arXiv:2602.21424v1 Announce Type: new Abstract: Reinforcement learning (RL) agents under partial observability often condition actions on internally accumulated information such as memory or inferred latent context. We formalise such information-conditioned interaction patterns as behavioural dependency: variation in action selection with respect to internal information under fixed observations. This induces a probe-relative notion of $epsilon$-behavioural equivalence and a within-policy behavioural distance that quantifies probe sensitivity. We establish three structural results. First, the set of policies exhibiting non-trivial behavioural dependency […]

Ver mais

All year long, we’ve been riding across the vast plains of open-source code, investigating crimes, taking out vulnerabilities, and collecting trophies. Today, we decided to step into the dustiest saloon: an experienced sheriff leans against the bar and reminisces about ten most daring and dangerous bugs in the Wild West. Want an interesting story? For the entire year, we’ve been battling various bugs from C and C++ open-source projects. We caught each one, interrogated it, and recorded its […]

Ver mais

arXiv:2602.16873v1 Announce Type: new Abstract: As large language models from diverse providers converge toward comparable benchmark performance, the traditional paradigm of selecting a single best model per task yields diminishing returns. We argue that orchestration topology — the structural composition of how multiple agents are coordinated, parallelized, and synthesized — now dominates system-level performance over individual model capability. We present AdaptOrch, a formal framework for task-adaptive multi-agent orchestration that dynamically selects among four canonical topologies (parallel, sequential, hierarchical, […]

Ver mais

How are you, hacker? 🪐 What’s happening in tech today, February 14, 2026? The HackerNoon Newsletter brings the HackerNoon homepage straight to your inbox. On this day, we present you with these top quality stories. Courts Are Drowning in Cases. Can AI Save the Day Without Becoming a Liability? By @150sec [ 4 Min read ] As courts adopt AI to ease backlogs, experts warn of bias, opacity, and threats to judicial independence. Can efficiency coexist with due […]

Ver mais

Graph Neural Networks (GNNs) have become essential in high-stakes domains such as drug discovery, yet their black-box nature remains a significant barrier to trustworthiness. While self-explainable GNNs attempt to bridge this gap, they often rely on standard message-passing backbones that inherit fundamental limitations, including the 1-Weisfeiler-Lehman (1-WL) expressivity barrier and a lack of fine-grained interpretability. To address these challenges, we propose SymGraph, a symbolic framework designed to transcend these constraints. By replacing continuous message passing with discrete structural […]

Ver mais

TL;DR A lot of LLM eval pipelines treat “LLM-as-judge” as a rough but usable proxy for quality. I kept running into something that felt off: different judges would give very different scores, yet each judge was weirdly consistent with itself. This paper tries to measure that effect and show it’s not random noise. What I did: I set up a simple multi-judge pipeline and ran the same items through multiple “judge” models, multiple times, using the same rubric […]

Ver mais

arXiv:2601.19951v1 Announce Type: new Abstract: Symbolic music representation is a fundamental challenge in computational musicology. While grid-based representations effectively preserve pitch-time spatial correspondence, their inherent data sparsity leads to low encoding efficiency. Discrete-event representations achieve compact encoding but fail to adequately capture structural invariance and spatial locality. To address these complementary limitations, we propose Pianoroll-Event, a novel encoding scheme that describes pianoroll representations through events, combining structural properties with encoding efficiency while maintaining temporal dependencies and local spatial […]

Ver mais

Several variations of adaptive first-order and second-order optimization methods have been proposed to accelerate and scale the training of large language models. The performance of these optimization routines is highly sensitive to the choice of hyperparameters (HPs), which are computationally expensive to tune for large-scale models. Maximal update parameterization $(μ$P$)$ is a set of scaling rules which aims to make the optimal HPs independent of the model size, thereby allowing the HPs tuned on a smaller (computationally cheaper) […]

Ver mais

Immersive applications such as virtual and augmented reality impose stringent requirements on frame rate, latency, and synchronization between physical and virtual environments. To meet these requirements, an edge server must render panoramic content, predict user head motion, and transmit a portion of the scene that is large enough to cover the user viewport while remaining within wireless bandwidth constraints. Each portion produces two feedback signals: prediction feedback, indicating whether the selected portion covers the actual viewport, and transmission […]

Ver mais