Agentic AI Swarm Optimization using Artificial Bee Colonization (ABC)Towards Data Science Using Agentic AI prompts with the Artificial Bee Colony algorithm to enhance unsupervised clustering and optimization workflows.
The post Agentic AI Swarm Optimization using Artificial Bee Colonization (ABC) appeared first on Towards Data Science.
Using Agentic AI prompts with the Artificial Bee Colony algorithm to enhance unsupervised clustering and optimization workflows.
The post Agentic AI Swarm Optimization using Artificial Bee Colonization (ABC) appeared first on Towards Data Science. Read More
Mistral AI Releases OCR 3: A Smaller Optical Character Recognition (OCR) Model for Structured Document AI at ScaleMarkTechPost Mistral AI has released Mistral OCR 3, its latest optical character recognition service that powers the company’s Document AI stack. The model, named as mistral-ocr-2512, is built to extract interleaved text and images from PDFs and other documents while preserving structure, and it does this at an aggressive price of $2 per 1,000 pages with
The post Mistral AI Releases OCR 3: A Smaller Optical Character Recognition (OCR) Model for Structured Document AI at Scale appeared first on MarkTechPost.
Mistral AI has released Mistral OCR 3, its latest optical character recognition service that powers the company’s Document AI stack. The model, named as mistral-ocr-2512, is built to extract interleaved text and images from PDFs and other documents while preserving structure, and it does this at an aggressive price of $2 per 1,000 pages with
The post Mistral AI Releases OCR 3: A Smaller Optical Character Recognition (OCR) Model for Structured Document AI at Scale appeared first on MarkTechPost. Read More
How to Build a High-Performance Distributed Task Routing System Using Kombu with Topic Exchanges and Concurrent WorkersMarkTechPost In this tutorial, we build a fully functional event-driven workflow using Kombu, treating messaging as a core architectural capability. We walk through step by step the setup of exchanges, routing keys, background workers, and concurrent producers, allowing us to observe a real distributed system. As we implement each component, we see how clean message flow,
The post How to Build a High-Performance Distributed Task Routing System Using Kombu with Topic Exchanges and Concurrent Workers appeared first on MarkTechPost.
In this tutorial, we build a fully functional event-driven workflow using Kombu, treating messaging as a core architectural capability. We walk through step by step the setup of exchanges, routing keys, background workers, and concurrent producers, allowing us to observe a real distributed system. As we implement each component, we see how clean message flow,
The post How to Build a High-Performance Distributed Task Routing System Using Kombu with Topic Exchanges and Concurrent Workers appeared first on MarkTechPost. Read More
A Coding Guide to Design a Complete Agentic Workflow in Gemini for Automated Medical Evidence Gathering and Prior Authorization SubmissionMarkTechPost In this tutorial, we devise how to orchestrate a fully functional, tool-using medical prior-authorization agent powered by Gemini. We walk through each component step by step, from securely configuring the model to building realistic external tools and finally constructing an intelligent agent loop that reasons, acts, and responds entirely through structured JSON. As we progress,
The post A Coding Guide to Design a Complete Agentic Workflow in Gemini for Automated Medical Evidence Gathering and Prior Authorization Submission appeared first on MarkTechPost.
In this tutorial, we devise how to orchestrate a fully functional, tool-using medical prior-authorization agent powered by Gemini. We walk through each component step by step, from securely configuring the model to building realistic external tools and finally constructing an intelligent agent loop that reasons, acts, and responds entirely through structured JSON. As we progress,
The post A Coding Guide to Design a Complete Agentic Workflow in Gemini for Automated Medical Evidence Gathering and Prior Authorization Submission appeared first on MarkTechPost. Read More
EDA in Public (Part 2): Product Deep Dive & Time-Series Analysis in PandasTowards Data Science Learn how to analyze product performance, extract time-series features, and uncover key seasonal trends in your sales data.
The post EDA in Public (Part 2): Product Deep Dive & Time-Series Analysis in Pandas appeared first on Towards Data Science.
Learn how to analyze product performance, extract time-series features, and uncover key seasonal trends in your sales data.
The post EDA in Public (Part 2): Product Deep Dive & Time-Series Analysis in Pandas appeared first on Towards Data Science. Read More
50,000 Copilot licences for Indian service companiesAI News Cognizant, Tata Consultancy Services, Infosys, and Wipro have announced plans to deploy more than 200,000 Microsoft Copilot licenses in their enterprises – over 50,000 per company – in what Microsoft is calling a new benchmark for enterprise-scale adoption of generative AI. The companies involved are framing the move as the implementation of a default tool
The post 50,000 Copilot licences for Indian service companies appeared first on AI News.
Cognizant, Tata Consultancy Services, Infosys, and Wipro have announced plans to deploy more than 200,000 Microsoft Copilot licenses in their enterprises – over 50,000 per company – in what Microsoft is calling a new benchmark for enterprise-scale adoption of generative AI. The companies involved are framing the move as the implementation of a default tool
The post 50,000 Copilot licences for Indian service companies appeared first on AI News. Read More
Penetration Testing of Agentic AI: A Comparative Security Analysis Across Models and Frameworkscs.AI updates on arXiv.org arXiv:2512.14860v1 Announce Type: cross
Abstract: Agentic AI introduces security vulnerabilities that traditional LLM safeguards fail to address. Although recent work by Unit 42 at Palo Alto Networks demonstrated that ChatGPT-4o successfully executes attacks as an agent that it refuses in chat mode, there is no comparative analysis in multiple models and frameworks. We conducted the first systematic penetration testing and comparative evaluation of agentic AI systems, testing five prominent models (Claude 3.5 Sonnet, Gemini 2.5 Flash, GPT-4o, Grok 2, and Nova Pro) across two agentic AI frameworks (AutoGen and CrewAI) using a seven-agent architecture that mimics the functionality of a university information management system and 13 distinct attack scenarios that span prompt injection, Server Side Request Forgery (SSRF), SQL injection, and tool misuse. Our 130 total test cases reveal significant security disparities: AutoGen demonstrates a 52.3% refusal rate versus CrewAI’s 30.8%, while model performance ranges from Nova Pro’s 46.2% to Claude and Grok 2’s 38.5%. Most critically, Grok 2 on CrewAI rejected only 2 of 13 attacks (15.4% refusal rate), and the overall refusal rate of 41.5% across all configurations indicates that more than half of malicious prompts succeeded despite enterprise-grade safety mechanisms. We identify six distinct defensive behavior patterns including a novel “hallucinated compliance” strategy where models fabricate outputs rather than executing or refusing attacks, and provide actionable recommendations for secure agent deployment. Complete attack prompts are also included in the Appendix to enable reproducibility.
arXiv:2512.14860v1 Announce Type: cross
Abstract: Agentic AI introduces security vulnerabilities that traditional LLM safeguards fail to address. Although recent work by Unit 42 at Palo Alto Networks demonstrated that ChatGPT-4o successfully executes attacks as an agent that it refuses in chat mode, there is no comparative analysis in multiple models and frameworks. We conducted the first systematic penetration testing and comparative evaluation of agentic AI systems, testing five prominent models (Claude 3.5 Sonnet, Gemini 2.5 Flash, GPT-4o, Grok 2, and Nova Pro) across two agentic AI frameworks (AutoGen and CrewAI) using a seven-agent architecture that mimics the functionality of a university information management system and 13 distinct attack scenarios that span prompt injection, Server Side Request Forgery (SSRF), SQL injection, and tool misuse. Our 130 total test cases reveal significant security disparities: AutoGen demonstrates a 52.3% refusal rate versus CrewAI’s 30.8%, while model performance ranges from Nova Pro’s 46.2% to Claude and Grok 2’s 38.5%. Most critically, Grok 2 on CrewAI rejected only 2 of 13 attacks (15.4% refusal rate), and the overall refusal rate of 41.5% across all configurations indicates that more than half of malicious prompts succeeded despite enterprise-grade safety mechanisms. We identify six distinct defensive behavior patterns including a novel “hallucinated compliance” strategy where models fabricate outputs rather than executing or refusing attacks, and provide actionable recommendations for secure agent deployment. Complete attack prompts are also included in the Appendix to enable reproducibility. Read More
Introducing SOCI indexing for Amazon SageMaker Studio: Faster container startup times for AI/ML workloadsArtificial Intelligence Today, we are excited to introduce a new feature for SageMaker Studio: SOCI (Seekable Open Container Initiative) indexing. SOCI supports lazy loading of container images, where only the necessary parts of an image are downloaded initially rather than the entire container.
Today, we are excited to introduce a new feature for SageMaker Studio: SOCI (Seekable Open Container Initiative) indexing. SOCI supports lazy loading of container images, where only the necessary parts of an image are downloaded initially rather than the entire container. Read More
Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contaminationcs.AI updates on arXiv.org arXiv:2507.10532v3 Announce Type: replace-cross
Abstract: Reasoning in large language models has long been a central research focus, and recent studies employing reinforcement learning (RL) have introduced diverse methods that yield substantial performance gains with minimal or even no external supervision. Surprisingly, some studies even suggest that random or incorrect reward signals can enhance performance. However, these breakthroughs are predominantly observed for the mathematically strong Qwen2.5 series on benchmarks such as MATH-500, AMC, and AIME, and seldom transfer to models like Llama, which warrants a more in-depth investigation. In this work, our empirical analysis reveals that pre-training on massive web-scale corpora leaves Qwen2.5 susceptible to data contamination in widely used benchmarks. Consequently, conclusions derived from contaminated benchmarks on Qwen2.5 series may be unreliable. To obtain trustworthy evaluation results, we introduce a generator that creates fully clean arithmetic problems of arbitrary length and difficulty, dubbed RandomCalculation. Using this leakage-free dataset, we show that only accurate reward signals yield steady improvements that surpass the base model’s performance boundary in mathematical reasoning, whereas random or incorrect rewards do not. Moreover, we conduct more fine-grained analyses to elucidate the factors underlying the different performance observed on the MATH-500 and RandomCalculation benchmarks. Consequently, we recommend that future studies evaluate models on uncontaminated benchmarks and, when feasible, test various model series to ensure trustworthy conclusions about RL and related methods.
arXiv:2507.10532v3 Announce Type: replace-cross
Abstract: Reasoning in large language models has long been a central research focus, and recent studies employing reinforcement learning (RL) have introduced diverse methods that yield substantial performance gains with minimal or even no external supervision. Surprisingly, some studies even suggest that random or incorrect reward signals can enhance performance. However, these breakthroughs are predominantly observed for the mathematically strong Qwen2.5 series on benchmarks such as MATH-500, AMC, and AIME, and seldom transfer to models like Llama, which warrants a more in-depth investigation. In this work, our empirical analysis reveals that pre-training on massive web-scale corpora leaves Qwen2.5 susceptible to data contamination in widely used benchmarks. Consequently, conclusions derived from contaminated benchmarks on Qwen2.5 series may be unreliable. To obtain trustworthy evaluation results, we introduce a generator that creates fully clean arithmetic problems of arbitrary length and difficulty, dubbed RandomCalculation. Using this leakage-free dataset, we show that only accurate reward signals yield steady improvements that surpass the base model’s performance boundary in mathematical reasoning, whereas random or incorrect rewards do not. Moreover, we conduct more fine-grained analyses to elucidate the factors underlying the different performance observed on the MATH-500 and RandomCalculation benchmarks. Consequently, we recommend that future studies evaluate models on uncontaminated benchmarks and, when feasible, test various model series to ensure trustworthy conclusions about RL and related methods. Read More
Agentic AI for Integrated Sensing and Communication: Analysis, Framework, and Case Studycs.AI updates on arXiv.org arXiv:2512.15044v1 Announce Type: new
Abstract: Integrated sensing and communication (ISAC) has emerged as a key development direction in the sixth-generation (6G) era, which provides essential support for the collaborative sensing and communication of future intelligent networks. However, as wireless environments become increasingly dynamic and complex, ISAC systems require more intelligent processing and more autonomous operation to maintain efficiency and adaptability. Meanwhile, agentic artificial intelligence (AI) offers a feasible solution to address these challenges by enabling continuous perception-reasoning-action loops in dynamic environments to support intelligent, autonomous, and efficient operation for ISAC systems. As such, we delve into the application value and prospects of agentic AI in ISAC systems in this work. Firstly, we provide a comprehensive review of agentic AI and ISAC systems to demonstrate their key characteristics. Secondly, we show several common optimization approaches for ISAC systems and highlight the significant advantages of generative artificial intelligence (GenAI)-based agentic AI. Thirdly, we propose a novel agentic ISAC framework and prensent a case study to verify its superiority in optimizing ISAC performance. Finally, we clarify future research directions for agentic AI-based ISAC systems.
arXiv:2512.15044v1 Announce Type: new
Abstract: Integrated sensing and communication (ISAC) has emerged as a key development direction in the sixth-generation (6G) era, which provides essential support for the collaborative sensing and communication of future intelligent networks. However, as wireless environments become increasingly dynamic and complex, ISAC systems require more intelligent processing and more autonomous operation to maintain efficiency and adaptability. Meanwhile, agentic artificial intelligence (AI) offers a feasible solution to address these challenges by enabling continuous perception-reasoning-action loops in dynamic environments to support intelligent, autonomous, and efficient operation for ISAC systems. As such, we delve into the application value and prospects of agentic AI in ISAC systems in this work. Firstly, we provide a comprehensive review of agentic AI and ISAC systems to demonstrate their key characteristics. Secondly, we show several common optimization approaches for ISAC systems and highlight the significant advantages of generative artificial intelligence (GenAI)-based agentic AI. Thirdly, we propose a novel agentic ISAC framework and prensent a case study to verify its superiority in optimizing ISAC performance. Finally, we clarify future research directions for agentic AI-based ISAC systems. Read More