Knowledge catalogue
arXiv:2607.02175v1 Announce Type: new Abstract: Multiple-choice medical benchmarks are increasingly saturated, and recent rubric-based evaluations such as HealthBench have shown that open-ended clinic
arXiv:2607.02432v1 Announce Type: new Abstract: Scalable and reliable grading of command-line examinations remains a challenge in computing education, where rising enrolments make manual marking diffi
arXiv:2607.02469v1 Announce Type: cross Abstract: Software tests and code evolve together: a code change should be followed by new or updated tests that record the new software behavior. Yet existing
arXiv:2607.00048v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used in exam- and certification-style question answering tasks, where their ability to retrieve, interpr
arXiv:2510.14113v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are transforming everyday applications, yet deployment in cybersecurity lags due to a lack of high-quality, domai
As generative AI tools continue to evolve, we believe it's more important than ever to know what's AI-generated and what isn't. That’s why @GoogleDeepMind launched SynthID in 2023—a technology that ad
arXiv:2606.29213v1 Announce Type: new Abstract: OCR systems, ranging from classical engines to specialised OCR vision-language models (OCR-VLMs) and frontier multimodal LLMs, report strong results on
arXiv:2510.14207v3 Announce Type: replace Abstract: Large Language Model (LLM) agents are powering a growing share of interactive web applications, yet remain vulnerable to misuse and harm. Prior jail
arXiv:2606.30613v1 Announce Type: new Abstract: We present Sequential Planning via Anchored Robotic Keypoints, SPARK, a training-free neurosymbolic manipulation system that reaches 43.7% on six LIBERO
We recently announced the preview of the BigQuery AI.AGG() function. With AI.AGG(), you can use natural-language instructions within a single line of SQL to summarize or synthesize information over mi
arXiv:2606.18142v3 Announce Type: replace Abstract: AI agents are moving from advisors to actors, booking travel, planning menus, and running procurement on behalf of users. Existing benchmarks for AI
As enterprises scale autonomous AI agents into production, enabling safe innovation requires robust architectural guardrails. AI agents connect across tools and datasets, so it’s essential to establis
arXiv:2606.26443v1 Announce Type: cross Abstract: A robot working alongside people must reason about what they have done, in what order, and with what intent. Video carries the spatial layouts, object
arXiv:2606.26079v1 Announce Type: new Abstract: Standard benchmarks for multimodal large language models (MLLMs) score each item on one canonical ordering and miss whether order-irrelevant shuffling c
arXiv:2606.22269v1 Announce Type: cross Abstract: We investigate the translation quality of current large language models (LLMs) for English-to-Hausa and English-to-Fongbe - two typologically distinct
arXiv:2606.22166v1 Announce Type: cross Abstract: Author rebuttals are the main post-submission window in peer review, but their effect on reviewer scores remains hard to measure because score updates
SQL is the industry standard for high-performance structured data analysis. However, expressing complex procedural logic, scientific computations, advanced string manipulations, or machine learning wo
You've got a working prototype in Google AI Studio. A React frontend, a Node.js backend, maybe a database. Now you want a live URL to share with your team, your users, or a friend who wants to try it.
arXiv:2606.11204v1 Announce Type: new Abstract: Accurate extraction of structured information from Safety Data Sheets (SDS) remains challenging in industrial safety due to heterogeneous document forma
Claude Fable 5 thinks document parsing is beneath it It is absolutely crushing on all reasoning-intensive/long horizon benchmarks: SWE-Bench Pro, FrontierCode, GDPval, Runescape, etc. But for document
arXiv:2606.11082v1 Announce Type: new Abstract: This study investigates cross-lingual distributional skew (the Shibboleth Effect) in frontier large language models (LLMs) subjected to sustained advers
arXiv:2606.08529v1 Announce Type: new Abstract: Published agent capability scores conflate what a model can do with what its scaffold lets it do, and the magnitude of this elicitation gap is not well
As enterprise storage footprints scale to billions of objects, AI applications and agentic workloads are fundamentally shifting the role of storage from a passive repository to the foundation of the d
arXiv:2606.05632v1 Announce Type: new Abstract: Within the past few years, the ability of Large Language Models (LLMs) to generate formal mathematical proofs has improved drastically. We provide a com
arXiv:2602.09464v2 Announce Type: replace-cross Abstract: Vericoding refers to the generation of formally verified code from rigorous specifications. Recent AI models show promise in vericoding, but a
arXiv:2510.01529v3 Announce Type: replace Abstract: Ball et al. recently established that prompt filtering for AI alignment faces a fundamental barrier: under standard cryptographic assumptions, no fi
arXiv:2602.04101v2 Announce Type: replace Abstract: We present Interfaze, a native hybrid model that fuses task-specific deep neural networks (CNNs and DNNs) directly into a transformer decoder throug
At Google Cloud, our goal is to let you run large-scale analytical and data science workloads with maximum efficiency so you can process big data pipelines, machine learning, and ETL tasks. We recentl
arXiv:2606.03641v1 Announce Type: new Abstract: We investigate whether large language models produce different medical triage recommendations for identical neurological symptoms when only the patient'
arXiv:2511.21731v2 Announce Type: replace-cross Abstract: We present the results of cognitive tests on conceptual combinations, performed using specific Large Language Models (LLMs) as test subjects.
arXiv:2606.02822v1 Announce Type: cross Abstract: Production LLM applications stack several defense families -- refusal-phrase filters, token-budget controls, model allowlists, rate limits, tool-regis
arXiv:2606.01136v1 Announce Type: new Abstract: Single-score translation metrics can conflate legitimate variation with error, a problem especially acute for classical languages where multiple defensi
arXiv:2602.16902v4 Announce Type: replace Abstract: We introduce LLM-Wikirace, a benchmark for evaluating planning, reasoning, and world knowledge in large language models (LLMs). In LLM-Wikirace, mod
arXiv:2606.00801v1 Announce Type: cross Abstract: Current approaches to LLM adversarial testing suffer from coverage gaps: manual red-teaming does not scale, LLM-as-attacker methods exhibit mode colla
arXiv:2606.01213v1 Announce Type: cross Abstract: Despite tremendous recent progress, current text-guided image editing methods still struggle with many aspects of editing involving instruction follow
arXiv:2605.30512v1 Announce Type: new Abstract: Generating physics diagrams from text requires strict adherence to physical laws. While current generative models produce visually plausible outputs, th
AI agents possess incredible reasoning capabilities and can perform increasingly complex actions. But the reliability of agentic outcomes depends entirely on the quality of the context they can access
arXiv:2605.30096v1 Announce Type: cross Abstract: Large language models (LLMs) can autonomously conduct multi-stage cyber attacks, but the consistency of their offensive behavior under repeated trials
arXiv:2605.29027v1 Announce Type: new Abstract: The use of Large Language Models (LLMs) is proliferating, yet their performance is observed to vary based on prompting styles and tones. In this study,
arXiv:2605.30052v1 Announce Type: cross Abstract: One-shot Program-of-Thought (PoT) emits a Python program that prints a primitive-action plan; a single invalid action silently invalidates the traject
arXiv:2605.26641v1 Announce Type: new Abstract: Unified multimodal embedding spaces have become the standard interface for cross-modal retrieval and multimodal RAG, and recent audio-video-text (AVT) e
arXiv:2605.23243v1 Announce Type: cross Abstract: We evaluate whether frontier LLMs are ready for cybersecurity through a dual-mode benchmark: white-box function-level vulnerability detection (VulnLLM
arXiv:2605.22971v1 Announce Type: new Abstract: Employees often struggle to identify ``who knows what,'' leading to organizational productivity losses. We investigate whether Large Language Models (LL
arXiv:2605.18937v1 Announce Type: new Abstract: Patient-managed Personal Health Records (PHRs) promises to empower patients to better understand their health; but information in the record is complex,
As models and harnesses improve, agents are taking on increasingly complex tasks that can run for hours or even days. But as we push agents to do more, this has surfaced a new operational problem: lon
We partnered with artists, designers, and builders to create new AI tools that solve real problems in their creative workflows. Here’s what’s new: — Introducing Google Pics in @GoogleWorkspace: A bran
arXiv:2605.18583v1 Announce Type: cross Abstract: Coding agents now run autonomously with shell, file, and network privileges. When a user issues a benign request, the agent sometimes does more than a
arXiv:2605.15734v1 Announce Type: new Abstract: The use of large language models to assess user states in conversational and adaptive systems is based on the assumption that the metrics used for such
arXiv:2511.09378v2 Announce Type: replace Abstract: A series of influential studies established that large language models cannot reliably solve even simple planning tasks. We show that the latest gen
Every device, user, and microservice generates data. Ingesting this data, extracting meaning and insights, and driving business decisions in real time has the potential to deliver transformational bus
arXiv:2605.14473v1 Announce Type: cross Abstract: The Context-Compliance Regime in Retrieval-Augmented Generation (RAG) occurs when retrieved context dominates the final answer even when it conflicts
arXiv:2511.08565v3 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly operate in social contexts, motivating analysis of how they express and shift moral judgments. In th
arXiv:2605.12746v1 Announce Type: cross Abstract: Monitoring the chain-of-thought (CoT) of reasoning models is a promising approach for detecting covert misbehavior (i.e., hidden objectives) in code g
arXiv:2605.09827v1 Announce Type: cross Abstract: We present Fashion Florence, a Florence-2 vision-language model fine-tuned with LoRA to extract structured fashion attributes from clothing images. Gi
arXiv:2605.09027v1 Announce Type: new Abstract: In multi-agent systems (MAS), a single deceptive agent can nullify all gains of an agentic AI collective and evade deployed defenses. However, existing
arXiv:2605.08437v1 Announce Type: cross Abstract: Existing benchmarks for legal AI focus primarily on tasks where LLMs must produce legal arguments or documents, yet the capacity to judge such argumen
arXiv:2602.00593v2 Announce Type: replace Abstract: Despite progress on general tasks, vision-language models (VLMs) still struggle with challenges that demand both fine-grained visual grounding and e
arXiv:2605.08658v1 Announce Type: cross Abstract: SKETCHVERIFY is a within-tier cost-performance policy, not a universal accuracy improvement. The operational question: a practitioner stuck with a sma
arXiv:2605.10408v1 Announce Type: cross Abstract: Testing robots requires assessing whether they perform their intended tasks correctly, dependably, and with high quality, a challenge known as the tes
arXiv:2605.07158v1 Announce Type: cross Abstract: Vector search and retrieval-augmented generation (RAG) rest on the assumption that cosine similarity between text embeddings reflects conceptual relat