Knowledge catalogue
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:2606.29537v1 Announce Type: new Abstract: Existing computer-use benchmarks fail to capture the realism, complexity, and long-horizon demands of real-world computer use, limiting their ability to
arXiv:2606.28480v1 Announce Type: cross Abstract: As large language models and harness frameworks continue to advance, agents operating in terminals are increasingly capable of performing a broader ra
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
arXiv:2606.16821v2 Announce Type: replace Abstract: Large language model (LLM)-based search agents synthesize open-web content into actionable recommendations on behalf of users, creating a risk that
arXiv:2606.24370v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly integrated into decision-support roles in business and policy contexts. While prior benchmark studies have
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
GLM-5.2 leads open weights models and sits at #3 overall on GDPval-AA, a real-world agentic work benchmark GLM-5.2 from @Zai_org scores 1524 Elo on GDPval-AA, which measures performance on real-world,
arXiv:2606.11447v1 Announce Type: new Abstract: Recent anecdotal evidence suggests that AI coding agents can reproduce published findings when provided with original data and code; yet systematic eval
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
arXiv:2601.12164v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed as analytical tools across multilingual contexts, yet their outputs may carry systemati
arXiv:2606.10106v1 Announce Type: cross Abstract: The term agent harness now circulates widely in software engineering with generative artificial intelligence. It names the layer that wraps a language
Fable 5 is the biggest step up I’ve felt in our models since Opus 4.5 back in November. After 4.5 came out I uninstalled my IDE when I realized that I’d been doing 100% of my coding in a terminal for
arXiv:2606.08036v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used in academic research workflows, but scholarly tasks require high factual precision and therefore ex
OpenAI is hosed. There is almost no reason to prefer them over Anthropic, they have lost their lead (despite every advantage in the world), they have made commitments far far beyond their means, their
arXiv:2606.07591v1 Announce Type: cross Abstract: AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify. We presen
TIL: Setting a custom price for a model in AgentsView I've been really enjoying AgentsView by Wes McKinney as a tool for exploring my token usage across different coding agents running on my laptop. C
arXiv:2606.09204v1 Announce Type: new Abstract: We present a reproducible failure mode of safety training in RAG-based LLM recommendation -- the Injection Paradox -- in which prompt injections embedde
arXiv:2602.08235v2 Announce Type: replace-cross Abstract: Although computer-use agents (CUAs) hold significant potential to automate increasingly complex OS workflows, they can demonstrate unsafe unin
arXiv:2606.07808v1 Announce Type: new Abstract: Reasoning language models deployed in agentic workflows must follow an instruction hierarchy: when instructions from different sources conflict, the mod
arXiv:2606.06788v1 Announce Type: new Abstract: Evaluations of large language models (LLMs) in scientific information seeking tasks have become increasingly use-centric, such as conducting live or mul
arXiv:2602.04894v4 Announce Type: replace-cross Abstract: LLMs are increasingly used for code generation, but their outputs often follow recurring templates that can induce predictable vulnerabilities
Great tips. In practice, this is how it roughly looks to run agents autonomously for hours or days. /goal or /loop to keep it going. Verification is crucial here. Seeing a number of benchmarks showing
arXiv:2606.05670v1 Announce Type: new Abstract: Does adding more agents help an LLM workflow once compared systems share the same benchmark loader, tool access, answer contract, usage accounting, and
Your margin is my opportunity: AI version… The biggest surprise of 2026 is that the capability gap between the best open-weight/source models and the best closed models has narrowed much faster than t
Critical context on the new Anthropic blog: 1, AGI is *harder* than RSI (as used below). AGI: machine can do anything human can do, autonomously [not achieved] RSI (as used below): AI is a useful codi
arXiv:2606.05158v1 Announce Type: cross Abstract: Multi-agent reasoning systems adopt a 'generate-then-transfer' paradigm that forces end-to-end latency to scale linearly with pipeline depth. We intro
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:2606.02630v1 Announce Type: cross Abstract: Patient-facing medical chatbots are commonly evaluated on single-turn prompts, yet real users push back after refusals, add urgency, and invoke author
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: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:2605.30686v1 Announce Type: cross Abstract: ReAct agents that interleave chain-of-thought reasoning with tool calls are increasingly deployed for real tasks such as scheduling, file retrieval, a
arXiv:2605.30589v1 Announce Type: cross Abstract: U.S. immigration law spans thousands of pages of official policy, federal regulations, and procedural guidance that change frequently and carry high s
arXiv:2605.29001v1 Announce Type: cross Abstract: A paraphrase-quality audit of MathCheck (ICLR 2025) detected 4 semantically incorrect paraphrases in 129 groups (3.1%); removing them drops GPT-4o fro
arXiv:2605.30094v1 Announce Type: new Abstract: Poker is a landmark challenge for artificial intelligence. The dominant approach relies on equilibrium solvers built on counterfactual regret minimizati
This is a diary entry to myself, so I remember what AI was like today. It's just going to be a bullet-list stream of consciousness. - There are still so many leaders that have never seen an agent run
arXiv:2605.27785v1 Announce Type: new Abstract: The fastest-growing data in production today is unstructured text: agent traces, chat logs, reasoning chains, model outputs. People want to analyze it,
BREAKING: Anthropic just dropped Opus 4.8—and it is a MONSTER We've been testing for about a week @every and our verdict is they could've just called it Opus 5, it's that good. Here's our vibe check:
arXiv:2603.21465v2 Announce Type: replace Abstract: Developing efficient CUDA kernels is a fundamental yet challenging task in the generative AI industry. Recent research leverages Large Language Mode
arXiv:2605.26747v1 Announce Type: new Abstract: Large Language Models (LLMs) have brought huge improvements to Artificial Intelligence (AI), which can be applied to general-purpose tasks. However, the
arXiv:2605.27130v1 Announce Type: cross Abstract: We present DEI: Diversity in Evolutionary Inference, a distributed Quality-Diversity (QD) search framework that assigns heterogeneous large language m
arXiv:2605.27072v1 Announce Type: cross Abstract: We present E3, an automated review assistant that augments reviewers and engineering teams by identifying decision-relevant technical concerns in rese
arXiv:2605.26329v1 Announce Type: new Abstract: Current benchmarks for occupational AI agents are scoped primarily by economic values, telling a replacement story. We introduce JobBench, which evaluat
arXiv:2605.25420v1 Announce Type: cross Abstract: Large language model safety evaluation remains heavily English-centered, leaving low-resource languages under-measured even when models are deployed g
arXiv:2605.25133v1 Announce Type: new Abstract: Reliably knowing when a language model is correct is almost as important as being correct. We introduce prover-verifier deliberation (PVD), an inference
arXiv:2605.21496v1 Announce Type: cross Abstract: Frontier language models are being deployed into clinical workflows faster than the infrastructure to evaluate them safely. Static medical-QA benchmar
We just announced the first release of Datasette Agent, a new extensible AI assistant for Datasette. I've been working on my LLM Python library for just over three years now, and Datasette Agent repre
arXiv:2605.19156v1 Announce Type: new Abstract: Recent auto-research systems can produce complete papers, but feasibility is not the same as quality, and the field still lacks a systematic study of ho
arXiv:2605.19193v1 Announce Type: new Abstract: Multi-agent LLM debate improves factuality and reasoning, but most recipes pick a fixed round count, over-spending on easy items and under-spending on h
arXiv:2605.16265v1 Announce Type: new Abstract: The safety of autonomous AI agents is increasingly recognized as a critical open problem. As agents transition from passive text generators to active ac
arXiv:2511.21654v2 Announce Type: replace Abstract: We introduce EvilGenie, a benchmark for reward hacking in programming settings. We source problems from LiveCodeBench and create an environment in w
Google’s new Gemini 3.5 Flash is the clear leader on the Intelligence vs Speed Pareto frontier and makes large gains on GDPval-AA (real-world agentic tasks), but is 5x the cost of Gemini 3 Flash @Goog
At Google I/O, we introduced a unified development toolkit featuring Antigravity 2.0 and the Managed Agents API, giving developers better ways to build locally and deploy securely to the cloud on a sh
we do not post AIE videos with bullshit brainrot hype lingo, and this is the consequence: the entire AIE back catalog is being reposted by 'influence operators' almost daily, without credit to speaker
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:2605.14415v1 Announce Type: cross Abstract: Coding agents powered by large language models are increasingly expected to perform realistic software maintenance tasks beyond isolated issue resolut
In just a short few months, we have witnessed several artificial intelligence technology events that deserve the overused “unprecedented” descriptor: a highly complex supply chain attack by TeamPCP, A
arXiv:2605.13532v1 Announce Type: new Abstract: As generative AI (GenAI) tools become easily accessible, there is promise in using such tools to support instructors. To that end, this paper examines u
arXiv:2510.15297v4 Announce Type: replace-cross Abstract: We introduce VERA-MH (Validation of Ethical and Responsible AI in Mental Health), an automated evaluation of the safety of AI chatbots used in
arXiv:2503.06139v2 Announce Type: replace Abstract: Pairwise LLM-as-a-judge evaluation asks the judge to identify the better of two candidate answers. We study a one-line modification that asks for th