arXiv:2601.16443v1 Announce Type: new Abstract: Environments are the bottleneck for self-improving agents. Current terminal benchmarks were built for evaluation, not training; reinforcement learning requires a scalable pipeline, not just a dataset. We introduce Endless Terminals, a fully autonomous pipeline that procedurally generates terminal-use tasks without human annotation. The pipeline has four stages: generating diverse task descriptions, building and validating containerized environments, producing completion tests, and filtering for solvability. From this pipeline we obtain 3255 tasks spanning file operations, […]

Ver mais

Large-scale optimization is a key backbone of modern business decision-making. However, building these models is often labor-intensive and time-consuming. We address this by proposing LEAN-LLM-OPT, a LightwEight AgeNtic workflow construction framework for LLM-assisted large-scale OPTimization auto-formulation. LEAN-LLM-OPT takes as input a problem description together with associated datasets and orchestrates a team of LLM agents to produce an optimization formulation. Specifically, upon receiving a query, two upstream LLM agents dynamically construct a workflow that specifies, step-by-step, how optimization models […]

Ver mais

arXiv:2601.18833v1 Announce Type: new Abstract: Since the early 90s, the evolution of the Business Process Management (BPM) discipline has been punctuated by successive waves of automation technologies. Some of these technologies enable the automation of individual tasks, while others focus on orchestrating the execution of end-to-end processes. The rise of Generative and Agentic Artificial Intelligence (AI) is opening the way for another such wave. However, this wave is poised to be different because it shifts the focus from […]

Ver mais

Temperature is a crucial hyperparameter in large language models (LLMs), controlling the trade-off between exploration and exploitation during text generation. High temperatures encourage diverse but noisy outputs, while low temperatures produce focused outputs but may cause premature convergence. Yet static or heuristic temperature schedules fail to adapt to the dynamic demands of reinforcement learning (RL) throughout training, often limiting policy improvement. We propose Temperature Adaptive Meta Policy Optimization (TAMPO), a new framework that recasts temperature control as a […]

Ver mais

arXiv:2602.20285v1 Announce Type: new Abstract: Cryptographic computations are fundamental to modern computing, ensuring data confidentiality and integrity. However, these operations are highly vulnerable to power side-channel attacks that exploit variations in power consumption to leak sensitive information. Masking is a widely used countermeasure, yet software-based techniques often introduce significant performance overhead and implementation complexity, while fixed-function hardware masking lacks flexibility across diverse cryptographic algorithms. In this paper, we present CryptRISC, the first RISC-V-based processor that combines cryptographic acceleration […]

Ver mais

TL;DR I don’t know what I believe about AI anymore. Some days I’m excited. Some days I’m scared. Some days I’m just tired of the shouting. And honestly? That’s okay. We don’t need to pick a team. The useful thing isn’t being “for AI” or “against AI.” The useful thing is staying honest about how complicated this feels—and letting myself sit with the discomfort long enough to understand what’s actually at stake. Also, heavy metal got there before […]

Ver mais

arXiv:2603.26673v1 Announce Type: new Abstract: There are growing promises that Large Language Models (LLMs) can support students’ learning by providing explanations, feedback, and guidance. However, despite their rapid adoption and widespread attention, there is still limited empirical evidence regarding the pedagogical skills of LLMs. This article presents a comparative study of popular LLMs, namely, ChatGPT, DeepSeek, and Gemini, acting as teaching agents. An evaluation protocol was developed, focusing on three pedagogical strategies: Examples, Explanations and Analogies, and the […]

Ver mais

arXiv:2602.03973v1 Announce Type: new Abstract: Why do pretrained diffusion or flow-matching policies fail when the same task is performed near an obstacle, on a shifted support surface, or amid mild clutter? Such failures rarely reflect missing motor skills; instead, they expose a limitation of imitation learning under train-test shifts, where action generation is tightly coupled to training-specific spatial configurations and task specifications. Retraining or fine-tuning to address these failures is costly and conceptually misaligned, as the required behaviors […]

Ver mais