LLM

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. ...

The GUI Agent Bottleneck: Stuck in Sparse Feedback Training LLM-based GUI agents to complete digital tasks—such as navigating mobile apps or automating workflows—faces a fundamental limitation: reward sparsity. Traditional reward formulations (Outcome Reward Models, or ORMs) provide feedback only at the end of a trajectory. If the task fails, the agent receives zero signal, regardless of how many useful intermediate steps it took. This severely limits credit assignment and slows learning, especially in environments with long action horizons. ...

When it comes to real-world problem solving, today’s LLMs face a critical dilemma: they can solve textbook problems well, but stumble when confronted with messy, open-ended challenges—like optimizing traffic in a growing city or managing fisheries under uncertain climate shifts. Enter ModelingAgent, an ambitious new framework that turns this complexity into opportunity. What Makes Real-World Modeling So Challenging? Unlike standard math problems, real-world tasks involve ambiguity, multiple valid solutions, noisy data, and cross-domain reasoning. They often require: ...

In the quest to make AI more trustworthy, few challenges loom larger than explaining sequential decision-making algorithms like Monte Carlo Tree Search (MCTS). Despite its success in domains from transit scheduling to game playing, MCTS remains a black box to most practitioners, generating decisions from expansive trees of sampled possibilities without accessible rationale. A new framework proposes to change that by fusing LLMs with formal logic to bring transparency and dialogue to this crucial planning tool1. ...