Knowledge catalogue
Anthropic: Anthropic launches Claude Haiku 5.5, the first Haiku model with effort controls, for high-volume, cost-sensitive tasks like summary and classification requests — Introducing Claude Haiku 5.
arXiv:2610.06966v1 Announce Type: cross Abstract: Indirect prompt injection (IPI) hides adversarial instructions in content that large language model (LLM) agents read at runtime. As agents compose he
arXiv:2606.21399v2 Announce Type: replace Abstract: Runtime oversight often intervenes when an LLM agent's calibrated failure score crosses a threshold. Yet states with the same failure risk can diffe
arXiv:2610.07289v1 Announce Type: cross Abstract: Manual repair of program failures is time-consuming and disruptive for software developers, particularly during the pre-submit phase where test failur
ChatGPT can now generate a custom UI for you! GPT-6 and Intelligent UI, now rolling out in ChatGPT for everyone. Intelligent UI in ChatGPT delivers fast, interactive answers that make everyday questio
arXiv:2610.07557v1 Announce Type: cross Abstract: Static-analysis checker synthesis requires agents to interpret a defect specification, inspect a repository, implement analyzer-specific logic, and re
arXiv:2610.08457v1 Announce Type: new Abstract: Integrated circuit design involves multiple design stages: logic synthesis, floorplanning, placement, and routing, with each stage taking hours to weeks
arXiv:2610.08683v1 Announce Type: new Abstract: Full-duplex speech models are trained to converse with a person, but they are increasingly made to converse with each other, in self-play data generatio
arXiv:2610.07075v1 Announce Type: new Abstract: High-quality datasets are essential for reliable machine learning, but dataset curation remains costly and hard to generalize across domains. Existing m
arXiv:2610.07816v1 Announce Type: new Abstract: Small language models (SLMs) are attractive as local agent controllers because they reduce remote inference, latency, and deployment footprint, yet stru
arXiv:2610.07654v1 Announce Type: cross Abstract: On-policy distillation (OPD) has attracted growing attention as an effective way to transfer capabilities from teacher models to student models. Recen
arXiv:2610.08090v1 Announce Type: cross Abstract: IPv6 extension headers (EHs), such as fragmentation, segment routing, and in-situ telemetry, are operationally important yetwidely dropped in transit,
Jay Peters / The Verge: Google launches Playground, a browser-based, no-code AI game creation platform available to US users aged 18+, powered by Gemini, Nano Banana, and Lyria — Google Playground is
GPT-6 and Intelligent UI, now rolling out in ChatGPT for everyone. Intelligent UI in ChatGPT delivers fast, interactive answers that make everyday questions more visual, complex topics easier to grasp
Had early access to the Intelligent UI experience and it was a nice change from walls of text. It also suggests that, increasingly, we are going to see interfaces built on demand for the problem that
arXiv:2610.05275v2 Announce Type: replace Abstract: A large part of political discourse on social media is built and expressed at a level of claims: i.e. declarative, typically single-clause statement
As previously promised, here's Anthropic's new fast, low cost model: Introducing Claude Haiku 5.5. The previous Haiku, 4.5, was very much showing its age. It came out almost a year ago, and was priced
arXiv:2610.07125v1 Announce Type: cross Abstract: While open-weight models have enjoyed steady progress in capabilities and wide adoption across multiple domains, their safety remains an important con
Thursday, October 8 — 15:00–19:00 UTC Access is free and the API is OpenAI-compatible. During those 4 hours, everyone will be asked to use it actively at the same time—coding, chatting, agents, long c
arXiv:2610.07853v1 Announce Type: cross Abstract: Ternary language models such as BitNet b1.58, Falcon-E and BitCPM are fine-tuned with higher-precision latent weights and deployed as ternary codes pr
arXiv:2610.08327v1 Announce Type: new Abstract: Large language models (LLMs) have shown promise in medical question answering and clinical reasoning, yet their improvement remains constrained by stati
Mistral AI introduced **Mistral Large 4** in October 2026 as a general‑purpose agentic model capable of gathering information and producing final deliverables across complex workflows. The launch high
After launching nearly a month ago and spending several weeks as the top free app in Apple's App Store, the latest update to Meta's Muse iOS app introduces native support for the iPad. A Mac version o
arXiv:2610.07519v1 Announce Type: new Abstract: Automatic sign language translation (SLT) has entered consumer products, turning American Sign Language into English text for dictation, messaging, and
Yuliya Chernova / Wall Street Journal: Nous Research, which makes the open-source Hermes AI agent that has hit 22M+ downloads since February, raised 90M at a 1.2B valuation to expand to enterprises —
arXiv:2610.08178v1 Announce Type: new Abstract: Existing latent-based watermarking methods for diffusion models have overestimated their robustness to image distortions, including geometric transforma
arXiv:2610.07817v1 Announce Type: cross Abstract: Organizations automating operational processes need more than a correct outcome: they need to predict how a process will run, know which one actually
arXiv:2610.07787v1 Announce Type: new Abstract: Multi-agent systems (MAS) powered by large language models have shown strong performance across code generation, mathematical reasoning, and question an
OpenAI “rogue” agent activities found on Wikimedia projects Given how tempting a target wikis are for rogue agent swarms, it's not a huge surprise that Wikipedia found evidence of that activity once t
Reuters: OpenAI's first report on teen ChatGPT use says teens spend under 15 minutes a day on average on the chatbot, with less than 2% using it for 3+ hours straight — Teens spend under 15 minutes a
arXiv:2605.06021v2 Announce Type: replace Abstract: Systematic reviews and meta-analyses often need numerical data reported only in figures, and extracting them with interactive digitisers usually req
arXiv:2610.07473v1 Announce Type: new Abstract: Large language models show promise in clinical reasoning, but psychiatric interviewing requires guiding an evolving conversation. Their ability to carry
Seems like a bit of a long shot, but since it’s so mystifying I figured I might as well ask: I have been trying to get Qwen 3.6 35B to function as a local implementation agent in my subagent driven de
Reading eval results is now the slowest part of building agents. I'm Elvis, founder of @dair_ai. I lead research, build, and teach about AI agents. I run harness experiments every night, but reading t
arXiv:2610.08137v1 Announce Type: cross Abstract: AI systems create images and videos with image/video generation models or by writing code and graphics descriptions that are then rendered. These rout
arXiv:2610.07846v1 Announce Type: cross Abstract: The scenario approach is a well-established statistical framework for data-driven decision-making. In particular, in data-driven optimization, the sce
arXiv:2610.08691v1 Announce Type: new Abstract: Large language model agents are accelerating scientific automation, yet verified executions rarely become persistent program-level improvements, and exi
arXiv:2610.08077v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) turns agent experience into learning signals primarily through scalar outcome rewards after intera
arXiv:2610.08668v1 Announce Type: cross Abstract: Behavioral watermarking embeds an owner identifier in an LLM agent's high-level action choices, giving provenance without touching output tokens. Prio
arXiv:2610.07645v1 Announce Type: cross Abstract: Self-improving LLM agents increasingly distill successful experiences into persistent, reusable skills. Existing skill attack methods corrupt this lea
arXiv:2512.23065v4 Announce Type: replace Abstract: The introduction of BERT established encoder-only transformer models as a foundational paradigm in natural language processing. Encoder-only models
arXiv:2610.06914v1 Announce Type: new Abstract: Text2Dashboard is a DataBrain-specific prototype that turns natural-language analytic requests into inspectable dashboards. An installable Codex plugin
This is a great paper from AWS AI Labs. They show that multi-agent coding teams raised their test pass rate by 28.2% and cut wall time by 16.5% without changing the model. The authors achieve this by
today we’re shipping gpt-6 and intelligent ui to everyone! intelligent ui is a bet on model intelligence. we’re letting gpt-6 fill the canvas with high utility visual and interactive components. it’s
arXiv:2610.07089v1 Announce Type: cross Abstract: LLM agents increasingly act in multi-actor environments, exposing them to misuse from multiple sources: decomposition attacks, where a harmful request
arXiv:2610.08225v1 Announce Type: new Abstract: In this work, we introduce Crazyflow, an accurate, differentiable simulator built on JAX. By leveraging jit compilation via XLA, Crazyflow unifies physi
arXiv:2610.07261v1 Announce Type: new Abstract: A team of coding agents can look fine agent by agent yet fail as a team: each passes its own tests while the merged result is broken, and single-agent e
arXiv:2509.26189v2 Announce Type: replace Abstract: The rapid proliferation of Large Language Models has intensified the challenge of distinguishing LLM-generated text from human writing in non-Englis
arXiv:2610.06650v2 Announce Type: replace Abstract: Wikidata is one of the largest open knowledge bases, yet answering a complex question over it still requires a SPARQL query that names the right ent
arXiv:2610.08502v1 Announce Type: cross Abstract: Proactive power management systems reduce processor dynamic power through runtime power prediction and power-aware scheduling. Accurate, stable and lo
arXiv:2610.04022v1 Announce Type: new Abstract: Powered neck exoskeletons are developed to restore head-neck motions for those with neck muscle weakness. Current methods using hand-held input devices
Row-Bot 5.0 with qwen3.8:27b in Ollama, on my own GPU. No API keys, no cloud. Gave it a year of bills, a tenancy agreement, an insurance policy and a rent increase letter (all made up). It spotted a l
Olivia Moore / Andreessen Horowitz: A look at consumer AI trends: ChatGPT has 3x more US subscribers than Claude or Gemini, the top 1% of spenders drive 19.5% of spend, and AI agents gain traction — T
YouTube Link in case it's still pending https://youtu.be/TWXF95YT7W8 🎬 How this was made My part • One-message brief: a 3-minute comedy in a therapist's office with funny, unique characters and one ma
arXiv:2610.06514v1 Announce Type: cross Abstract: The growing adoption of large language model (LLM) agents creates a need for network administrators and security teams to audit agent behavior within
Ashley Capoot / CNBC: Anthropic expands its Claude Startups program with 45K in discounts and credits via the Claude Startup Stack, a 1,000 API credit, and a year of Claude Team — Anthropic on Tuesday
arXiv:2610.06439v1 Announce Type: new Abstract: What happens when a legal AI model learns to look like a lawyer instead of reasoning like one? We fine tune Qwen3-8B with Group Relative Policy Optimisa
Add a voice travel concierge to an airline app with Amazon Bedrock AgentCore, Amazon Nova Sonic for real-time speech, and Amazon Bedrock Knowledge Bases for policy answers. Travelers change seats, che
Context compression is a huge bottleneck for long-running agents. This work finds that context compression hurts long-horizon agents at a few specific points. They propose PAIR, which replays the agen
arXiv:2610.06366v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly deployed for automated software vulnerability analysis. Binary classification alone is insufficient; pra