arXiv:2602.13245v1 Announce Type: new Abstract: Wireless communication is evolving into an agent era, where numerous intelligent agents equipped with perception, reasoning, and interaction capabilities will operate in highly dynamic wireless environments. To complete diverse complex tasks, agent communication will play a critical role, which enables autonomous information exchange with external tools, services, and other agents. This trendy movement will dramatically increase spectrum demand and result in unprecedented challenges for spectrum management. However, current spectrum management paradigms, including static […]

Ver mais

arXiv:2604.02334v1 Announce Type: new Abstract: As large language models (LLM)-driven agents transition from isolated task solvers to persistent digital entities, the emergence of the Agentic Web, an ecosystem where heterogeneous agents autonomously interact and co-evolve, marks a pivotal shift toward Artificial General Intelligence (AGI). However, LLM-based multi-agent systems (LaMAS) are hindered by open-world issues such as scaling friction, coordination breakdown, and value dissipation. To address these challenges, we introduce Holos, a web-scale LaMAS architected for long-term ecological persistence. […]

Ver mais

arXiv:2602.15882v1 Announce Type: new Abstract: General vision-language models increasingly support unified spatiotemporal reasoning over long video streams, yet deploying such capabilities on robots remains constrained by the prohibitive latency of processing long-horizon histories and generating high-dimensional future predictions. To bridge this gap, we present FUTURE-VLA, a unified architecture that reformulates long-horizon control and future forecasting as a monolithic sequence-generation task. Adopting a dual-sided efficiency paradigm, FUTURE-VLA leverages a temporally adaptive compression strategy to maximize spatiotemporal information density, enabling […]

Ver mais

Growth hacks work, until they don’t. Most startups begin with quick wins: viral reels, aggressive ads, referral incentives, clever copy. For a while, momentum builds. Metrics go up. Dashboards look healthy. It feels like progress. Then something changes. Your customer acquisition costs start rising. Engagement flattens. What once felt like growth starts to feel like a constant fight. At this point, you usually assume the answer is another tactic. A new channel. A new funnel. A new trick. […]

Ver mais

arXiv:2602.09163v1 Announce Type: new Abstract: Scientific knowledge bases accelerate discovery by curating findings from primary literature into structured, queryable formats for both human researchers and emerging AI systems. Maintaining these resources requires expert curators to search relevant papers, reconcile evidence across documents, and produce ontology-grounded annotations – a workflow that existing benchmarks, focused on isolated subtasks like named entity recognition or relation extraction, do not capture. We present FlyBench to evaluate AI agents on end-to-end agentic ontology curation […]

Ver mais

arXiv:2509.22122v2 Announce Type: replace-cross Abstract: This study considers the estimation of the direct bias-correction term for estimating the average treatment effect (ATE). Let ${(X_i, D_i, Y_i)}_{i=1}^{n}$ be the observations, where $X_i$ denotes $K$-dimensional covariates, $D_i in {0, 1}$ denotes a binary treatment assignment indicator, and $Y_i$ denotes an outcome. In ATE estimation, $h_0(D_i, X_i) = frac{1[D_i = 1]}{e_0(X_i)} – frac{1[D_i = 0]}{1 – e_0(X_i)}$ is called the bias-correction term, where $e_0(X_i)$ is the propensity score. The bias-correction term […]

Ver mais

Current deep learning primitives dealing with temporal dynamics suffer from a fundamental dichotomy: they are either discrete and unstable (LSTMs) citep{pascanu_difficulty_2013}, leading to exploding or vanishing gradients; or they are continuous and dissipative (Neural ODEs) citep{dupont_augmented_2019}, which destroy information over time to ensure stability. We propose the textbf{Causal Hamiltonian Learning Unit} (pronounced: textit{clue}), a novel Physics-grounded computational learning primitive. By enforcing a Relativistic Hamiltonian structure and utilizing symplectic integration, a CHLU strictly conserves phase-space volume, as an attempt […]

Ver mais

Reinforcement Learning (RL) has achieved impressive success in post-training Large Language Models (LLMs) and Vision-Language Models (VLMs), with on-policy algorithms such as PPO, GRPO, and REINFORCE++ serving as the dominant paradigm. However, these methods discard all collected trajectories after a single gradient update, resulting in poor sample efficiency, particularly wasteful for agentic tasks where multi-turn environment interactions are expensive. While Experience Replay drives sample efficiency in classic RL by allowing agents to reuse past trajectories and prioritize informative […]

Ver mais

7B Models: Cheap, Fast… and Brutally Honest About Your Prompting If you’ve deployed a 7B model locally (or on a modest GPU), you already know the trade: Pros low cost low latency easy to self-host Cons patchy world knowledge weaker long-chain reasoning worse instruction-following unstable formatting (“JSON… but not really”) The biggest mistake is expecting 7B models to behave like frontier models. They won’t. But you can get surprisingly high-quality output if you treat prompting like systems design, […]

Ver mais