arXiv:2603.03456v1 Announce Type: new Abstract: Agentic coding agents are increasingly deployed autonomously, at scale, and over long-context horizons. Throughout an agent’s lifetime, it must navigate tensions between explicit instructions, learned values, and environmental pressures, often in contexts unseen during training. Prior work on model preferences, agent behavior under value tensions, and goal drift has relied on static, synthetic settings that do not capture the complexity of real-world environments. To this end, we introduce a framework built on OpenCode […]

Ver mais

arXiv:2603.00592v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models achieve over 95% success on standard benchmarks. However, through systematic experiments, we find that current state-of-the-art VLA models largely ignore language instructions. Prior work lacks: (1) systematic semantic perturbation diagnostics, (2) a benchmark that forces language understanding by design, and (3) linguistically diverse training data. This paper constructs the LangGap benchmark, based on a four-dimensional semantic perturbation method — varying instruction semantics while keeping the tabletop layout fixed — revealing […]

Ver mais

arXiv:2602.16758v1 Announce Type: new Abstract: This paper presents a smooth trajectory generation method for a four-degree-of-freedom parallel kinematic milling robot. The proposed approach integrates B-spline and Quaternion interpolation techniques to manage decoupled position and orientation data points. The synchronization of orientation and arc-length-parameterized position data is achieved through the fitting of smooth piece-wise Bezier curves, which describe the non-linear relationship between path length and tool orientation, solved via sequential quadratic programming. By leveraging the convex hull properties of […]

Ver mais

arXiv:2603.24714v1 Announce Type: new Abstract: Analog design often slows down because even small changes to device sizes or biases require expensive simulation cycles, and high-quality solutions typically occupy only a narrow part of a very large search space. While existing optimizers reduce some of this burden, they largely operate without the kind of judgment designers use when deciding where to search next. This paper presents an actor-critic optimization framework (ACOF) for analog sizing that brings that form of […]

Ver mais

arXiv:2603.07005v1 Announce Type: cross Abstract: A matching platform is a system that matches different types of participants, such as companies and job-seekers. In such a platform, merely maximizing the number of matches can result in matches being concentrated on highly popular participants, which may increase dissatisfaction among other participants, such as companies, and ultimately lead to their churn, reducing the platform’s profit opportunities. To address this issue, we propose a novel online learning problem, Combinatorial Allocation Bandits (CAB), […]

Ver mais

:::info Astounding Stories of Super-Science October 2022, by Astounding Stories is part of HackerNoon’s Book Blog Post series. You can jump to any chapter in this book here. THE MURDER OF ROGER ACKROYD – THE MAN WHO GREW VEGETABLE MARROWS Astounding Stories of Super-Science October 2022: THE MURDER OF ROGER ACKROYD – THE MAN WHO GREW VEGETABLE MARROWS By Agatha Christie ::: I told Caroline at lunch time that I should be dining at Fernly. She expressed no objection—on the […]

Ver mais

Dear RL fellows, My Ph.D. research focus was on Reinforcement Learning (offline, online, offline-to-online, policy regularization). I was definitely not in the top-tier labs, not working on the hottest topics: Robotics and LLM. All I have learned is out of fashion right now. I know people are now using VLA and diffusion policy, etc. I am now working in the LLM industry to do LLM-RL, which is definitely not REAL RL. Sadly, I really want to work in […]

Ver mais

arXiv:2505.21799v4 Announce Type: replace-cross Abstract: The ever-growing scale of deep learning models and training data underscores the critical importance of efficient optimization methods. While preconditioned gradient methods such as Adam and AdamW are the de facto optimizers for training neural networks and large language models, structure-aware preconditioned optimizers like Shampoo and Muon, which utilize the matrix structure of gradients, have demonstrated promising evidence of faster convergence. In this paper, we introduce a unifying framework for analyzing “matrix-aware” preconditioned […]

Ver mais