Generative AI (GenAI) is expected to play a pivotal role in enabling autonomous optimization in future wireless networks. Within the ORAN architecture, Large Language Models (LLMs) can be specialized to generate xApps and rApps by leveraging specifications and API definitions from the RAN Intelligent Controller (RIC) platform. However, fine-tuning base LLMs for telecom-specific tasks remains expensive and resource-intensive. Retrieval-Augmented Generation (RAG) offers a practical alternative through in-context learning, enabling domain adaptation without full retraining. While traditional RAG systems rely on vector-based retrieval, emerging variants such as GraphRAG and Hybrid GraphRAG incorporate knowledge graphs or dual retrieval strategies to support multi-hop reasoning and improve factual grounding. Despite their promise, these methods lack systematic, metric-driven evaluations, particularly in high-stakes domains such as ORAN. In this study, we conduct a comparative evaluation of Vector RAG, GraphRAG, and Hybrid GraphRAG using ORAN specifications. We assess performance across varying question complexities using established generation metrics: faithfulness, answer relevance, context relevance, and factual correctness. Results show that both GraphRAG and Hybrid GraphRAG outperform traditional RAG. Hybrid GraphRAG improves factual correctness by 8%, while GraphRAG improves context relevance by 11%.

Path recommendation (PR) aims to generate travel paths that are customized to a user's specific preferences and constraints. Conventional approaches often employ explicit optimization objectives or specialized machine learning architectures; however, these methods typically exhibit limited flexibility and generalizability, necessitating costly retraining to accommodate new scenarios. This paper introduces an alternative paradigm that conceptualizes PR as a natural language generation task. We present PathGPT, a retrieval-augmented large language model (LLM) system that leverages historical trajectory data and natural language user constraints to generate plausible paths. The proposed methodology first converts raw trajectory data into a human-interpretable textual format, which is then stored in a database. Subsequently, a hybrid retrieval system extracts path-specific context from this database to inform a pretrained LLM. The primary contribution of this work is a novel framework that demonstrates how integrating established information retrieval and generative model components can enable adaptive, zero-shot path generation across diverse scenarios. Extensive experiments on large-scale trajectory datasets indicate that PathGPT's performance is competitive with specialized, learning-based methods, underscoring its potential as a flexible and generalizable path generation system that avoids the need for retraining inherent in previous data-driven models.

What if AI could do the same? Bilt, a company that offers local shopping and restaurant deals to renters, recently deployed several million agents with the hopes of doing just that. Bilt uses technology from a startup called Letta that allows agents to learn from previous conversations and share memories with one another. Using a process called "sleeptime compute," the agents decide what information to store in its long-term memory vault and what might be needed for faster recall. "We can make a single update to a [memory] block and have the behavior of hundreds of thousands of agents change," says Andrew Fitz, an AI engineer at Bilt. "This is useful in any scenario where you want fine-grained control over agents' context," he adds, referring to the text prompt fed to the model at inference time.

Sign up for the Slatest to get the most insightful analysis, criticism, and advice out there, delivered to your inbox daily. The other week, I was reading an email I'd written when a strange notion occurred to me. Would it perhaps be better, an unsettling new voice suddenly whispered, to leave it in? This is a thought that would've appalled me a year ago. As a professional writer, I have long prided myself on impeccable grammar, judiciously wielded punctuation, and (at times indulgent) verbosity.

This paper introduces a novel approach that leverages Large Language Models (LLMs) and Generative Agents to enhance time series forecasting by reasoning across both text and time series data.

Breaking down a problem into intermediate steps has demonstrated impressive performance in Large Language Model (LLM) reasoning.

On a Sunday morning in a Midwestern megachurch, worshippers step through sliding glass doors into a bustling lobby--unaware they've just passed through a gauntlet of biometric surveillance. High-speed cameras snap multiple face "probes" per second, before passing the results to a local neural network that distills these images into digital fingerprints. Before people find their seats, they are matched against an on-premises database--tagged with names, membership tiers, and watch-list flags--that's stored behind the church's firewall. This hypothetical scene reflects real capabilities increasingly woven into places of worship nationwide, where spiritual care and surveillance converge in ways few congregants ever realize. Where Big Tech's rationalist ethos and evangelical spirituality once mixed like oil and holy water, now they're combining to redraw the contours of community and pastoral power in modern spiritual life.

With the capability of modeling bidirectional contexts, denoising autoencoding based pretraining like BERT achieves better performance than pretraining approaches based on autoregressive language modeling. However, relying on corrupting the input with masks, BERT neglects dependency between the masked positions and suffers from a pretrain-finetune discrepancy.