Autonomous Agents

Opening — Why this matters now Agentic AI is having a credibility problem. Not because agents can’t browse, code, or call tools—but because we still train them like they’re taking a final exam with no partial credit. Most agentic reinforcement learning (RL) systems reward outcomes, not process. Either the agent finishes the task correctly, or it doesn’t. For short problems, that’s tolerable. For long-horizon, tool-heavy reasoning tasks, it’s catastrophic. A single late-stage mistake erases an otherwise competent trajectory. ...

Opening — Why this matters now Inference-time scaling has quietly replaced parameter scaling as the most interesting battleground in large language models. With trillion-parameter training runs yielding diminishing marginal returns, the industry has pivoted toward how models think together, not just how big they are. Mixture-of-Agents (MoA) frameworks emerged as a pragmatic answer: run multiple models, stack their outputs, and hope collective intelligence beats individual brilliance. It worked—up to a point. But most MoA systems still behave like badly moderated panel discussions: everyone speaks, nobody listens. ...

Opening — Why this matters now Audio-first interfaces are everywhere. Voice assistants, call-center bots, in-car copilots, and accessibility tools all rely on large audio-language models (LALMs) that promise to hear and think at the same time. Yet in practice, something awkward happens: the same model that reasons fluently when reading text suddenly becomes hesitant, shallow, or just wrong when listening to speech. ...

Opening — Why this matters now Modern deep learning quietly assumes a comforting fiction: that training is memoryless. Given the current parameters (and maybe the optimizer buffers), tomorrow’s update shouldn’t care about yesterday’s data order, augmentation choice, or micro-step path. This assumption underwrites theory, stabilizes intuition, and keeps whiteboards clean. Reality, however, has been less cooperative. Practitioners know that order matters, momentum carries ghosts of past gradients, and small curriculum tweaks can echo far longer than expected. Yet until now, there has been no clean, operational way to measure whether training truly forgets—or merely pretends to. ...

Opening — Why this matters now For years, scaling AI meant one thing: train bigger models, then freeze them. At inference time, we search harder, sample wider, and hope brute force compensates for epistemic limits. This paper challenges that orthodoxy. It argues—quietly but decisively—that search alone is no longer enough. If discovery problems are truly out-of-distribution, then the model must be allowed to learn at test time. ...

Opening — Why this matters now LLM agents are getting longer memories, better tools, and more elaborate planning stacks—yet they still suffer from a strangely human flaw: emotional whiplash. An agent that sounds empathetic at turn 5 can become oddly cold at turn 7, then conciliatory again by turn 9. For applications that rely on trust, continuity, or persuasion—mental health tools, tutors, social robots—this instability is not a cosmetic issue. It’s a structural one. ...

Opening — Why this matters now Robotics has quietly entered an awkward phase. Models can see remarkably well and talk impressively about tasks—but when it comes to executing long-horizon, high-precision actions in the physical world, performance still collapses in the details. Grasp slips. Motions jitter. Multimodal uncertainty wins. At the same time, video generation models have undergone a renaissance. Large diffusion-based video models now encode temporal causality, implicit physics, and motion continuity at a scale robotics has never had access to. The obvious question follows: ...

Opening — Why this matters now Mixed-Integer Linear Programming (MILP) sits quietly underneath a surprising amount of modern infrastructure: logistics routing, auctions, facility placement, chip layout, resource allocation. When it works, no one notices. When it doesn’t, the solver spins for hours, racks up nodes, and quietly burns money. At the center of this tension is branch-and-bound—an exact algorithm that is elegant in theory and painfully sensitive in practice. Its speed hinges less on raw compute than on where it looks first. For decades, that decision has been guided by human-designed heuristics: clever, brittle, and wildly inconsistent across problem families. ...

Opening — Why this matters now Educational AI has entered its prompt era. Models are powerful, APIs are cheap, and everyone—from edtech startups to university labs—is tweaking prompts like seasoning soup. The problem? Most of this tweaking is still artisanal. Intuition-heavy. Barely documented. And almost never evaluated with the same rigor we expect from the learning science it claims to support. ...

Opening — Why this matters now Foreign Information Manipulation and Interference (FIMI) has quietly evolved from a niche security concern into a persistent, high‑tempo operational problem. Social media platforms now host influence campaigns that are faster, cheaper, and increasingly AI‑augmented. Meanwhile, defenders are expected to produce timely, explainable, and interoperable assessments—often across national and institutional boundaries. ...