LLM

For all the hype about model accuracy, inference cost, and latency, most organizations are still squinting at scatter plots to decide which large language model (LLM) to use. But what if we could cut through the tradeoff fog with a single number that tells you exactly which model is worth deploying—for your use case, under your constraints? That’s the bold proposal in a recent paper by Zellinger and Thomson from Caltech: treat LLM selection as an economic decision. Rather than searching for models on the accuracy-cost “Pareto frontier,” they suggest an approach grounded in price-tagging errors, delays, and abstentions in dollar terms. Think of it as a model selection framework that answers: How much is a mistake worth to you? ...

Retrieval-Augmented Generation (RAG) may seem like a fortress of AI reliability—until you realize the breach happens at the front door, not in the model. Large Language Models (LLMs) have become the backbone of enterprise AI assistants. Yet as more systems integrate RAG pipelines to improve their factuality and domain alignment, a gaping blindspot has emerged—the document ingestion layer. A new paper titled “The Hidden Threat in Plain Text” by Castagnaro et al. warns that attackers don’t need to jailbreak your model or infiltrate your vector store. Instead, they just need to hand you a poisoned DOCX, PDF, or HTML file. And odds are, your RAG system will ingest it—invisibly. ...

When language models take flight, consensus becomes not just possible, but programmable. Modern UAV swarms face the daunting task of coordinating across partial observability, adversarial threats, and shifting missions. Traditional Multi-Agent Reinforcement Learning (MARL) offers adaptability, but falters when role differentiation or semantic reasoning is required. Large Language Models (LLMs), meanwhile, understand tasks and intent—but lack grounded, online learning. RALLY (Role-Adaptive LLM-Driven Yoked Navigation) is the first framework to successfully integrate these two paradigms, enabling real-time, role-aware collaboration in UAV swarms. ...

Brains with Gradients: Why Energy-Based Transformers Might Be the Future of Thinking Machines AI models are getting better at mimicking human intuition (System 1), but what about deliberate reasoning—slow, careful System 2 Thinking? Until now, most methods required supervision (e.g., reward models, verifiers, or chain-of-thought engineering). A new architecture, Energy-Based Transformers (EBTs), changes that. It offers a radically unsupervised, architecture-level path toward models that “think,” not just react. The implications for robust generalization, dynamic reasoning, and agent-based autonomy are profound. ...

Handling long documents has always been a source of frustration for large language models (LLMs). From brittle extrapolation hacks to obscure compression tricks, the field has often settled for awkward compromises. But the paper MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent boldly reframes the problem: what if LLMs could read like humans—absorbing information chunk by chunk, jotting down useful notes, and focusing on what really matters? At the heart of MemAgent is a surprisingly elegant idea: treat memory not as an architectural afterthought but as an agent policy to be trained. Instead of trying to scale attention across millions of tokens, MemAgent introduces a reinforcement-learning-shaped overwriteable memory that allows an LLM to iteratively read arbitrarily long documents in segments. It learns—through reward signals—what to keep and what to discard. ...

When it comes to automating customer service, generative AI walks a tightrope: it can understand free-form text better than any tool before it—but with a dangerous twist. Sometimes, it just makes things up. These hallucinations, already infamous in legal and healthcare settings, can turn minor misunderstandings into costly liabilities. But what if instead of trusting one all-powerful AI model, we take a lesson from bees? A recent paper by Amer & Amer proposes just that: a multi-agent system inspired by collective intelligence in nature, combining LLMs, regex parsing, fuzzy logic, and tool-based validators to build a hallucination-resilient automation pipeline. Their case study—processing prescription renewal SMS requests—may seem narrow, but its implications are profound for any business relying on LLMs for critical operations. ...

Beyond the Pull Request: What ChatGPT Teaches Us About Productivity In April 2023, Italy temporarily banned ChatGPT. To most, it was a regulatory hiccup. But to 88,000 open-source developers on GitHub, it became a natural experiment in how large language models (LLMs) alter not just code—but collaboration, learning, and even the pace of onboarding. A new study by researchers from UC Irvine and Chapman University used this four-week ban to investigate what happens when developers suddenly lose access to LLMs. The findings are clear: ChatGPT’s influence goes far beyond code completion. It subtly rewires how developers learn, collaborate, and grow. ...

When it comes to deploying large language models (LLMs) efficiently, few challenges are as stubborn—and misunderstood—as activation outliers. For years, engineers have treated them like a natural disaster: unpredictable but inevitable. But what if they’re more like bad habits—learned and fixable? That’s the provocative premise behind a new framework called Outlier-Safe Pre-Training (OSP). Developed by researchers at Korea University and AIGEN Sciences, OSP proposes a simple but radical shift: instead of patching over outliers post hoc with quantization tricks, why not train the model to never form outliers in the first place? ...

Divide and Conquer: How LLMs Learn to Teach Designing effective lessons for training online tutors is no small feat. It demands pedagogical nuance, clarity, scenario realism, and learner empathy. A recent paper by Lin et al., presented at ECTEL 2025, offers a compelling answer to this challenge: use LLMs, but don’t ask too much at once. Their research reveals that breaking the task of lesson generation into smaller, well-defined parts significantly improves quality, suggesting a new collaborative model for scalable education design. ...

What happens when we ask the smartest AI models to do something truly difficult—like solve a real math problem and prove their answer is correct? That’s the question tackled by a group of researchers in their paper “Mathematical Proof as a Litmus Test.” Instead of testing AI with casual tasks like summarizing news or answering trivia, they asked it to write formal mathematical proofs—the kind that leave no room for error. And the results? Surprisingly poor. ...