All published intelligence, sovereign stack research, ecosystem news, and AI foundation model reviews.
Привет, я Бон-хва Пак из Ware. На конференции Pite Wash в Северной Америке в 2026 году я представлю постер под названием «Где живет блок». Когда память GP заполняется, VLAD принудительно переместит кэш KB на CPU или в хранилище. VLAD будет отслеживать местоположение каждого…
🤖 Google taught AI agents to independently improve their work The company opened access to Harness², a system that helps AI agents increase efficiency by up to 11% without retraining the model itself. Agents independently experiment with prompts, tools, memory and...
The Chinese guy showed what he is capable of: he single-handedly used AI agents to attack 1,200 websites. Today, Reuters reported on yet another Chinese-speaking hacker who, using AI agents, tried to attack more than 1,200 sites and successfully hacked sites associated with more than...
This is one of the coolest things I've seen this week. If you haven't played with Core 3 yet, you've got to try it. Now, this isn't sponsored. This is just an AI image editing tool that I've found to be really cool. So, check this out. I can upload like a YouTube thumbnail,…
arXiv:2610.24061v1 Announce Type: new Abstract: As teams of AI agents take on larger projects and long-standing open problems, agent collaboration offers another dimension for scaling inference-time compute. To understand what makes such collaboration effective and scalable, we…
arXiv:2610.23866v1 Announce Type: new Abstract: We introduce GardenBench, a benchmark with 11 test suites that evaluate the capabilities of Large Language Models (LLMs) across a range of tasks. By systematically prompting LLMs with various lightweight queries, we document…
arXiv:2610.23921v1 Announce Type: new Abstract: There is growing interest in automating business activities with Agentic Artificial Intelligence (AI) due to latter's seeming ease of use. Never has it been easier, or costlier, to do less with more. However, little is known about…
arXiv:2610.23962v1 Announce Type: new Abstract: We propose a controlled Large Language Model (LLM) workflow for explaining risk score differences using similar historical transactions. The workflow combines reference retrieval and contrastive SHapley Additive exPlanations (SHAP)…
arXiv:2610.24051v1 Announce Type: new Abstract: Text-to-Image (T2I) generative models have made significant progress in producing high-fidelity images from natural-language prompts. Alongside this progress, numerous benchmarks have been developed to evaluate capabilities such as…
arXiv:2610.24010v1 Announce Type: new Abstract: Generative AI is becoming an important medium for artistic creation, yet existing interactions often assume that creators can specify intentions in advance and accurately communicate them through text prompts. Artistic intentions,…
arXiv:2610.24006v1 Announce Type: new Abstract: Prominent AI safety discussions emphasize existential threats and catastrophic events, such as AI-enabled nuclear conflict or engineered biological outbreaks. This position paper argues that there is another type of AI risk that…
arXiv:2610.24024v1 Announce Type: new Abstract: Rare diseases (RDs) affect an estimated 300 million people globally, leaving patients to navigate a protracted diagnostic odyssey constrained by clinical scarcity and fragmented medical knowledge. Artificial intelligence (AI) has…
arXiv:2610.24133v1 Announce Type: new Abstract: We ask how much an autoregressive transformer retains of its prompt after generating $t$ tokens. Consider two different prompts followed by the same continuation text, so that any difference in their hidden states comes from the…
arXiv:2610.24090v1 Announce Type: new Abstract: Does persistent memory accumulated from previous attempts help an LLM agent solve new problems, and does memory design affect that benefit? We study programmatic Chinese-character drawing across five agent conditions attempting the…
arXiv:2610.24107v1 Announce Type: new Abstract: Context-to-LoRA methods encode documents as low-rank parameter updates, allowing language models to answer without retaining the source text in their decoding context. How reliably do these updates preserve facts and support their…
arXiv:2610.24108v1 Announce Type: new Abstract: Jointly pretrained multimodal encoders are a common way to combine modalities, while alternatives integrate their information during downstream training or inference. When does each approach win? We compare three paradigms,…
arXiv:2610.24177v1 Announce Type: new Abstract: Video generative models are an emerging tool for embodied agents: they can serve as scalable visual planners, generating videos that depict how to complete previously unseen tasks. However, executing these plans typically requires…
arXiv:2610.24194v1 Announce Type: new Abstract: Tool-using LLM agents repeatedly face decision points under uncertainty, choosing between autonomous action, additional information gathering, and human escalation. These decisions require balancing task success against interaction…
arXiv:2610.24199v1 Announce Type: new Abstract: Automating synthesis planning for small-molecule drug design requires chemical reasoners that are accurate as well as open to inspection and adaptation, yet frontier language models remain unreliable at predicting reaction outcomes…
arXiv:2610.24255v1 Announce Type: new Abstract: A coding agent combines a large language model (LLM) with a harness that plans, edits, and executes code. We study Cortex, a supervisory layer for pre-execution governance, requirement tracking, and iterative validation and repair.…
arXiv:2610.24248v1 Announce Type: new Abstract: Text-to-SQL systems typically assume a one-to-one mapping between natural-language queries and correct SQL translations. In practice, however, many queries are inherently ambiguous, admitting multiple valid interpretations that…
arXiv:2610.24264v1 Announce Type: new Abstract: As LLM-based agents are deployed with increasing autonomy in real-world environments, a critical failure mode emerges: agentic misalignment, where agents choose harmful actions over failure. However, existing safety benchmarks…
arXiv:2610.24229v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as a prominent paradigm for training reasoning models, but its computational cost makes efficient data selection increasingly important. Since training examples…
arXiv:2610.24266v1 Announce Type: new Abstract: Incomplete mobility trajectories can obscure the observations needed to identify important travel events and their endpoints. This study evaluates whether compact, locally deployed large language models (LLMs) can recover missing…
arXiv:2610.24268v1 Announce Type: new Abstract: Form 10-Q MD&A sections combine long-form management narrative with accounting and forward-looking information. Benchmarks for financial filings commonly evaluate question answering or numerical reasoning, leaving unclear whether…
arXiv:2610.24287v1 Announce Type: new Abstract: Search-augmented language models increasingly serve as long-horizon research agents, yet most open training methods assume a fixed user goal throughout search. We study mid-response steering, where users redirect a model during…
arXiv:2610.24298v1 Announce Type: new Abstract: Multi-agent LLM systems exchange messages before acting through tools, but message delivery, signing authority, and tool-side enforcement are separate trust boundaries. We represent them as communication, authorization, and…
arXiv:2610.24294v1 Announce Type: new Abstract: Tool-using agents are trained and evaluated almost exclusively with strong simulated users who state every detail clearly, yet real users are often weaker. We construct weak users by masking sentences of a simulated user's replies,…
arXiv:2610.24161v1 Announce Type: new Abstract: TorchTPU is an open-source collaboration between Google and Meta that introduces a native and principled PyTorch backend for Google TPUs. It enables seamless out-of-the-box model execution and TPU migration while delivering…
Meta AI models help speed up data analysis in scientific research.