Knowledge catalogue
IBM has released Granite 4.2, an open‑source agentic AI model that adds native reasoning, tool use, coding instruction following and speech capabilities to enterprise agents. The suite of pre‑built mo
arXiv:2608.21928v1 Announce Type: new Abstract: In embodied AI, safety risk can be latent: a benign instruction and a safe scene become hazardous only when composed. Prior work has advanced embodied s
arXiv:2608.22817v1 Announce Type: new Abstract: Industrial technical reports contain high-value knowledge for maintenance, troubleshooting, and product engineering, but their heterogeneous structure (
arXiv:2608.22140v1 Announce Type: cross Abstract: Large Language Models (LLMs) achieve strong reasoning performance, but their robustness to realistic lexical corruption remains poorly understood. We
arXiv:2608.22149v1 Announce Type: cross Abstract: LLMs generate fluent plans for robots but routinely violate the syntactic and se8mantic constraints they must satisfy to execute, and existing remedie
arXiv:2608.23476v1 Announce Type: new Abstract: Narrow fine-tuning on small, domain-specific datasets can produce broad and surprising changes in model behavior-a phenomenon called weird generalizatio
arXiv:2606.13610v2 Announce Type: replace-cross Abstract: Search-augmented LLMs increasingly mediate everyday consumer recommendations by retrieving live web content. This creates a new risk: LLM reco
Emma Roth / The Verge: OpenAI says its Jalapeño chip delivered 1.5x-1.9x more AI work per watt and 1.7x-3.6x lower latency vs. Nvidia chips across GPT-OSS, DeepSeek R1, Kimi K2.5 1T — Jalapeño outperf
arXiv:2608.21853v1 Announce Type: new Abstract: Large language models are increasingly moving beyond text processing, adding support for other modalities such as images and audio. While text understan
We've closed our Series B, bringing total funding to $232M under new leadership. This round welcomes entertainment titans Electronic Arts, Sony Music Group, Universal Music Group, Warner Music Group,
arXiv:2608.21382v1 Announce Type: new Abstract: Multiple-choice benchmarks fix the questions and the correct answers, but not the harness: the order of the options, the wording of the prompt, and whet
arXiv:2608.22917v1 Announce Type: new Abstract: We present TSWAP, a deployed eight-language conversational wellness advisor grounded, via retrieval-augmented generation, in a verified knowledge base o
arXiv:2608.22852v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used in investment decision-making, yet prior work shows that they exhibit systematic, model-specific inve
arXiv:2608.20554v1 Announce Type: cross Abstract: The critical failure modes in deployed large language models (LLMs) are cross-dimensional: a model can score 99.3 in safety alignment while refusing o
// Applying Anthropic Primitives at Large Enterprises // Frontier models collapsed the cost of writing custom code. But they did not reduce the cost of reviewing and maintaining it. Each bespoke solut
arXiv:2608.20637v1 Announce Type: cross Abstract: Static analyzers have been widely adopted for vulnerability detection in C/C++ programs. Query-based static analyzers (e.g., CodeQL) encode vulnerable
arXiv:2608.20763v1 Announce Type: cross Abstract: Linear probes and activation steering have uncovered that vision-language models (VLMs) internally represent mental states such as agents' beliefs, kn
similar to video upscaler LLMs, what's the bleeding edge right now on something similar for audio music? the idea is you feed it in with a low bitrate MONO old soundtrack, and the LLM then recreates i
arXiv:2607.11818v2 Announce Type: replace-cross Abstract: We introduce MM-ToolSandBox, a benchmark and evaluation framework for visually grounded tool-calling agents. The framework provides a stateful
Our 2nd founder dinner in SF co-hosted by @jerryjliu0 and @GuangyuRobert at @Fundamental - the team behind @tryshortcutai Talking about existing moats in the AI era. Frontier labs are moving past mode
arXiv:2608.20438v1 Announce Type: cross Abstract: Population-level behavior in large-language-model (LLM) agents cannot be characterized by single-agent benchmarks. We introduce PV-SST, a peer-voted s
arXiv:2608.20432v1 Announce Type: cross Abstract: Formal proofs in Lean 4 that pass the kernel's type checker can nonetheless vary widely in quality. We introduce ProofJudge, an agentic LLM-as-judge s
arXiv:2608.20953v1 Announce Type: cross Abstract: Serving large language models cheaply increasingly means shipping models that are both structurally compressed to a fraction of their parameters and q
arXiv:2608.21236v1 Announce Type: new Abstract: Representation engineering offers a lightweight means of controlling language-model behavior by modifying intermediate hidden states, but its direct app
arXiv:2608.20786v1 Announce Type: new Abstract: Multi-agent pipelines that author formal documents must both read a requester's forms and write against them. We report a deployed tender-response syste
Today, we’re announcing a strategic collaboration with @HUMAIN spanning AI infrastructure, advanced model development, and the deployment of AI solutions in Saudi Arabia and across the region. Togethe
arXiv:2608.20347v1 Announce Type: cross Abstract: Language models (LMs) often pass behavioral bias evaluations, but it remains unclear whether they no longer represent the underlying associations that
Do you know you can use open weight models like GLM, Deepseek, Kimi in Claude Code? Setup Fireworks account - you get free credits on signup curl -fsSL https://raw.githubusercontent.com/fw-ai/fireconn
arXiv:2608.20047v1 Announce Type: new Abstract: Watermarking schemes for large language model output are evaluated almost exclusively on English text using each scheme's detection threshold and a narr
arXiv:2606.15910v2 Announce Type: replace Abstract: A vision-language model can answer a question about a chest radiograph or a pathology slide fluently and confidently while barely using the image, r
arXiv:2608.19207v1 Announce Type: new Abstract: Production deployments of Multimodal Large Language Models (MLLMs) increasingly rely on system messages to govern model behavior. Yet existing benchmark
arXiv:2608.19659v1 Announce Type: new Abstract: Choosing tensor-parallel (TP) degrees and replica counts for an LLM serving fleet is difficult because performance is not monotonic in TP and the feasib
arXiv:2608.19680v1 Announce Type: new Abstract: Smart contract vulnerability detection with Large Language Models (LLMs) faces three causally linked challenges. First, new vulnerability categories dem
Inkling and Inkling Small are now served directly by @thinkymachines on OpenRouter, free to use inside agentic harnesses only. Plug them into Claude Code, Codex, Hermes Agent and more to unlock the fr
arXiv:2608.20106v1 Announce Type: new Abstract: We introduce OenoBench, a wine-domain knowledge benchmark of 3,266 multiple-choice questions across six pillars (regions, grape varieties, viticulture,
arXiv:2608.19741v1 Announce Type: new Abstract: Recent agent benchmarks increasingly ground evaluation in executable environments, from code repair to web navigation, app APIs, and function calling. Y
Our general-purpose coding agent just scored 100% on the ARC-AGI-3 interactive reasoning benchmark. NVIDIA AVO completed all 183 levels across all 25 public environments, figuring out what to do with
arXiv:2608.20116v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used in settings where textual summaries, numerical observations, and external tool outputs may provide co
Agree with @gdb that we need to arm cyber defenders much more than they are now, both with APIs and open models. The real cybersecurity risk of AI is asymmetry of power, capabilities and ressources be
arXiv:2608.18578v1 Announce Type: new Abstract: Proactive interference (PI) is a documented failure mode in large language models in which retrieval of a repeatedly overwritten value degrades as prior
arXiv:2608.18289v1 Announce Type: new Abstract: The extraction of structured information from unstructured documents represents a critical component of digital transformations in all sectors. While pr
arXiv:2608.18089v1 Announce Type: cross Abstract: Instruction-tuned models often refuse harmful requests in English but comply with the same requests in Yoruba, Igbo, Igala, and Hausa. This suggests t
arXiv:2606.17809v2 Announce Type: replace Abstract: Automated pollen identification from microscopy remains a bottleneck in aerobiology, palaeoecology and biodiversity monitoring, because scalable sys
arXiv:2608.18131v1 Announce Type: new Abstract: Current safety alignment training for Large Language Models (LLMs) are heavily English-centric. When such safety filters fail for non-English languages,
arXiv:2608.17184v1 Announce Type: new Abstract: Job Safety Analysis (JSA) and pre-task planning can benefit from prior incident records, yet historical accident data is often stored as unstructured na
arXiv:2608.17895v1 Announce Type: cross Abstract: While Multimodal Large Language Models (MLLMs) have made significant strides in visual comprehension, their ability to reason about text-dense, profes
arXiv:2602.23088v2 Announce Type: replace Abstract: Vision foundation models increasingly support interactive scientific workflows, but natural-language interaction requires coupling visual representa
New open-source agent harness just landed! I got early access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the mo
arXiv:2608.17129v1 Announce Type: new Abstract: Vision-language Models (VLMs) excel at 2D grounding, spatial reasoning and agentic tool-based planning in static scenes. However, consider asking a home
arXiv:2608.17501v1 Announce Type: new Abstract: Recent efforts toward fully automated AI scientists have demonstrated that language-model agents can generate hypotheses, execute experiments, and draft
arXiv:2608.17205v1 Announce Type: new Abstract: Vision-language models (VLMs) combine images and text, but when the two conflict and one becomes harder to read, it is unclear how a model shifts its re
arXiv:2608.15939v1 Announce Type: new Abstract: Stateful language agents assume a rejected branch can be taken back by clearing it from the application transcript. We show this breaks when the serving
arXiv:2608.16347v1 Announce Type: new Abstract: Direct communication between AI systems relies on natural language as an intermediate layer, incurring encoding/decoding overhead, token cost, and laten
arXiv:2608.15404v1 Announce Type: new Abstract: Concept Bottleneck Models (CBMs) are designed to make visual classification interpretable by expressing predictions through human-understandable concept
arXiv:2608.14791v1 Announce Type: new Abstract: Abductive reasoning, often characterized as inference to the best explanation, is central to explanation under uncertainty, from everyday sense-making a
arXiv:2608.16190v1 Announce Type: cross Abstract: Trusted monitoring has a cheap, trusted model score a stronger untrusted model's actions, and a diverse ensemble of them beats a single stronger monit
arXiv:2608.14651v1 Announce Type: new Abstract: Effective disaster risk communication is a foundational humanitarian challenge, yet current emergency infrastructure fails to meet the needs of individu
arXiv:2608.14903v1 Announce Type: new Abstract: Quantitative forecasts of frontier artificial intelligence often connect dated targets to trends in benchmark scores, training compute, release time, or
arXiv:2608.15022v1 Announce Type: new Abstract: Language models hold latent quantities in a form they can report on, and more of a quantity is present in that form when the task requires reusing it fl
GLM-5.3 achieves 60 on the Artificial Analysis Intelligence Index, on par with Kimi K3 and up 7 points from GLM-5.2. Once the weights are released it will be tied as the leading open weights model @Za