Large language models (LLMs) increasingly serve as the central control unit of AI agents, yet current approaches remain limited in their ability to deliver personalized interactions. While Retrieval Augmented Generation enhances LLM capabilities by improving context-awareness, it lacks mechanisms to combine contextual information with user-specific data. Although personalization has been studied in fields such as human-computer interaction or cognitive science, existing perspectives largely remain conceptual, with limited focus on technical implementation. To address these gaps, we build on a unified definition of personalization as a conceptual foundation to derive technical requirements for adaptive, user-centered LLM-based agents. Combined with established agentic AI patterns such as multi-agent collaboration or multi-source retrieval, we present a framework that integrates persistent memory, dynamic coordination, self-validation, and evolving user profiles to enable personalized long-term interactions. We evaluate our approach on three public datasets using metrics such as retrieval accuracy, response correctness, or BertScore. We complement these results with a five-day pilot user study providing initial insights into user feedback on perceived personalization. The study provides early indications that guide future work and highlights the potential of integrating persistent memory and user profiles to improve the adaptivity and perceived personalization of LLM-based agents.

We introduce a new Multi-Agent System (MAS) - Allen, designed to address two core challenges in current MAS design: (1) improve system's policy autonomy, empowering agents to dynamically adapt their behavioral strategies, and (2) achieving the trade-off between collaborative efficiency, task supervision, and human oversight in complex network topologies. Our core insight is to redefine the basic execution unit in the MAS, allowing agents to autonomously form different patterns by combining these units. We have constructed a four-tier state architecture (Task, Stage, Agent, Step) to constrain system behavior from both task-oriented and execution-oriented perspectives. This achieves a unification of topological optimization and controllable progress. Allen grants unprecedented Policy Autonomy, while making a trade-off for the controllability of the collaborative structure. The project code has been open source at: https://github.com/motern88/Allen

Continual memory augmentation lets computer-using agents (CUAs) learn from prior interactions, but unvetted memories can encode domain-inappropriate or unsafe heuristics--spurious rules that drift from user intent and safety constraints. We introduce VerificAgent, a scalable oversight framework that treats persistent memory as an explicit alignment surface. VerificAgent combines (1) an expert-curated seed of domain knowledge, (2) iterative, trajectory-based memory growth during training, and (3) a post-hoc human fact-checking pass to sanitize accumulated memories before deployment. Evaluated on OSWorld productivity tasks and additional adversarial stress tests, VerificAgent improves task reliability, reduces hallucination-induced failures, and preserves interpretable, auditable guidance--without additional model fine-tuning. By letting humans correct high-impact errors once, the verified memory acts as a frozen safety contract that future agent actions must satisfy. Our results suggest that domain-scoped, human-verified memory offers a scalable oversight mechanism for CUAs, complementing broader alignment strategies by limiting silent policy drift and anchoring agent behavior to the norms and safety constraints of the target domain.

Large language models (LLMs) excel at rapid generation of text and multimodal content, yet they falter on transaction-style planning that demands ACID-like guarantees and real-time disruption recovery. We present Adaptive LLM Agent System (ALAS), a framework that tackles four fundamental LLM deficits: (i) absence of self-verification, (ii) context erosion, (iii) next-token myopia, and (iv) lack of persistent state. ALAS decomposes each plan into role-specialized agents, equips them with automatic state tracking, and coordinates them through a lightweight protocol. When disruptions arise, agents apply history-aware local compensation, avoiding costly global replanning and containing cascade effects. On real-world, large-scale job-shop scheduling benchmarks, ALAS sets new best results for static sequential planning and excels in dynamic reactive scenarios with unexpected disruptions. These gains show that principled modularization plus targeted compensation can unlock scalable and resilient planning with LLMs.

Video summarization has become an increasingly important task in the field of computer vision due to the vast amount of video content available on the internet. In this project, we propose a new method for natural language query based joint video summarization and highlight detection using multi-modal transformers. This approach will use both visual and audio cues to match a user's natural language query to retrieve the most relevant and interesting moments from a video. Our approach employs multiple recent techniques used in Vision Transformers (ViTs) to create a transformer-like encoder-decoder model. We evaluated our approach on multiple datasets such as YouTube Highlights and TVSum to demonstrate the flexibility of our proposed method.

Mischief can happen when AI is let loose in the world, just like any technology. The examples of AI gone wrong are numerous, the most vivid in recent memory being the disastrously bad performance of Amazon's facial recognition technology, Rekognition, which had a propensity to erroneously match members of some ethnic groups with criminal mugshots to a disproportionate extent. Given the risk, how can society know if a technology has been adequately refined to a level where it is safe to deploy? "This is a really good question, and one we are actively working on," Sergey Levine, assistant professor with the University of California at Berkeley's department of electrical engineering and computer science, told ZDNet by email this week. Levine and colleagues have been working on an approach to machine learning where the decisions of a software program are subjected to a critique by another algorithm within the same program that acts adversarially.

Do not take the Intel portfolio for granted. Sure, Intel products are present everywhere in our digitalised world. But this company is way more than silicon, hardware, and software. Not long ago, Intel introduced customisable silicon (such a win for their customers) and rapid-deployment options like Intel Select Solutions pre-verified configurations of hardware and software. Now, the conversation has turned to the built-in AI acceleration on the newest 3rd Gen Intel Xeon Scalable processors; quite the incredible AI-infused, data-intensive digital solution.

Virtual Flash Memory Summit (FMS), the world's premiere flash memory conference and exposition, announces a major program track on Storage for Artificial Intelligence and Machine Learning (AI/ML) Applications. The new track features talks on storage strategies, model training, workloads, NVMe and logical volumes, persistent memory, software-defined architectures, and accelerating the GPU data path. It also includes panels on model scalability and long-term horizons, plus a keynote by Geoffrey Burr, Distinguished Researcher at IBM Almaden Research Center. Virtual Flash Memory Summit 2020 will be held on November 10-12 and expects to draw more than 6,000 attendees. AI/ML applications require vast amounts of low latency, high-throughput flash storage.

With the rise of AI at the edge comes a whole host of new requirements for memory systems. Can today's memory technologies live up to the stringent demands of this challenging new application, and what do emerging memory technologies promise for edge AI in the long-term? The first thing to realize is that there is no standard "edge AI" application; the edge in its broadest interpretation covers all AI-enabled electronic systems outside the cloud. That might include "near edge," which generally covers enterprise data centers and on-premise servers. Further out are applications like computer vision for autonomous driving.

SAN FRANCISCO, September 17, 2019 -- Oracle Exadata Database Machine X8M, available today, sets a new bar and changes the dynamics of the database infrastructure market. Exadata X8M combines Intel Optane DC persistent memory and 100 gigabit remote direct memory access (RDMA) over Converged Ethernet (RoCE) to remove storage bottlenecks and dramatically increase performance for the most demanding workloads such as Online Transaction Processing (OLTP), analytics, IoT, fraud detection, and high frequency trading. "With Exadata X8M, we deliver in-memory performance with all the benefits of shared storage for both OLTP and analytics," said Juan Loaiza, executive vice president, mission-critical database technologies, Oracle. "Reducing response times by an order of magnitude using direct database access to shared persistent memory accelerates every OLTP application, and is a game changer for applications that need real-time access to large amounts of data such as fraud detection and personalized shopping." Exadata X8M helps customers perform existing tasks faster and accelerates time-to-insight, while also enabling deeper and more frequent analyses.