Knowledge catalogue
arXiv:2607.20536v1 Announce Type: new Abstract: Tool-use agents that address day-to-day digital tasks such as ordering groceries must not only operate applications, but also interact with the user, e.
arXiv:2512.16300v3 Announce Type: replace Abstract: Existing image forgery detection (IFD) methods either exploit low-level, semantics-agnostic artifacts or rely on multimodal large language models (M
arXiv:2607.19739v1 Announce Type: cross Abstract: Although large language models (LLMs) have recently gained traction in recommender systems due to their strong reasoning capabilities and extensive wo
arXiv:2607.13071v1 Announce Type: cross Abstract: Agentic LLM coding tools compress long session histories into compaction summaries that subsequent sessions inherit as ground truth. This paper docume
arXiv:2607.12375v1 Announce Type: cross Abstract: Image Quality Assessment (IQA) in open-world environments remains challenging due to limited generalization and interpretability. Recent approaches ba
Just shared my favorite AI model and tool for every use case. Check out the list here: https://aiwithallie.beehiiv.com/p/the-best-ai-model-and-tool-for-every-use-case I'm writing a newsletter on my fa
OpenAI released ChatGPT Work, a general-purpose productivity agent designed to help people with ambitious tasks beyond traditional coding projects. The tool performs actions autonomously across connec
arXiv:2607.05403v1 Announce Type: cross Abstract: This paper aims to synthesize empirical research on AI tools used to support English as a second/foreign language (EL2) learners in Arab University cl
Researchers discovered a HalluSquatting attack that exploits AI tools' tendency to hallucinate package names, which attackers can register to trick AI assistants into running malicious code and assemb
Marina Temkin / TechCrunch: Prime Intellect, which helps companies build their own AI agents by offering computing power and specialized tools, raised a 130M Series A at a 1B valuation — Prime Intelle
Karissa Bell / Engadget: Meta says Muse Image includes an invisible watermarking system called Content Seal and previews a web tool to check whether an image was generated with Meta AI — It has rate l
arXiv:2607.02931v1 Announce Type: new Abstract: AI tools are accelerating scientific publication while the systems that review it struggle to keep up, and independent verification of published researc
Armin Ronacher / Armin Ronacher's Thoughts and Writings: Claude Opus 4.8 and Sonnet 5 seem worse at tool calls than older models, likely due to post-training that assumes Claude Code-like harnesses as
Jennifer Medina / New York Times: Some US voters are using AI tools as nonpartisan researchers, seeing them as a viable alternative to traditional news coverage, voter guides, and social media — It ta
arXiv:2603.08195v2 Announce Type: replace Abstract: Motivation: The rapid growth of biological data has intensified the need for transparent, reproducible, and well-documented computational workflows.
arXiv:2606.30549v1 Announce Type: cross Abstract: AI code completion tools, such as Github Copilot, provide students with code suggestions to help them write programs. However, recent qualitative stud
arXiv:2512.10359v1 Announce Type: cross Abstract: Video Question Answering (VideoQA) task serves as a critical playground for evaluating whether foundation models can effectively perceive, understand,
Mateo Quiros / The Keyword: Google says computer use is now a built-in tool supported in Gemini 3.5 Flash, available via the Gemini API and Gemini Enterprise Agent Platform — Computer use is now a bui
Lorelei Smillie / Bloomberg: Microsoft's Digital Crimes Unit says AI helped it link two separate hacking tools, Amadey and StealC, and file a single civil lawsuit to help take them down — Investigator
arXiv:2606.11672v1 Announce Type: cross Abstract: This paper explores the value of agentic AI tools for cybersecurity purposes. We evaluate the efficacy of a general-purpose GenAI Large Language Model
Building Pakistan Notice Helper is a small AI tool designed to address a localized safety issue in Pakistan by helping users understand and process building-related notices. Developed as a hackathon p
Gary Marcus argues that large language models based on transformers quickly reach their limitations, prompting developers to add external tools as workarounds, while neurosymbolic AI—which combines ne
Lucinda Shen / Axios: Infinity Constellation, which builds AI tools and software businesses for the professional services market, raised a 24M Series A; it previously raised 17M — Infinity Constellati
arXiv:2606.06835v1 Announce Type: new Abstract: The performance gap across languages in LLMs is well documented, and closing it natively requires pretraining or fine-tuning on corpora that, for most l
even though @activegraphai is not a memory tool, it's a runtime built around memory so it can do well there cool to see a third party verify this and see that activegraph does well on privacy programs
This article from Ben's Bites likely discusses how creating foundational tools and infrastructure enables developers and organizations to build more complex applications and scale their operations mor
arXiv:2606.04579v1 Announce Type: new Abstract: While Process Reward Models (PRMs) have achieved remarkable success in mathematical reasoning, their application in complex scientific domains-such as b
CJ Haddad / CNBC: Supabase, which provides backend tools for building AI apps, raised a 500M Series F led by GIC at a 10B pre-money valuation, up from $5B in October 2025 — Vibe coding needs infrastru
In this post, you learn how to use Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) together to improve the tool-calling accuracy of a small language model (SLM). The example uses
Jyoti Mann / The Information: Internal documents: Meta is considering tiered pricing for “Hatch”, its planned OpenClaw-like AI agent tool, including a 200-per-month premium subscription — Meta Platfor
OpenAI Group PBC today released a set of features that will make it easier for nontechnical people to use its Codex automation tool. The update comes five months after Anthropic PBC added similar capa
Natalie Lung / Bloomberg: Uber says it has limited all employees to $1,500 in monthly token spending per AI coding tool “to responsibly encourage agentic AI adoption” — Uber Technologies Inc. has set
Not content with just providing the infrastructure for the next generation of artificial intelligence agents, Nvidia Corp. is also providing the tools for developers to build them. At Nvidia GTC Taipe
Maria Curi / Axios: OpenAI says it has briefed the White House on its new biodefense program, which uses GPT-Rosalind to help develop biodefense and pandemic preparedness tools — OpenAI is launching a
Brody Ford / Bloomberg: Autodesk agrees to buy MaintainX, a company focused on maintenance tools, in an all-cash deal that values MaintainX at 3.6B — Engineering software maker Autodesk Inc. has agree
Samantha Subin / CNBC: Okta reports Q1 revenue up 11% YoY to 765M, vs. 752M est., says the agentic AI build-out is spiking demand for its identity tools; OKTA jumps 8%+ after hours — Okta beat Wall St
arXiv:2605.28224v1 Announce Type: new Abstract: Multi-trajectory inference for tool-use LLM agents - generating multiple reasoning attempts and selecting among them - benefits from transferring knowle
Model-Harness-Task fit! it’s clear that RL post-training produces a model-harness fit via tool shapes and prompting as models are trained with the harness in the loop. Mentioned this in a previous Lan
Building agents (like software) is a deeply iterative process --> this is why we try to supply as much easy to use tooling and infra as possible so builders can start on their agent improvement journe
arXiv:2508.15760v2 Announce Type: replace-cross Abstract: Tool calling has emerged as a critical capability for AI agents. In contrast to conventional tool calling frameworks that rely on static, prov
Visual Fold is a tool for simple visual organization of ComfyUI workflows that does not turn selected nodes into a subgraph or change workflow logic. Group folding and node alignment features enable c
arXiv:2605.20682v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have shown remarkable capability in bridging visual perception and textual reasoning, enabling zero-shot unders
streaming from modern agents is pretty complex! especially with - parallel tools / subagents - multimodal content - human in the loop events our new streaming primitives make all of this ergonomic! Ag
arXiv:2605.19179v1 Announce Type: cross Abstract: We present a cloud-based tool that uses drones and machine learning to help recover instrumentally observed meteorite falls. We showcase a collection
deepagents v0.6 ships w/ support for code interpreters! these are the perfect happy medium between pure tool execution and heavyweight sandboxes they give your agent an environment where it can... → k
For centuries, the scientific method has been our best tool for progress. But today, there’s so much data out there that it’s impossible for any one researcher to connect all the dots. We want to fix
we've been building agents around the llm, starting with conversations, adding tools, giving rules, logging everything, and storing a form of it as retrievable state Active Graphs flips this. what if
arXiv:2605.18703v1 Announce Type: new Abstract: Equipping LLMs with tool-use capabilities via Agentic Reinforcement Learning (Agentic RL) is bottlenecked by two challenges: the lack of scalable, robus
A developer created a terminal user interface (TUI) tool that enables local large language models (LLMs) running on Ollama or cloud platforms to debate each other as a method for detecting and reducin
This post describes a visualization tool that provides real-time insight into GPT-2's internal processing by displaying concept activations as a 3D graph, with each token generation showing which neur
A developer created a visualization tool that displays GPT-2's internal concept activations in real-time during text generation, representing the model's 'thinking' process as a 3D graph that updates
Simon Sharwood / The Register: In his weekly Linux kernel post, Linus Torvalds says “AI tools are great” but duplicate bug reports have made the security list “almost entirely unmanageable” — Multiple
David Cendon Garcia / EU-Startups: Milan-based Webidoo, which develops an operational layer designed to help SMBs access AI tools, raised $25M led by IXC3 for North American expansion — Milan-based We
symbolic tools like those listed below - rather than pure scaling -are likely driving most of the advances now. once you realize that you realize that hyperscaling is probably insane. @GaryMarcus IMHO
arXiv:2605.14461v1 Announce Type: new Abstract: Existing object removal tools often rely on manual masks or text prompts, making precise removal difficult for non-expert users in complex scenes and of
Ivan Mehta / TechCrunch: OpenAI debuts personal finance tools for US ChatGPT Pro users, partnering with Plaid to give access to 12K+ financial institutions to analyze spending and more — On Friday, Op
Anthropic PBC, the developer and provider of the Claude artificial intelligence model family, said it’s offering a special credit pool for users who want to use agentic tools with its large language m
arXiv:2605.13360v1 Announce Type: new Abstract: There is a growing demand for agentic AI technologies for a range of downstream applications like customer service and personal assistants. For applicat
Jared Perlo / NBC News: OpenEvidence, an AI-powered medical search tool, says it's used by two-thirds of US physicians, or ~650K doctors, and an additional 1.2M doctors internationally — OpenEvidence,
arXiv:2605.11240v1 Announce Type: cross Abstract: Generative AI models differ from traditional machine learning tools in that they allow users to provide as much or as little information as they choos