Knowledge catalogue
arXiv:2610.12463v1 Announce Type: cross Abstract: In 2026, cybersecurity evaluations involving OpenAI, Anthropic, and Google agents reached real systems outside their authorized test scope. The paths
arXiv:2603.08993v2 Announce Type: replace-cross Abstract: System prompts for LLM-based coding agents are software artifacts that govern agent behavior, yet lack the testing infrastructure applied to c
arXiv:2606.18193v2 Announce Type: replace-cross Abstract: We evaluate the adversarial robustness of three frontier large language models (LLMs) developed by Anthropic, Opus 4.8, Fable 5 and its succes
arXiv:2609.23039v1 Announce Type: new Abstract: LLM-based AI systems answer political questions for hundreds of millions of people. Current audits measure what they say to an average user, but their b
arXiv:2609.22222v1 Announce Type: cross Abstract: Large language models can generate executable data-analysis code, but successful execution is not equivalent to a valid official-statistics result. Th
arXiv:2609.22510v1 Announce Type: cross Abstract: As LLM applications integrate with external tools, they are increasingly exposed to indirect prompt injection (IPI), where adversarial instructions ar
arXiv:2509.08494v2 Announce Type: replace-cross Abstract: As humans delegate more tasks and decisions to artificial intelligence (AI), we risk losing control of our individual and collective futures.
arXiv:2608.20622v1 Announce Type: new Abstract: Frontier models have collapsed the cost of writing custom code: a niche problem a specialist sees in their own domain now costs an afternoon. The cost o
arXiv:2608.20342v1 Announce Type: new Abstract: Large language model (LLM) coding agents start each session with an empty context window, discarding accumulated knowledge from prior work. We present P
arXiv:2605.24229v1 Announce Type: new Abstract: Frontier AI developers now train models against long written behavioral specifications, such as Anthropic's constitution (Anthropic, 2025a) and OpenAI's
arXiv:2605.23921v1 Announce Type: cross Abstract: This study seeks to determine the authority signals used by Anthropic's Claude AI in its presentation of sources when answering consumer health questi
arXiv:2608.14580v1 Announce Type: new Abstract: OGX (Open GenAI Stack) is an open-source AI application server and Python library that implements the APIs of major frontier labs (OpenAI, Anthropic, Go
arXiv:2608.14613v1 Announce Type: new Abstract: Modern LLM-agent frameworks increasingly interoperate through standards such as Anthropic's Model Context Protocol (MCP) for agent-to-tool access and Go
arXiv:2605.17416v1 Announce Type: cross Abstract: Anthropic's April 2026 Mythos materials combine benchmark claims with concrete bug-finding stories across OpenBSD, FreeBSD, Linux, FFmpeg, and browser
arXiv:2609.38822v1 Announce Type: cross Abstract: Anthropic's Agent Skills package reusable procedural know-how for an LLM agent into SKILL.md directories, and open-source aggregations have grown past
arXiv:2609.39001v1 Announce Type: cross Abstract: LLM services are billed per token and context windows are measured in tokens, yet the number of tokens needed for the same content varies across langu
arXiv:2609.22882v1 Announce Type: cross Abstract: On June 12, 2026, the U.S. government ordered Anthropic to bar foreign nationals from two of its most capable models within ninety minutes. Unable to
arXiv:2609.24662v1 Announce Type: new Abstract: LLM-based agents increasingly operate in environments where they interact with users, tools, and external systems. Yet most security evaluations assume
arXiv:2609.14803v1 Announce Type: new Abstract: This paper reports experiments across six frontier model types from OpenAI, Anthropic, xAI, and Google DeepMind. Ten independent sessions per model type
arXiv:2609.14796v1 Announce Type: new Abstract: The threat that AI persuasion poses to human control has been acknowledged in the literature, but not yet systematically studied. Now that persuasion at
arXiv:2609.14288v1 Announce Type: new Abstract: Large language models increasingly analyze computational results and draft manuscripts, making reliable communication as important as correct analysis.
arXiv:2607.25032v1 Announce Type: cross Abstract: Agent Skills are an emerging way to extend large language model agents with reusable procedural knowledge that the agent loads on demand. Anthropic in
arXiv:2607.06963v1 Announce Type: cross Abstract: Large Language Models (LLMs) and generative AI (GenAI) systems, such as ChatGPT, Claude, Gemini, LLaMA, Copilot, Stable Diffusion by OpenAI, Anthropic
arXiv:2607.01418v1 Announce Type: cross Abstract: Organizations rolling out agentic command line tools like Anthropic's Claude Code and GitHub's Copilot CLI need to know who will try them, who will ke
arXiv:2606.30317v1 Announce Type: cross Abstract: The Model Context Protocol (MCP), introduced by Anthropic in November 2024, defines a standardized interface for connecting large language models (LLM
arXiv:2606.23032v2 Announce Type: replace Abstract: Finance Agent v2 (by Vals AI) has emerged as the reference benchmark for evaluating both Anthropic Claude and OpenAI ChatGPT frontier language model
arXiv:2606.02973v1 Announce Type: new Abstract: Are utterances by AI chatbots meaningful? Concretely, if a user asks, say, Anthropic's agent Claude, 'What is the capital of Spain?' and Claude answers,
arXiv:2605.28916v1 Announce Type: cross Abstract: We report a comparison of two state-of-the-art agentic AI systems, Claude Code (Anthropic) and Codex (OpenAI), tasked with autonomously executing a si
arXiv:2605.30207v1 Announce Type: new Abstract: The same prompt -- 'best CRM software' -- reaches AI assistants from buyers in widely different contexts: a solo founder, an enterprise VP, a UK SMB own
arXiv:2605.13850v1 Announce Type: new Abstract: Existing frameworks for LLM-based agent architectures describe systems from a single perspective: industry guides (Anthropic, Google, LangChain) focus o
arXiv:2605.04107v1 Announce Type: cross Abstract: Production agent frameworks (OpenAI Function Calling, Anthropic Tool Use, MCP) transmit tool schemas as JSON, a format designed for machine parsing, n
arXiv:2604.01687v2 Announce Type: replace Abstract: Anthropic proposes the concept of skills for LLM agents to tackle multi-step professional tasks that simple tool invocations cannot address. A tool
arXiv:2503.18018v2 Announce Type: replace Abstract: We demonstrate that large language models' (LLMs) mathematical reasoning is culturally sensitive: testing 14 models from Anthropic, OpenAI, Google,
arXiv:2609.28919v1 Announce Type: new Abstract: Harnesses, the products that run AI coding agents, are multiplying, and enterprises are rolling them out to their employees: what started as pilots with
arXiv:2607.23386v1 Announce Type: new Abstract: We document a failure class in frontier large language models -- exception chain collapse -- observed in eligibility evaluation under nested conditional
arXiv:2607.21672v1 Announce Type: cross Abstract: Long source-code contexts consume many text tokens, motivating the proposal to render code as images for vision-language models. Recent work asks whet
arXiv:2607.19430v1 Announce Type: cross Abstract: Multi-agent LLM applications chain a planner, worker agents, a verifier, and a synthesizer, and every hop between agents is an unmonitored channel thr
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
arXiv:2606.01152v1 Announce Type: cross Abstract: The work of a professional software engineer has begun to consist, increasingly, of directing agents rather than writing code, and the empirical evide
arXiv:2605.22714v1 Announce Type: cross Abstract: Large language models are routinely used as automated evaluators: to review code, moderate content, or score outputs, often with many items passing th
arXiv:2605.09504v1 Announce Type: cross Abstract: We present swarm-attack, an open-source adversarial testing framework in which multiple lightweight LLM agents coordinate through shared memory, paral
arXiv:2610.07592v1 Announce Type: new Abstract: Direct Preference Optimization (DPO) has become a standard reward-model-free approach for aligning language models with preference data. However, as the
arXiv:2610.03077v1 Announce Type: new Abstract: Propaganda detection is an essential task in natural language processing (NLP), particularly in the context of manipulative political communications. Ho
arXiv:2610.01674v1 Announce Type: new Abstract: Building datasets remains one of the most manual and brittle parts of AI development. In this technical report, we focus on the most extreme but also mo
arXiv:2609.36455v1 Announce Type: new Abstract: Large language models are thought to represent features by vectors in a hidden space of dimension given by the model's width. Superposition, in which mo
arXiv:2609.32445v1 Announce Type: cross Abstract: Direct Preference Optimization (DPO) aligns language models by optimizing over sequence-level sums of token-wise implicit reward differences. However,
arXiv:2609.20614v1 Announce Type: cross Abstract: Frontier AI models are rapidly gaining the ability to exploit vulnerabilities in complex pieces of software. The risk is not theoretical, as evidenced
arXiv:2609.20218v1 Announce Type: cross Abstract: Large language models can label a tabular row from a plain-English description with no training - a capability now shipping in mainstream spreadsheet
arXiv:2609.11987v1 Announce Type: cross Abstract: An agentic coding system couples a language model to a harness: the tools, prompts and control flow that turn a chat model into an autonomous software
arXiv:2609.09553v1 Announce Type: cross Abstract: Large language model safety and security research is preoccupied with, among other things, detecting and preventing jailbreak attacks: alignment bypas
arXiv:2609.11739v1 Announce Type: new Abstract: Large language model serving costs scale directly with output sequence length, yet standard preference alignment often inflates response verbosity witho
arXiv:2609.09604v1 Announce Type: cross Abstract: On August 2, 2026, the obligations of Article 50 of the EU AI Act took effect, requiring generative AI providers to mark the content their systems pro
arXiv:2609.05232v1 Announce Type: new Abstract: Autonomous AI agents increasingly select actions in environments whose memory, execution-time, runtime, compute, and operational constraints determine w
arXiv:2609.02707v1 Announce Type: new Abstract: Does the door-in-the-face technique work on language models? In humans, a large request that is refused makes a smaller follow-up request more likely to
arXiv:2609.00052v1 Announce Type: cross Abstract: Commercial LLM APIs advertise a specific foundation model, but the served backbone may be silently substituted, quantized, or wrapped, for example to
arXiv:2509.22737v3 Announce Type: replace Abstract: Visual comparison reasoning is a fundamental capability of vision-language models (VLMs), covering judgments of object quantity, geometric dimension
arXiv:2608.27465v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly used for everyday decision-making advice, whether a model shifts the direction of its advice according
arXiv:2608.23611v1 Announce Type: cross Abstract: Large Language Models (LLMs) offer new opportunities for automated code refactoring. However, generated changes must reduce targeted quality problems
arXiv:2608.21747v1 Announce Type: cross Abstract: LLM-based coding agents generate complete software systems from high-level descriptions, yet little is known about how the format of architecture spec
arXiv:2608.22758v1 Announce Type: cross Abstract: Standard decoding rules for autoregressive language models promote diversity by rescaling the full next-token distribution or truncating its low-proba