Knowledge catalogue
arXiv:2511.12710v2 Announce Type: replace Abstract: Automated red teaming frameworks for Large Language Models (LLMs) have become increasingly sophisticated, yet many still formulate attack optimizati
arXiv:2605.17246v1 Announce Type: cross Abstract: We introduce fidelity probes: natural-language questions generated from a reference artifact with code-derived ground-truth answers, answered from a c
arXiv:2605.17558v1 Announce Type: cross Abstract: Training tool-calling agents requires large-scale trajectory data with verifiable labels, yet existing approaches either synthesize environments that
arXiv:2605.16475v1 Announce Type: cross Abstract: Generative artificial intelligence (GenAI), based on large-language models (LLMs), such as ChatGPT, has taken organizations, academia, and the public
arXiv:2605.17792v1 Announce Type: new Abstract: Calibrating distributed hydrologic models is a critical bottleneck across operational water resources management - streamflow prediction, reservoir oper
arXiv:2605.16632v1 Announce Type: cross Abstract: Despite the effectiveness of Cube-and-Conquer (C&C) for solving challenging Boolean Satisfiability (SAT) problems, no prior work has shown that transf
arXiv:2605.17986v1 Announce Type: cross Abstract: AI agents such as OpenClaw are increasingly deployed in local workflows with access to external tools. This creates indirect prompt-injection (IPI) ri
arXiv:2605.16301v1 Announce Type: cross Abstract: Single-turn benchmarks such as AnimalHarmBench (AHB) have established important baselines for measuring animal welfare alignment in large language mod
arXiv:2510.10528v3 Announce Type: replace Abstract: Large reasoning models (LRMs) have demonstrated remarkable proficiency in tackling complex tasks through step-by-step thinking. However, this length
'One thing that we've been seeing recently is that inference benchmarks don't really match production workloads that well.' - @realDanFu, VP of Kernels When you're running dozens of concurrent coding
arXiv:2605.17172v1 Announce Type: cross Abstract: Personal AI stacks, like OpenClaw and Hermes Agent, are becoming central to daily work, yet they route nearly every query (often over sensitive local
arXiv:2605.18414v1 Announce Type: cross Abstract: Large language models increasingly operate as autonomous agents that select and invoke tools from large registries. We identify a critical gap: when u
arXiv:2605.17448v1 Announce Type: cross Abstract: Computer-aided design (CAD) is the backbone of modern industrial design, yet learned CAD generators still fall short of real engineering pipelines: th
arXiv:2512.17843v4 Announce Type: replace-cross Abstract: By evaluating Large Language Models (LLMs) through uniform, text-only interfaces, current academic benchmarks obscure how the unique designs a
arXiv:2605.18548v1 Announce Type: cross Abstract: Large language models (LLMs) deployed in real-world agentic applications must be capable of replanning and adapting when mid-task disruptions invalida
arXiv:2605.16909v1 Announce Type: new Abstract: Tool-using agents are increasingly expected to operate across realistic professional workflows, where they must interpret multimodal inputs, coordinate
arXiv:2510.16252v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) for web agents demands environments that are both effective for evaluation and efficient enough for large-scale on
arXiv:2605.16288v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used in clinical and care settings. This exploratory study investigates whether LLMs exhibit sycophantic
arXiv:2605.16972v1 Announce Type: cross Abstract: Cultural heritage exhibitions often struggle to sustain attention and support reflective engagement. Physical exhibitions rely on fixed interpretive a
arXiv:2605.15237v1 Announce Type: cross Abstract: Accelerating applications through the design of hardware accelerators can significantly enhance system performance and energy efficiency. Despite adva
arXiv:2605.15680v1 Announce Type: new Abstract: Online patient inquiries are often informal, incomplete, and written before professional assessment, yet they must still be routed to an appropriate lev
arXiv:2605.15846v1 Announce Type: cross Abstract: Coding agents are increasingly deployed in real software development, where a single version iteration requires months of coordinated work across many
arXiv:2505.18134v3 Announce Type: replace Abstract: Vision-language models (VLMs) have achieved strong results on coding and math benchmarks that are challenging for humans, yet their ability to perfo
Witchcraft is a Rust reimplementation of Stanford's XTR-Warp semantic search engine that uses a single-file SQLite database for storage, enabling client-side deployment. The system operates completely
doomers and AI fans love hearing “it’s over” - but @scaling01 really should have noted that the below refers to a domain specific benchmark (exploitbench) rather than general purpose AI. also note the
Harness profiles! https://docs.langchain.com/oss/python/deepagents/profiles I like what Langchain recently released in their deepagents harness, which is an adapter to modify the syntax of primitive f
There’s an open question on whether grep is all you need for agentic search. This recent paper by @PwCUS (Sen et al.) seems to suggest that. It’s titled “Is Grep All You Need? How Agent Harnesses Resh
We built TERMS-Bench, a three-tier benchmark for LLM agents in real-world economic negotiation. No LLM-as-judge, no outcome rubrics: the environment itself is the verifier. 🏆Among frontier models, @An
'You cannot govern a technology you have only been briefed on.' Singapore Minister for Foreign Affairs, Dr. @VivianBala, echoing @karpathy and @yacineMTB on why he runs NanoClaw: 'you can outsource me
arXiv:2605.14163v1 Announce Type: new Abstract: Can a committee of weak reasoning-model calls reach the performance of much stronger models? We study verifier-backed committee search as inference-time
Andon Labs has been running a series of experiments in which AI agents run businesses without human intervention. Its latest is a quartet of radio stations run by some of the most popular AI models ou
arXiv:2605.14068v1 Announce Type: new Abstract: We introduce CurveBench, a benchmark for hierarchical topological reasoning from visual input. CurveBench consists of extbf{756 images} of pairwise non-
arXiv:2605.14912v1 Announce Type: new Abstract: Pluralistic alignment is typically operationalised as preference aggregation: producing responses that span (Overton), steer toward (Steerable), or prop
Anthropic has reset API rate limits for all users, specifically resetting both 5-hour and weekly rate limit quotas. This announcement suggests the company addressed rate limiting issues or provided us
arXiv:2605.13851v1 Announce Type: new Abstract: Multi-agent orchestration -- in which a hidden coordinator manages specialized worker agents -- is becoming the default architecture for enterprise AI d
arXiv:2605.15184v1 Announce Type: new Abstract: Recent advances in Large Language Model (LLM) agents have enabled complex agentic workflows where models autonomously retrieve information, call tools,
arXiv:2605.14186v1 Announce Type: new Abstract: Large language models (LLMs) often expose useful signals of self-monitoring: before solving a problem, they can estimate whether they are likely to succ
arXiv:2605.14635v1 Announce Type: cross Abstract: This paper introduces a multi-label visual emotion analysis benchmark dataset for comprehensively evaluating the ability of multimodal large language
arXiv:2605.14381v1 Announce Type: cross Abstract: Recent advancements in generative AI facilitate large-scale synthetic data generation for model evaluation. However, without targeted approaches, thes
OpenAI Group PBC today made its Codex programming assistant available on mobile devices. The service is accessible through ChatGPT’s iOS and Android clients. It’s rolling out about eight months after
arXiv:2605.14604v1 Announce Type: new Abstract: This position paper argues that effective tutoring requires corrective friction: surfacing misconceptions and challenging them supportively to drive con
arXiv:2605.14542v1 Announce Type: new Abstract: A skilled live-commerce host is not merely a narrator, but a sales agent who converts viewer curiosity into purchase intent through expert product knowl
Carmen Arroyo / Bloomberg: xAI launches Grok Build, an agentic CLI for coding, building apps, and automating workflows, in beta for SuperGrok Heavy subscribers — Elon Musk's xAI is rolling out its fir
arXiv:2603.26839v2 Announce Type: replace-cross Abstract: How do multimodal models solve visual spatial tasks -- through genuine planning, or through brute-force search in token space? We introduce ex
arXiv:2605.12728v1 Announce Type: cross Abstract: The power distribution engineering workforce faces a projected shortage of up to 1.5 million engineers by 2030, creating urgent demand for more access
arXiv:2601.18842v3 Announce Type: replace-cross Abstract: As GUI agents increasingly rely on screenshots to perceive and operate digital environments, they may inadvertently expose sensitive informati
arXiv:2603.03295v2 Announce Type: replace-cross Abstract: Whether in agentic workflows, social studies, or chat settings, large language models (LLMs) are increasingly being asked to replace humans in
OpenAI is going to let users access Codex, its desktop AI tool that can write code and use apps on your computer, from the ChatGPT app on your phone. Following the surge in popularity for Anthropic's
arXiv:2605.13695v1 Announce Type: cross Abstract: LLM-as-a-judge is now the default measurement instrument for open-ended generation, but on the public JudgeBench benchmark even strong instruction-tun
A lot of people have been wondering about Mythos, Glasswing, and the vulns we / our partners are fixing. Today, I’m excited for us to start sharing more. (For context, I lead Glasswing @AnthropicAI.)
arXiv:2605.11732v1 Announce Type: cross Abstract: In this paper, we present AgentDisCo, a novel Disentangled and Collaborative agentic architecture that formulates deep research as an adversarial opti
arXiv:2605.11143v1 Announce Type: new Abstract: Reasoning benchmarks measure clinical performance on clean inputs. We evaluate the step before reasoning: retrieval over real EHR notes, where negation,
arXiv:2605.11467v1 Announce Type: new Abstract: Reasoning models post-hoc rationalize answers they have already committed to internally, producing chains of *reasoning theater*: deliberative-looking s
arXiv:2605.11086v1 Announce Type: cross Abstract: AI agents are rapidly gaining capabilities that could significantly reshape cybersecurity, making rigorous evaluation urgent. A critical capability is
May 2026 update: We’ve refreshed this post to reflect our mid-cycle positioning and the evolution of our platform since the report was first published last November. Last fall, Google was recognized a
HTML Artifacts are a big part of how I work with agents now. Artifacts can be more than just static files. When combined with agents, they can take action or help you take action. This unlocks all kin
arXiv:2605.12477v1 Announce Type: cross Abstract: LLM-based agents increasingly operate in persistent environments where they must store, update, and reason over information across many sessions. Whil
arXiv:2605.11680v1 Announce Type: new Abstract: We introduce ShapeCodeBench, a synthetic benchmark for perception-to-program reconstruction: given a rendered raster image, a model must emit an executa
arXiv:2605.12466v1 Announce Type: cross Abstract: Looped Transformers offer a promising alternative to purely feed-forward computation by iteratively refining latent representations, improving languag
arXiv:2605.11574v1 Announce Type: new Abstract: The literature on how large language models handle conflict between their training knowledge and a contradicting document presents a persistent empirica