Knowledge catalogue
2/ a cost benchmark showed the same coding task running three to four times cheaper, depending purely on the harness wrapped around the model. Same intelligence, wildly different accuracy and cost, de
An internal version of Astra, @OpenAI’s next major model family, solved 10 major open problems in mathematics, quantum complexity, and theoretical computer science. We believe it will be a major step
**Kimi K3 is Moonshot AI’s 2.8‑trillion‑parameter open‑weight language model—the largest ever released—designed for frontier tasks such as long‑horizon coding and deep reasoning.** Its architecture us
Ten advances in mathematics and theoretical computer science A few days ago it was Anthropic discovering cryptographic weaknesses with Claude using Mythos Preview, spending 100,000 on tokens and with
arXiv:2607.28618v1 Announce Type: new Abstract: Chemistry literature synthesis often requires assembling specific findings scattered across many publications, yet existing literature-search systems pr
arXiv:2607.27845v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have enabled AI systems to assist scientific research and peer review. However, an essential capability
arXiv:2607.27726v1 Announce Type: cross Abstract: Deep research over data lakes requires an LLM agent to investigate evidence across thousands of heterogeneous tables and passages to synthesize a repo
arXiv:2607.28146v1 Announce Type: new Abstract: As large language models (LLMs) are deployed as agents in high-stakes settings, such as medical and legal systems, understanding their deceptive capabil
arXiv:2607.26155v1 Announce Type: new Abstract: Clinical data-science agents must transform heterogeneous longitudinal records into auditable analyses, yet existing benchmarks largely isolate medical
arXiv:2607.28229v1 Announce Type: new Abstract: The web is increasingly accessed by AI agents rather than humans. Every agent needs knowledge, especially in the life-sciences, where agentic pipelines
arXiv:2607.27704v1 Announce Type: cross Abstract: As large language models (LLMs) continue to demonstrate exceptional capabilities across various domains, the challenge of achieving energy-efficient a
arXiv:2607.28347v1 Announce Type: new Abstract: LLMs are increasingly deployed as proxies for human study participants in social science experiments, yet the fidelity of this practice has rarely been
arXiv:2607.27739v1 Announce Type: cross Abstract: Context compression discards most of a document before a language model reads it, and is normally evaluated by downstream task accuracy - which makes
arXiv:2607.28227v1 Announce Type: cross Abstract: GUI agents have the potential to become a general purpose executor over existing digital devices. To advance them toward real-world use, we envision a
arXiv:2607.28128v1 Announce Type: new Abstract: LLM tutoring poses a measurement problem: can a general-purpose helpfulness rubric distinguish direct answer-giving from pedagogical guidance? We audit
smevals - a small eval suite for evaluating models, prompts, and harnesses I've been working with Jesse Vincent's Prime Radiant applied AI research lab building out this evals framework to help answer
arXiv:2607.27232v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly shaping how we consume information and form our worldview. This raises concerns beyond bias in AI: do LLMs
arXiv:2602.08159v2 Announce Type: replace-cross Abstract: When a language model asserts that 'the capital of Australia is Sydney,' does it know this is wrong? Models assert misconceptions with the sam
arXiv:2607.27940v1 Announce Type: cross Abstract: Federated fine-tuning of large language models (LLMs) enables collaborative training without exposing raw data. However, a recent attack, NeuroImprint
arXiv:2607.28287v1 Announce Type: cross Abstract: ARC-AGI-3 turns abstraction into an interactive problem of skill acquisition. A player must infer an unfamiliar game's rules, hidden state, and goal w
arXiv:2607.27553v1 Announce Type: cross Abstract: This research evaluates the efficacy of large language models (LLMs) in generating new product ideas. To do so, we compare three pools of ideas for ne
Answer from OpenAI @emollick re ARC-AGI-3: human testers scored ~48% (ARC uploaded testers logs to HuggingFace some time ago, I believe). re GDPval: it’s close to saturated now, so we’re mostly lookin
arXiv:2607.27189v1 Announce Type: new Abstract: We introduce APEX-Accounting, a benchmark built by Mercor in partnership with Ramp, to assess whether frontier models can do the real work of accountant
Ethan Mollick highlights that large, currently under‑explored benchmarks (e.g., ARC‑AGI, GDPval, METR long horizons, ASI cyber tasks) are growing in complexity, yet they increasingly lack systematic h
arXiv:2607.26828v1 Announce Type: new Abstract: Large language models increasingly support scientific and algorithmic discovery through inference-time search over evaluated candidates. Existing adapti
arXiv:2607.26368v1 Announce Type: new Abstract: Financial disclosures contain numerical claims, temporal statements, entity references, policy commitments, and risk descriptions that may conflict in q
Release: llm-chat-completions-server 0.1a0 A key goal of the new content-addressable logs in LLM 0.32rc1 was being able to support OpenAI Chat Completion style requests where each incoming message ext
arXiv:2505.22039v2 Announce Type: replace Abstract: While anomaly detection has made significant progress, generating detailed analyses that incorporate industrial knowledge remains a challenge. To ad
arXiv:2607.26541v1 Announce Type: cross Abstract: Audio-capable foundation models enable end-to-end spoken interaction, but they also introduce safety risks beyond transcript content. It remains uncle
arXiv:2607.27084v1 Announce Type: new Abstract: Scientific images are the core elements of presenting experimental conclusions, elaborating system architecture, and supporting comparative arguments in
arXiv:2607.26977v1 Announce Type: new Abstract: Travel planning is a demanding stress test for tool-using LLM agents: a usable itinerary is a single artifact that must be right along many axes at once
arXiv:2607.24884v1 Announce Type: cross Abstract: Repository-level code generation relies on heterogeneous evidence whose relevance, compatibility, and completeness are inherently uncertain. Similar-c
BREAKING: Grok 4.5 (high) ranks #1 on the HighWalk benchmark, which tests how well AI agents update technical specifications from code changes. Grok delivered the best combination of quality and opera
arXiv:2607.25021v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) can connect visualization patterns to external causes, consequences, and domain knowledge, but the evidential b
arXiv:2607.25921v1 Announce Type: cross Abstract: In this work, we study the use of Vision-Language Models (VLMs) for anomaly detection in an agent-driven game Quality Assurance (QA) pipeline focusing
arXiv:2607.25218v1 Announce Type: new Abstract: Debt collection is a critical negotiation task in the financial industry, with strong practical relevance and exceptional academic value as a behavioral
arXiv:2607.24898v1 Announce Type: cross Abstract: State-of-the-art toxicity detectors for text-to-image generation adopt a one-size-fits-all approach: a single universal model applying fixed safety gu
I know this is the 1000000th new sub billion parameter model out there and probably isn't as good as Qwen 3 0.6B or Qwen 3.5 0.8B but it still packs a decent punch. My intention to to continuously pre
arXiv:2607.25136v1 Announce Type: new Abstract: Research on preference optimization often varies the training objective while holding the data fixed. We instead ask whether a small, high-confidence se
arXiv:2510.13434v2 Announce Type: replace Abstract: Aligning Large Language Models (LLMs) with human preferences is pivotal for Machine Translation (MT), yet current approaches are often hindered by m
arXiv:2507.23541v5 Announce Type: replace Abstract: In medical scenarios, effectively retrieving external knowledge and leveraging it for rigorous logical reasoning is of significant importance. Despi
Model + harness. We have barely begun to understand the best ways to do harness engineering. A huge amount of untapped potential even without models getting better (but models are getting better) Turn
arXiv:2607.24768v1 Announce Type: new Abstract: Prenatal care is an important preventive service designed to improve outcomes for pregnant individuals. The American College of Obstetricians and Gyneco
arXiv:2607.24782v1 Announce Type: new Abstract: LLM behavior may be conditioned by human identity in several ways: they may be asked to adapt to users, role-play populations, or forecast how people wo
arXiv:2607.25157v1 Announce Type: new Abstract: Discrete masked diffusion language models support bidirectional generation and infilling, but adapting pretrained autoregressive (AR) transformers requi
arXiv:2607.24797v1 Announce Type: cross Abstract: In the literate human brain, reading and writing are two doubly-dissociable systems: a ventral decoding route (impaired in pure alexia) and a fronto-p
arXiv:2607.09800v3 Announce Type: replace Abstract: Direct low-precision write-back can erase optimizer proposals, while aggregate update visibility need not identify parameters worth protecting. We s
The number of times I have had to tell Opus 5 and Fable 5 to talk to me like an excited teenager and not a computer science phd is high. Was going through a Google auth thing and got multiple paragrap
arXiv:2607.24750v1 Announce Type: new Abstract: Large Language Models (LLMs) are temporally overexposed: trained on vast contemporary corpora, they encode present-day concepts that make them unreliabl
Who on earth came up with 5 hour limits? The day is 24 hours long. While do our limit times shift by an hour each day. Pls if you are going to have limits 4 or 6 hours. Hello people of Sol! I've reset
arXiv:2607.22620v1 Announce Type: cross Abstract: Yun, Sra, and Jadbabaie (COLT 2021, open question) conjectured the SS--RS--GD inequalities: for well-conditioned symmetric matrices A_1,ots,A_n, the o
arXiv:2607.22745v1 Announce Type: cross Abstract: Rapid advances in image generation are eroding the evidentiary value of visual content in settings where authenticity can affect public safety and per
arXiv:2607.23519v1 Announce Type: cross Abstract: Political audits of large language models (LLMs) usually reduce each to one point on a political compass. But that resting point barely matters in dep
arXiv:2607.24743v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) hold immense potential to revolutionize clinical practice, yet deploying them in the medical domain is fundam
arXiv:2607.22577v1 Announce Type: new Abstract: Scaling large language models (LLMs) has driven their success, yet dense Transformers couple capacity and computation: every parameter is activated for
Code Arena now measures fullstack capabilities! View overall rankings across AI models on full-stack web development tasks: multi-step reasoning, tool use, and end-to-end app generation. - Kimi K3 (Ma
arXiv:2607.23513v1 Announce Type: cross Abstract: Diagrams are widely used to support logical reasoning, and prior studies suggest that representations such as Euler diagrams can improve human reasoni
arXiv:2607.22653v1 Announce Type: new Abstract: Large language models are increasingly used in recursive refinement workflows, where an initial draft is repeatedly revised by the same model. Despite t
arXiv:2607.23496v1 Announce Type: new Abstract: Safety-aligned large language models are trained to refuse harmful requests, yet embedding the same requests in particular scenarios can bypass their sa
arXiv:2603.05607v2 Announce Type: replace-cross Abstract: Computer-Aided Design (CAD) relies on structured and editable geometric representations, yet existing generative methods are constrained by sm