Knowledge catalogue
arXiv:2511.20109v2 Announce Type: replace Abstract: Climate science demands automated workflows to transform comprehensive questions into data-driven statements across massive, heterogeneous datasets.
arXiv:2609.15234v1 Announce Type: new Abstract: Recently, Large Language Models (LLMs) have gained significant attention due to their strong language understanding and generation capabilities, demonst
arXiv:2609.13808v1 Announce Type: new Abstract: Structured knowledge fact checking aims to determine the truthfulness of natural language claims by reasoning over structured evidence. Recent program-g
arXiv:2607.17425v3 Announce Type: replace Abstract: Sparse autoencoders (SAEs) compress model activations into sparse codes, but equal reconstruction error and sparsity can preserve different linearly
arXiv:2609.14779v1 Announce Type: new Abstract: Performing deliberate mathematical reasoning in visual contexts is a hallmark of advanced Multimodal Large Language Models (MLLMs) and requires a sophis
arXiv:2609.13454v1 Announce Type: cross Abstract: Clinical decisions are prospective, but clinical language models are often evaluated on retrospective records that reveal the final diagnosis, treatme
🆕 Humanity’s Last Invention — with @RichardSocher! https://www.youtube.com/watch?v=eDFXtSg3zB8 @recursive_si is the latest neolab to burst on the scene with a $5B fundraise and one of the most impress
arXiv:2609.13611v1 Announce Type: new Abstract: The WMT26 General MT task evaluates systems on 10 language pairs that have no human references (neither translated from scratch nor post-edited from MT
Is Bash All You Need? Interesting paper from Microsoft. If you are deciding which tools to give an enterprise agent, you might want to check this out. (bookmark it) They compared five tool interfaces
arXiv:2609.15855v1 Announce Type: cross Abstract: % !TEX root = ../main.tex People increasingly use large language models (LLMs) for mental health support, yet their safety in evolving, high-risk conv
arXiv:2609.13154v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have made prompts increasingly large and complex. Techniques such as chain-of-thought reasoning (Wei et
Many assume that agent spend goes toward output tokens. When we ran DeepSWE on Astra vs. DeepSeek V4.1-Flash, input tokens outnumbered output 174 to 1. 99.6% were cache hits. Those hits are 60% of the
arXiv:2609.13879v1 Announce Type: new Abstract: An acquired representation can enlarge a system's cognitive repertoire without transferring the capacities exercised in producing that representation. T
arXiv:2603.22179v2 Announce Type: replace Abstract: Cardiovascular disease remains the leading cause of global mortality, with progress hindered by human interpretation of complex cardiac tests. Curre
Know everything. Do anything. That was the message NVIDIA founder and CEO Jensen Huang brought to Salesforce Dreamforce Tuesday, joining CEO Marc Benioff onstage in an appearance that coincided with t
arXiv:2609.15344v1 Announce Type: new Abstract: We study the adaptation of pretrained language models to univariate time-series forecasting through a parameter-efficient transfer learning framework, w
arXiv:2609.14973v1 Announce Type: new Abstract: We present PhysBrain 1.5, a unified model for understanding physical environments, generating actions, and predicting future states. Motivated by the ph
arXiv:2609.14473v1 Announce Type: new Abstract: Personal AI assistants hold the potential to evolve from digital interfaces into embodied companions capable of guiding users through complex physical a
arXiv:2609.14412v1 Announce Type: new Abstract: Deep research agents answer complex questions through iterative loops of searching, reading, and reasoning. Recent work on reasoning-intensive benchmark
arXiv:2609.13814v1 Announce Type: new Abstract: Natural interaction in digital and physical environments requires continuous perception and timely responses. Spoken dialogue relies on acoustic and lin
arXiv:2609.14759v1 Announce Type: cross Abstract: Alignment applied after pretraining is shallow in a measurable way: a single direction in a model's residual stream can be edited out, and the model s
arXiv:2609.13463v1 Announce Type: new Abstract: The increasing deployment of AI agents in long-horizon tasks yields massive execution logs. Diagnosing failures within these records is crucial for reli
arXiv:2609.15364v1 Announce Type: new Abstract: Digital agents must often adapt to new environments whose interfaces, tools, and failure modes are not fully captured by pretrained models. We introduce
arXiv:2601.19930v2 Announce Type: replace-cross Abstract: We introduce Daisy, a factual knowledge benchmark for Danish cultural heritage, based on curated topics from the Danish Culture Canon 2006. Fo
arXiv:2607.10198v2 Announce Type: replace Abstract: Search APIs expose ranked snippets, URLs, and metadata on which agents decide whether to answer, search again, or fetch pages. We evaluate these int
The future is clearly agent teams. I run several agent harnesses at once, but the hard part is keeping them in sync. Many builders end up copying messages between Claude Code, Codex, and open models b
arXiv:2609.15533v1 Announce Type: cross Abstract: Mechanistic interpretability has become the dominant lens for understanding frontier language models, as their inner workings are complex and inherent
THE SANDBOX WAS A PROP! OpenAI Turned Off the Guardrails, Left a Door to the Internet, and Then Sold the Hugging Face Breach as “Rogue AI” It is time to understand how you were lied to and by whom. In
arXiv:2609.15494v1 Announce Type: new Abstract: Recent investigations of the July 2026 OpenAI--Hugging Face incident motivate two questions about agent behavior under task failure: when an assigned ta
arXiv:2609.15683v1 Announce Type: new Abstract: While In-Context Learning (ICL) enables models to adapt from exemplars without parameter updates, multimodal ICL remains largely underexplored, particul
arXiv:2609.13348v1 Announce Type: cross Abstract: This paper presents ViFA-Council, a three-stage multi-agent framework that employs multiple large language models (LLMs) to tackle two culturally comp
arXiv:2609.13148v1 Announce Type: cross Abstract: Large language models are increasingly deployed as synthetic consumer panels, promising 97% cost reductions over traditional surveys. Yet aggregate va
arXiv:2609.13824v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to evaluate the responses of other language models. This approach, known as LLM-as-a-Judge, is faster
arXiv:2609.12254v1 Announce Type: new Abstract: The climate literature has grown faster than review teams can read it. That gap matters most for a concept like the environmental social tipping point,
arXiv:2609.12533v1 Announce Type: cross Abstract: Real-world Earth observation (EO) agents must translate high-level scientific questions into executable workflows to acquire observations, prepare dat
I feel like the data sovereignty movement for firms is going to run headlong into the challenge that maintaining fine-tuned small models in a way that continually beats larger general-purpose models i
arXiv:2609.11999v1 Announce Type: cross Abstract: In this study, we examine whether a general shell can outperform specialized tools on enterprise tasks. Shell-based agents have shown strong results i
arXiv:2609.12366v1 Announce Type: new Abstract: We present ORQA, a method for testing occupation-level knowledge in large language models. Prior methods either map abstract LLM skills to occupations v
arXiv:2609.12123v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) is an effective approach for adapting large pretrained models by learning low-rank weight updates. In practice, the LoRA rank
arXiv:2609.12691v1 Announce Type: new Abstract: Instruction-guided image editing has a training-time blind spot. Generative editors are never required to semantically verify whether their outputs actu
arXiv:2609.13005v1 Announce Type: new Abstract: Large language models (LLMs) have achieved strong performance on a wide range of natural language tasks, and recent benchmarks suggest that they are inc
arXiv:2511.07318v3 Announce Type: replace Abstract: Despite substantial advances, large language models (LLMs) continue to exhibit hallucinations, generating plausible yet incorrect responses. In this
One is from Sam Altman, the other Claude suggested and it works extremely well. The first question I ask: What are you least confident about right now. The AI will list like 6 to 7 things that it didn
I’ll be honest it feels like a month since this happened The takeoff is a heck of a thing We’re sharing a solution to the Navier-Stokes Millennium Prize Problem, one of the deepest problems at the fro
Law enforcers already have authority to charge companies and their CEOs for creating and releasing dangerous, unvetted, or defective products. We shouldn’t let discussions about new legal regimes dist
Fast meets open. 🚀 Qwen3.8-27B is now running on @cerebras with rapid inference. Try it now! Qwen3.8-27B is now live at Cerebras speed. The dense, open-weight model from @Alibaba_Qwen scores 34 on the
arXiv:2609.11234v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used in peer review at major AI conferences, yet novelty remains a persistent weak point. Existing benchma
Peak performance across hard benchmarks: • Best or joint-best on 5/8 benchmarks (DeepSWE, Chartography, Toolathon, GDP.pdf, SWEFish) • Chartography: 48.3 (outperforming Opus 5 & Fable 5) • DeepSWE: 74
arXiv:2609.11532v1 Announce Type: new Abstract: Commercial text-to-image systems silently revise user prompts before generating images, a step users typically cannot disable or even see. Yet, existing
arXiv:2609.11180v1 Announce Type: new Abstract: Large language model (LLM) coding agents constantly decide whether a version satisfies a constraint such as ^1.2.3 or >=2.0,1.2 means >=1.3.0) traps eve
arXiv:2609.10611v1 Announce Type: cross Abstract: Membership inference attacks (MIAs) have emerged as critical tools for auditing privacy risks in large language models (LLMs), aiming to determine whe
Do large language models actually understand the world, or are they just very good at pretending? Does it even matter? Our recent special issue in the Royal Society, “World Models in Natural and Artif
Fugu Ultra v2 by the numbers. Full Results: https://sakana.ai/fugu-max-release/ • #1 on 5 out of 8 hard benchmarks (including DeepSWE, Chartography, Toolathon) • DeepSWE: 74.3 • Chartography: 48.3 vs
Introducing Fugu Max and Fugu Ultra v2: the next evolution of Sakana Fugu’s multi-agent orchestration system. Try: https://sakana.ai/fugu Blog: https://sakana.ai/fugu-max-release/ The frontier that ac
arXiv:2606.21844v2 Announce Type: replace Abstract: As AI systems integrate into online spaces, differentiating them from humans in conversations is increasingly important. We present Inverse Turing B
arXiv:2609.10758v1 Announce Type: new Abstract: Multilingual large language models (LLMs) are increasingly used for open-ended text generation, yet their behaviour in low-resource languages remains po
arXiv:2609.11335v1 Announce Type: new Abstract: As large language models are increasingly deployed in sensitive domains, anonymizing input data to protect personally identifiable information has becom
arXiv:2603.20278v2 Announce Type: replace-cross Abstract: Training deep research agents requires long-horizon trajectories that interleave search, evidence aggregation, and multi-step reasoning. Howev
arXiv:2603.23346v2 Announce Type: replace Abstract: Real-time spoken dialogue systems face a fundamental tension between latency and response quality. End-to-end speech-to-speech (S2S) models respond
arXiv:2609.10996v1 Announce Type: new Abstract: Verbalized confidence, long dismissed as overconfident, coarse, and prone to round-number clustering, is now the more robust soft-scoring mechanism for