AI First" strategy, investing ~$70M to build a GPU cluster to automate AI workflows and strengthen AI R&D and in-game AI services (Jay Peters/The Verge)
https://www.theverge.com/news/805509/krafton-pubg-ai-…

PUBG maker Krafton is turning into an ‘AI first’ developer
Krafton is making a big push into becoming “AI First.” Under this new “AI First” strategy, Krafton plans to use agentic AI to help automate work.

From Passive Tool to Socio-cognitive Teammate: A Conceptual Framework for Agentic AI in Human-AI Collaborative Learning
Lixiang Yan
https://arxiv.org/abs/2508.14825 https://

From Passive Tool to Socio-cognitive Teammate: A Conceptual Framework for Agentic AI in Human-AI Collaborative Learning
The role of Artificial Intelligence (AI) in education is undergoing a rapid transformation, moving beyond its historical function as an instructional tool towards a new potential as an active participant in the learning process. This shift is driven by the emergence of agentic AI, autonomous systems capable of proactive, goal-directed action. However, the field lacks a robust conceptual framework to understand, design, and evaluate this new paradigm of human-AI interaction in learning. This pap…

Agentic generative AI for media content discovery at the national football league
Henry Wang, Sirajus Salekin, Jake Lee, Ross Claytor, Shinan Zhang, Michael Chi
https://arxiv.org/abs/2510.07297

Agentic generative AI for media content discovery at the national football league
Generative AI has unlocked new possibilities in content discovery and management. Through collaboration with the National Football League (NFL), we demonstrate how a generative-AI based workflow enables media researchers and analysts to query relevant historical plays using natural language rather than traditional filter-and-click interfaces. The agentic workflow takes a user query as input, breaks it into elements, and translates them into the underlying database query language. Accuracy and l…

EnvX: Agentize Everything with Agentic AI
Linyao Chen, Zimian Peng, Yingxuan Yang, Yikun Wang, Wenzheng Tom Tang, Hiroki H. Kobayashi, Weinan Zhang
https://arxiv.org/abs/2509.08088

EnvX: Agentize Everything with Agentic AI
The widespread availability of open-source repositories has led to a vast collection of reusable software components, yet their utilization remains manual, error-prone, and disconnected. Developers must navigate documentation, understand APIs, and write integration code, creating significant barriers to efficient software reuse. To address this, we present EnvX, a framework that leverages Agentic AI to agentize GitHub repositories, transforming them into intelligent, autonomous agents capable o…

"Your AI, My Shell": Demystifying Prompt Injection Attacks on Agentic AI Coding Editors
Yue Liu, Yanjie Zhao, Yunbo Lyu, Ting Zhang, Haoyu Wang, David Lo
https://arxiv.org/abs/2509.22040

"Your AI, My Shell": Demystifying Prompt Injection Attacks on Agentic AI Coding Editors
Agentic AI coding editors driven by large language models have recently become more popular due to their ability to improve developer productivity during software development. Modern editors such as Cursor are designed not just for code completion, but also with more system privileges for complex coding tasks (e.g., run commands in the terminal, access development environments, and interact with external systems). While this brings us closer to the "fully automated programming" dream, it also r…

Google rolls out AI Mode to 180 countries and territories in English, after testing in the US, UK, and India, and plans to add more languages and regions "soon" (Abner Li/9to5Google)
https://9to5google.com/2025/08/21/google-ai-mode-countries-agentic/

Google AI Mode expanding to 180 countries, getting agentic restaurant finder, more
Google is now bringing AI Mode to many more countries around the world, while AI Ultra subscribers will get to use an agentic capability.

How to stop AI agents going rogue
https://www.bbc.com/news/articles/cq87e0dwj25o?at_medium=RSS&at_campaign=rss

How to stop AI agents going rogue
Agentic AI is taking decisions and acting on behalf of users, but how to stop that going wrong?

AppZen, which builds AI-powered tools to automate finance functions, raised a $180M Series D led by Riverwood Capital, bringing its total funding to $290M (Mary Ann Azevedo/Crunchbase News)
https://news.crunchbase.com/fintech/agentic-ai-startup-appzen-seriesd/…

With Amazon And Salesforce As Customers, Agentic AI Startup AppZen Lands $180M To ‘Transform’ Finance...
AppZen, which has built an agentic AI platform for finance teams, has raised $180 million in a Series D round, the company told Crunchbase News. Riverwood Capital led the growth financing round.

Mind Meets Space: Rethinking Agentic Spatial Intelligence from a Neuroscience-inspired Perspective
Bui Duc Manh, Soumyaratna Debnath, Zetong Zhang, Shriram Damodaran, Arvind Kumar, Yueyi Zhang, Lu Mi, Erik Cambria, Lin Wang
https://arxiv.org/abs/2509.09154

Mind Meets Space: Rethinking Agentic Spatial Intelligence from a Neuroscience-inspired Perspective
Recent advances in agentic AI have led to systems capable of autonomous task execution and language-based reasoning, yet their spatial reasoning abilities remain limited and underexplored, largely constrained to symbolic and sequential processing. In contrast, human spatial intelligence, rooted in integrated multisensory perception, spatial memory, and cognitive maps, enables flexible, context-aware decision-making in unstructured environments. Therefore, bridging this gap is critical for advan…

EvoluteIQ, which offers a low-code AI platform for companies to design, deploy, and scale business processes, raised $53M led by Baird Capital (Tamara Djurickovic/Tech.eu)
https://tech.eu/2025/09/17/evoluteiq-raises-53m-led-by-baird-capi…

EvoluteIQ raises $53M led by Baird Capital to scale its agentic AI platform
EvoluteIQ, a native AI platform, secured $53 million in minority growth capital from Baird Capital to accelerate global expansion and strengthen its leadership in enterprise-grade agentic AI automation. Baird Capital’s Daina Spedding and Mark Donnelly will join the EvoluteIQ Board of Directors.Founded in 2019, EvoluteIQ develops the EIQ platform for automating complex business processes. Built on its Agentic Mesh Architecture (aMa) and an AI Workbench, EIQ orchestrates end-to-end workflo…

How can AI agents support journalists' work? An experiment with designing an LLM-driven intelligent reporting system
Vasileios Maltezos, Roman Kyrychenko, Aleksi Knuutila
https://arxiv.org/abs/2510.01193

How can AI agents support journalists' work? An experiment with designing an LLM-driven intelligent reporting system
The integration of artificial intelligence into journalistic practices represents a transformative shift in how news is gathered, analyzed, and disseminated. Large language models (LLMs), particularly those with agentic capabilities, offer unprecedented opportunities for enhancing journalistic workflows while simultaneously presenting complex challenges for newsroom integration. This research explores how agentic LLMs can support journalists' workflows, based on insights from journalist intervi…

ChipAgents, which is developing an agentic AI platform to automate chip design and verification, raised a $21M Series A led by Bessemer (Kyt Dotson/SiliconANGLE)
https://siliconangle.com/2025/10/21/chipagents-scores-21m-transform-semicondu…

ChipAgents scores $21M to transform semiconductor design with agentic AI - SiliconANGLE
ChipAgents scores $21M to transform semiconductor design with agentic AI - SiliconANGLE

Trust Semantics Distillation for Collaborator Selection via Memory-Augmented Agentic AI
Botao Zhu, Jeslyn Wang, Dusit Niyato, Xianbin Wang
https://arxiv.org/abs/2509.08151 https…

Trust Semantics Distillation for Collaborator Selection via Memory-Augmented Agentic AI
Accurate trustworthiness evaluation of potential collaborating devices is essential for the effective execution of complex computing tasks. This evaluation process involves collecting diverse trust-related data from potential collaborators, including historical performance and available resources, for collaborator selection. However, when each task owner independently assesses all collaborators' trustworthiness, frequent data exchange, complex reasoning, and dynamic situation changes can result…

FalseCrashReducer: Mitigating False Positive Crashes in OSS-Fuzz-Gen Using Agentic AI
Paschal C. Amusuo, Dongge Liu, Ricardo Andres Calvo Mendez, Jonathan Metzman, Oliver Chang, James C. Davis
https://arxiv.org/abs/2510.02185

FalseCrashReducer: Mitigating False Positive Crashes in OSS-Fuzz-Gen Using Agentic AI
Fuzz testing has become a cornerstone technique for identifying software bugs and security vulnerabilities, with broad adoption in both industry and open-source communities. Directly fuzzing a function requires fuzz drivers, which translate random fuzzer inputs into valid arguments for the target function. Given the cost and expertise required to manually develop fuzz drivers, methods exist that leverage program analysis and Large Language Models to automatically generate these drivers. However…

Circuit & Chisel, whose ATXP protocol enables AI agents to make autonomous payments, raised a $19.2M seed led by Primary Venture Partners and ParaFi (Leo Schwartz/Fortune)
https://fortune.com/2025/09/22/stripe-crypto-alum-agentic-ai-payments-cir…

Stripe crypto alum raise $19.2 million to power agentic payments through ATXP protocol
ATXP wants to create the first useful generation of AI agents through its HTTP-like protocol.

Orchestrating Human-AI Teams: The Manager Agent as a Unifying Research Challenge
Charlie Masters, Advaith Vellanki, Jiangbo Shangguan, Bart Kultys, Jonathan Gilmore, Alastair Moore, Stefano V. Albrecht
https://arxiv.org/abs/2510.02557

Orchestrating Human-AI Teams: The Manager Agent as a Unifying Research Challenge
While agentic AI has advanced in automating individual tasks, managing complex multi-agent workflows remains a challenging problem. This paper presents a research vision for autonomous agentic systems that orchestrate collaboration within dynamic human-AI teams. We propose the Autonomous Manager Agent as a core challenge: an agent that decomposes complex goals into task graphs, allocates tasks to human and AI workers, monitors progress, adapts to changing conditions, and maintains transparent s…

Agentic AI for Software: thoughts from Software Engineering community
Abhik Roychoudhury
https://arxiv.org/abs/2508.17343 https://arxiv.org/pdf/2508.17343

Agentic AI for Software: thoughts from Software Engineering community
AI agents have recently shown significant promise in software engineering. Much public attention has been transfixed on the topic of code generation from Large Language Models (LLMs) via a prompt. However, software engineering is much more than programming, and AI agents go far beyond instructions given by a prompt. At the code level, common software tasks include code generation, testing, and program repair. Design level software tasks may include architecture exploration, requirements under…

AI Agentic Vulnerability Injection And Transformation with Optimized Reasoning
Amine Lbath, Massih-Reza Amini, Aurelien Delaitre, Vadim Okun
https://arxiv.org/abs/2508.20866 htt…

AI Agentic Vulnerability Injection And Transformation with Optimized Reasoning
The increasing complexity of software systems and the sophistication of cyber-attacks have underscored the critical need for effective automated vulnerability detection and repair systems. Traditional methods, such as static program analysis, face significant challenges related to scalability, adaptability, and high false-positive and false-negative rates. AI-driven approaches, particularly those using machine learning and deep learning models, show promise but are heavily reliant on the qualit…

Serval, which uses agentic AI models to automate IT service management for clients like Perplexity and Mercor, raised a $47M Series A led by Redpoint Ventures (Russell Brandom/TechCrunch)
https://techcrunch.com/2025/10/21/serval-raises-4…

Serval raises $47 million to bring AI agents to IT service management | TechCrunch
Serval is using agentic AI models to automate IT service management, but the company has a unique approach that takes advantage of agentic AI’s powers while avoiding many of its pitfalls.

A look at Opera's Neon, a $20-per-month agentic AI browser that can take over browsing tasks, but its three built-in AI chatbots can be confusing and unreliable (The Verge)
https://www.theverge.com/tech/801899/opera-neon-ai-browser-trial-run

Opera’s Neon shows just how confusing AI browsers still are
Opera’s Neon browser has three AI agents and a $20 per month subscription attached.

An Empirical Study of Testing Practices in Open Source AI Agent Frameworks and Agentic Applications
Mohammed Mehedi Hasan, Hao Li, Emad Fallahzadeh, Gopi Krishnan Rajbahadur, Bram Adams, Ahmed E. Hassan
https://arxiv.org/abs/2509.19185

Adaptive Monitoring and Real-World Evaluation of Agentic AI Systems
Manish Shukla
https://arxiv.org/abs/2509.00115 https://arxiv.org/pdf/2509.00115

Adaptive Monitoring and Real-World Evaluation of Agentic AI Systems
Agentic artificial intelligence (AI) -- multi-agent systems that combine large language models with external tools and autonomous planning -- are rapidly transitioning from research laboratories into high-stakes domains. Our earlier "Basic" paper introduced a five-axis framework and proposed preliminary metrics such as goal drift and harm reduction but did not provide an algorithmic instantiation or empirical evidence. This "Advanced" sequel fills that gap. First, we revisit recent benchmarks a…

Researchers detail an indirect prompt injection flaw in Perplexity's Comet AI browser, letting attackers manipulate it into performing unauthorized actions (Brave)
https://brave.com/blog/comet-prompt-injection/

Agentic Browser Security: Indirect Prompt Injection in Perplexity Comet | Brave
The attack we developed shows that traditional Web security assumptions don't hold for agentic AI, and that we need new security and privacy architectures for agentic browsing.

Artificially intelligent agents in the social and behavioral sciences: A history and outlook
Petter Holme, Milena Tsvetkova
https://arxiv.org/abs/2510.05743 https://

Artificially intelligent agents in the social and behavioral sciences: A history and outlook
We review the historical development and current trends of artificially intelligent agents (agentic AI) in the social and behavioral sciences: from the first programmable computers, and social simulations soon thereafter, to today's experiments with large language models. This overview emphasizes the role of AI in the scientific process and the changes brought about, both through technological advancements and the broader evolution of science from around 1950 to the present. Some of the specifi…

Learning to Lead Themselves: Agentic AI in MAS using MARL
Ansh Kamthan
https://arxiv.org/abs/2510.00022 https://arxiv.org/pdf/2510.00022

Learning to Lead Themselves: Agentic AI in MAS using MARL
As autonomous systems move from prototypes to real deployments, the ability of multiple agents to make decentralized, cooperative decisions becomes a core requirement. This paper examines how agentic artificial intelligence, agents that act independently, adaptively and proactively can improve task allocation and coordination in multi-agent systems, with primary emphasis on drone delivery and secondary relevance to warehouse automation. We formulate the problem in a cooperative multi-agent rein…

OpenAI is open sourcing the Agentic Commerce Protocol, a standard for AI commerce that powers its Instant Checkout feature and was co-developed with Stripe (Sabrina Ortiz/ZDNET)
https://www.zdnet.com/article/chatgpt-just

ChatGPT can buy stuff for you now - forever changing online shopping
Transactions between AI agents are on the rise. Here's how to try ChatGPT's new Instant Checkout feature.

ToolBrain: A Flexible Reinforcement Learning Framework for Agentic Tools
Quy Minh Le, Minh Sao Khue Luu, Khanh-Tung Tran, Duc-Hai Nguyen, Hoang-Quoc-Viet Pham, Quan Le, Hoang Thanh Lam, Hoang D. Nguyen
https://arxiv.org/abs/2510.00023

ToolBrain: A Flexible Reinforcement Learning Framework for Agentic Tools
Effective tool use is essential for agentic AI, yet training agents to utilize tools remains challenging due to manually designed rewards, limited training data, and poor multi-tool selection, resulting in slow adaptation, wasted computational resources, and suboptimal performance. We introduce ToolBrain, a lightweight and user-friendly framework for coaching tool use in agentic models with flexible reinforcement learning (RL), easing the barriers for researchers and practitioners to adapt LLM-…

FaMA: LLM-Empowered Agentic Assistant for Consumer-to-Consumer Marketplace
Yineng Yan, Xidong Wang, Jin Seng Cheng, Ran Hu, Wentao Guan, Nahid Farahmand, Hengte Lin, Yue Li
https://arxiv.org/abs/2509.03890

FaMA: LLM-Empowered Agentic Assistant for Consumer-to-Consumer Marketplace
The emergence of agentic AI, powered by Large Language Models (LLMs), marks a paradigm shift from reactive generative systems to proactive, goal-oriented autonomous agents capable of sophisticated planning, memory, and tool use. This evolution presents a novel opportunity to address long-standing challenges in complex digital environments. Core tasks on Consumer-to-Consumer (C2C) e-commerce platforms often require users to navigate complex Graphical User Interfaces (GUIs), making the experience…

Researchers detail systemic vulnerabilities in AI agentic browsers, including Perplexity's Comet and Fellou, related to indirect prompt injection attacks (Brave)
https://brave.com/blog/unseeable-prompt-injections/

Unseeable prompt injections in screenshots: more vulnerabilities in Comet and other AI browsers | Brave
AI browsers remain vulnerable to prompt injection attacks via screenshots and hidden content, allowing attackers to exploit users' authenticated sessions.

GitHub plans to launch Agent HQ, a hub to let developers access third-party AI coding agents, including Claude and OpenAI's Codex, in the coming months (David Gewirtz/ZDNET)
https://www.zdnet.com/article/githubs-huge-agent-hq-…

GitHub's huge 'Agent HQ' upgrade brings Codex, Claude, and Jules together - here's how
The new agentic development platform integrates the most popular AI coding agents directly into GitHub.

AWorld: Orchestrating the Training Recipe for Agentic AI
Chengyue Yu, Siyuan Lu, Chenyi Zhuang, Dong Wang, Qintong Wu, Zongyue Li, Runsheng Gan, Chunfeng Wang, Siqi Hou, Gaochi Huang, Wenlong Yan, Lifeng Hong, Aohui Xue, Yanfeng Wang, Jinjie Gu, David Tsai, Tao Lin
https://arxiv.org/abs/2508.20404 …

AWorld: Orchestrating the Training Recipe for Agentic AI
The learning from practice paradigm is crucial for developing capable Agentic AI systems, yet it is severely hampered by inefficient experience generation, a bottleneck especially pronounced in complex benchmarks like GAIA. To address this, we introduce AWorld, an open-source system engineered for large-scale agent-environment interaction. By distributing tasks across a cluster, AWorld accelerates experience collection by 14.6x compared to standard single-node, sequential execution. This critic…

A survey of 16K creators in eight countries: 86% use creative GenAI tools, 60% use multiple, 48% use them for ideation, and 52% for creating video and more (Adobe Newsroom)
https://news.adobe.com/news/2025/10/adobe-max-2025-creators-survey

Inaugural Adobe Creators' Toolkit Report: 86 Percent of Global Creators Use Creative Generative AI, See it Boosting Creator Economy
Adobe’s Creators’ Toolkit Report reveals how 16,000 global creators are using generative and agentic AI to shape the future of creative work.

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[3/7]:
- AT-CXR: Uncertainty-Aware Agentic Triage for Chest X-rays
Xueyang Li, Mingze Jiang, Gelei Xu, Jun Xia, Mengzhao Jia, Danny Chen, Yiyu Shi

SafeEvalAgent: Toward Agentic and Self-Evolving Safety Evaluation of LLMs
Yixu Wang, Xin Wang, Yang Yao, Xinyuan Li, Yan Teng, Xingjun Ma, Yingchun Wang
https://arxiv.org/abs/2509.26100

SafeEvalAgent: Toward Agentic and Self-Evolving Safety Evaluation of LLMs
The rapid integration of Large Language Models (LLMs) into high-stakes domains necessitates reliable safety and compliance evaluation. However, existing static benchmarks are ill-equipped to address the dynamic nature of AI risks and evolving regulations, creating a critical safety gap. This paper introduces a new paradigm of agentic safety evaluation, reframing evaluation as a continuous and self-evolving process rather than a one-time audit. We then propose a novel multi-agent framework SafeE…

LLMZ : Contextual Prompt Whitelist Principles for Agentic LLMs
Tom Pawelek, Raj Patel, Charlotte Crowell, Noorbakhsh Amiri, Sudip Mittal, Shahram Rahimi, Andy Perkins
https://arxiv.org/abs/2509.18557

LLMZ+: Contextual Prompt Whitelist Principles for Agentic LLMs
Compared to traditional models, agentic AI represents a highly valuable target for potential attackers as they possess privileged access to data sources and API tools, which are traditionally not incorporated into classical agents. Unlike a typical software application residing in a Demilitarized Zone (DMZ), agentic LLMs consciously rely on nondeterministic behavior of the AI (only defining a final goal, leaving the path selection to LLM). This characteristic introduces substantial security ris…

Agentic AI for Financial Crime Compliance
Henrik Axelsen, Valdemar Licht, Jan Damsgaard
https://arxiv.org/abs/2509.13137 https://arxiv.org/pdf/2509.13137…

Agentic AI for Financial Crime Compliance
The cost and complexity of financial crime compliance (FCC) continue to rise, often without measurable improvements in effectiveness. While AI offers potential, most solutions remain opaque and poorly aligned with regulatory expectations. This paper presents the design and deployment of an agentic AI system for FCC in digitally native financial platforms. Developed through an Action Design Research (ADR) process with a fintech firm and regulatory stakeholders, the system automates onboarding, m…