All published intelligence, sovereign stack research, ecosystem news, and AI foundation model reviews.
arXiv:2610.26942v1 Announce Type: new Abstract: Automated theorem provers often rely on sampling language models, but proof assistants like Lean reject each failed step with a precise error message --- information that pure sampling discards. To overcome this, we introduce a…
arXiv:2610.26964v1 Announce Type: new Abstract: Large language models (LLMs) struggle with classical planning, but benchmarks rarely distinguish structural difficulty from the difficulty of interpreting symbolic vocabulary. We examine seven STRIPS domains with BFS-optimal plan…
arXiv:2610.26995v1 Announce Type: new Abstract: LLM-based agents increasingly rely on reusable skills. However, scaling skill libraries makes efficient and accurate skill use difficult. Full skill loading incurs high token and runtime overhead. In contrast, flat semantic…
arXiv:2610.27027v1 Announce Type: new Abstract: Multi-agent LLM systems improve performance on clinical tasks, and that improvement is often read as evidence of a more trustworthy system. However, the two are not the same claim. A clinician acts on the stated reasoning and not…
arXiv:2610.27028v1 Announce Type: new Abstract: A poker agent can make a legal move and still make a strategically poor one. We ask whether compact AI agents can exhibit strategic behavior under hidden information and whether preference optimization can improve beyond static and…
arXiv:2610.27032v1 Announce Type: new Abstract: Large language model (LLM)-based agents have recently demonstrated outstanding performance in single-turn tasks, yet they continue to struggle with long-horizon tasks, particularly in environments without prior training. A key…
arXiv:2610.27119v1 Announce Type: new Abstract: LLM agents perform tasks over multiple steps and revise their actions based on feedback. As the total reasoning budget is often limited and must support future steps, the agent must choose between short and long reasoning before…
arXiv:2610.26887v1 Announce Type: new Abstract: Large language model (LLM) agents are evolving from conversational assistants into Cowork Agents capable of autonomous planning, tool use, and complex task execution. Financial analysis requires these agents to integrate…
arXiv:2610.27103v1 Announce Type: new Abstract: Recent Omni LLMs (OLLMs) have demonstrated remarkable capabilities in joint audio-visual reasoning, yet cross-modal hallucinations remain a major challenge. Existing mitigation methods mainly operate at the output level,…
arXiv:2610.27115v1 Announce Type: new Abstract: LLM agents act on the external world through tools and third-party skills, so a single executed action can cause irreversible harm. Existing defenses judge a proposed action without tracking whether its content comes from the user…
arXiv:2610.27120v1 Announce Type: new Abstract: Multimodal question answering (MMQA) is based on integrating heterogeneous data sources, selectively leveraging relevant modalities, and ignoring distractors. Existing approaches based on Multimodal Large Language Models (MLLMs)…
arXiv:2610.27156v1 Announce Type: new Abstract: Object: Motion artefacts remain a major limitation of routine two-dimensional T2-weighted turbo spin-echo (TSE) brain MRI, reducing diagnostic confidence and often necessitating repeated acquisitions. MoSAIK (Motion Search with AI…
arXiv:2610.27159v1 Announce Type: new Abstract: Public charging of electric vehicles (EVs) adds a large and synchronized load to the distribution feeders. In most networks, it is rare to overload a feeder at the same time. When it does happen, the consequences can be severe: an…
arXiv:2610.27203v1 Announce Type: new Abstract: Class-Incremental Learning (CIL) enables models to recognize new classes over time while retaining prior knowledge, but many real-world problems are compositional, where visual concepts arise from combinations of primitives such as…
arXiv:2610.27220v1 Announce Type: new Abstract: Recent work has explored continuous representations in place of discrete tokens during Chain-of-Thought (CoT) reasoning, often referred to as soft CoT. This is motivated by the idea that a mixture of token embeddings can represent…
arXiv:2610.27099v1 Announce Type: new Abstract: Clinical care, health-system operations and biomedical discovery depend on extracting reliable answers from patient records, yet applying diverse clinical questions across entire populations remains computationally expensive. Here…
arXiv:2610.27046v1 Announce Type: new Abstract: As AI systems begin to resolve open research problems, reliable verification becomes increasingly important. Formal mathematics provides a trusted framework for mathematical reasoning, enabling agents to produce machine-checkable…
arXiv:2610.27045v1 Announce Type: new Abstract: In recent years, physical artificial intelligence (physical AI) has experienced rapid development, capturing significant attention in academia and industry. However, the field has yet to reach consensus on its definition, technical…
arXiv:2610.26943v1 Announce Type: new Abstract: Mathematical reasoning is a fundamental capability for educational applications of Large Language Models (LLMs), where reliable problem solving requires not only correct answers but also coherent and verifiable reasoning processes.…
Амулья Вишванат объясняет, что физический ИИ сейчас на этапе создания основ.
Website admins, brace yourselves. Fixes for what are believed to be uncommonly severe vulnerabilities are scheduled to drop in a little more than 12 hours for PHP, a programming language that powers websites and Web applications everywhere. PHP maintainers said Monday that they…
Anthropic предложила законопроект по безопасности ИИ, который может блокировать модели при угрозе для жизни более 50 человек.
Google внедряет персонализированный ИИ Gemini в автомобили для удобства водителей.
🤖 The co-founder of Replika launched Wabi - an AI messenger that creates applications itself. Evgenia Kuida opened access to Wabi - a personal AI agent that combines a messenger and a mini-application generator. Instead of the usual chats, here you can create separate threads for different...
Modern advances in DNA technology and AI help solve old cases that have remained unsolved for decades. In one case, the company Othram used genetic genealogy to identify a suspect in a 1993 murder. Also…
On Tuesday, US District Judge Zachary Bluestone dismissed the lawsuit Ann Altman filed last year alleging that her brother, OpenAI CEO Sam Altman, had sexually abused her throughout her childhood. As reported earlier by The Guardian, the judge wrote that over the last year, Ann…
The proposed policy seems to offer protections against AI run amok but actually forbids federal agencies from blocking a model's release without the permission of a judge.
Before you share the Netflix documentary "AI Gone Rogue" take note. Clem Delangue, Hugging Face's co-founder who is featured in the film, says it went "full doomer mode" and isn't accurate.
SpaceX Reports AI Profit Growth, Beating Expectations.
Google is bringing Personal Intelligence to Gemini AI in your car. With this update, Gemini in Android Auto and cars with Google built-in can tap into your information across Google apps, including Gmail, Calendar, Maps, Photos, YouTube, and Search. As an example, Google says…