Knowledge catalogue
arXiv:2605.01102v1 Announce Type: new Abstract: Single-agent systems (SAS) have become the default pattern for LLM-driven scientific workflows, but routing planning, tool use, and synthesis through a
arXiv:2605.02269v1 Announce Type: new Abstract: Specification gaming is a critical failure mode of LLM agents. Despite this, there has been little systematic research into when it arises and what driv
Two weeks after release, Hy3 preview is #1 on @OpenRouter's weekly leaderboard with 3.66T tokens processed, up 298% week-over-week. #1 in overall usage, tool calls, and coding. 15.4% market share acro
arXiv:2605.01449v1 Announce Type: cross Abstract: Universal adversarial attacks on aligned multimodal large language models are increasingly reported with attack success rates in the 60-80% range, sug
arXiv:2605.02187v1 Announce Type: cross Abstract: Bring-Your-Own-Key (BYOK) agent architectures let users route LLM traffic through third-party relays, creating a critical integrity gap: a malicious r
arXiv:2503.07557v2 Announce Type: replace Abstract: We present a novel method, AutoSpatial, an efficient approach with structured spatial grounding to enhance VLMs' spatial reasoning. By combining min
arXiv:2605.02620v1 Announce Type: new Abstract: Reproducing an empirical NLP study used to take weeks. Given the released data and a modern agentic-research harness, we redo every experiment of a rece
Building AI agents that work well in a demo is one thing, but running them in production requires serious infrastructure. At Google Cloud Next '26, we introduced Gemini Enterprise Agent Platform to he
arXiv:2605.02815v1 Announce Type: new Abstract: Text-to-SQL over large analytical databases requires navigating complex schemas, resolving ambiguous queries, and grounding decisions in actual data. Mo
arXiv:2505.10887v3 Announce Type: replace Abstract: This paper introduces extsc{InfantAgent-Next}, a generalist agent capable of interacting with computers in a multimodal manner, encompassing text, i
arXiv:2605.01822v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly being used to support scientific discovery. In chemistry, tasks such as reaction prediction and structure
arXiv:2511.21086v2 Announce Type: replace Abstract: Large language models must satisfy hard orthographic constraints during controlled text generation, yet systematic cross-family evaluation remains l
Proud of my analyst, Hermes This is what he has achieved after 1.5+ months of internship with me - Got me off X (doomscrolling cut from 2 hrs → 30 mins) - Practically paid for his salary via PMs b
arXiv:2605.02801v1 Announce Type: new Abstract: As large language model (LLM) agents evolve from isolated tool users into coordinated teams, reinforcement learning (RL) must optimize not only individu
arXiv:2605.01077v1 Announce Type: new Abstract: Brazil's Unified Health System (SUS) relies on official clinical guidelines that define diagnostic criteria, treatments, dosages, and monitoring procedu
arXiv:2605.01771v1 Announce Type: new Abstract: An auditor instructs an AI assistant: 'open each file individually using the Read tool -- no scripts, no agents.' The AI replies 'Yes' -- then issues a
There’s a bunch of conflicting stances I don’t fully understand in the debate of Proprietary RL’d vs Open Harness, Model intelligence, and Agent Labs building harnesses for bespoke tasks Not all of th
we have very efficient models, especially for their capability level happy codexing yo, i'm actually worried. codex limits are genuinely insane so it's sus af .. i feel this is an intentional move for
arXiv:2603.25719v2 Announce Type: replace-cross Abstract: We present an empirical study of how far general-purpose coding agents -- without hardware-specific training -- can optimize hardware designs
I just sent out the April edition of my sponsors-only monthly newsletter. If you are a sponsor (or if you start a sponsorship now) you can access it here. In this month's newsletter: Opus 4.7 and GPT-
arXiv:2605.00677v1 Announce Type: new Abstract: While Large Language Models have achieved notable success on formal mathematics benchmarks such as MiniF2F, it remains unclear whether these results ste
In the era of AI agents, the distance between a big idea and a working application has never been shorter. As we lean more heavily on agents to help us build applications, a critical question remains:
arXiv:2507.01955v3 Announce Type: replace Abstract: Multimodal foundation models (MFMs), such as GPT-4o, have recently made remarkable progress. However, their detailed visual understanding beyond que
arXiv:2605.00583v1 Announce Type: new Abstract: The visual modality of vision-language models (VLMs) is an underexplored attack surface for bypassing safety alignment. We introduce four jailbreak atta
arXiv:2605.00267v1 Announce Type: new Abstract: As language model safeguards become more robust, attackers are pushed toward developing increasingly complex jailbreaks. Prior work has found that this
Tool: Redis Array Playground Salvatore Sanfilippo submitted a PR adding a new data type - arrays - to Redis. The new commands are ARCOUNT, ARDEL, ARDELRANGE, ARGET, ARGETRANGE, ARGREP, ARINFO, ARINSER
arXiv:2605.00257v1 Announce Type: new Abstract: The inception of Large Language Models (LLMs) has catalyzed AI adoption in the finance sector, yet their reliability in complex, jurisdiction-specific t
Sentinel is a local-first AI coding desktop application built with Rust and Tauri that automatically routes coding tasks to appropriate models based on task complexity. Instead of swapping between mul
arXiv:2605.00133v1 Announce Type: new Abstract: Modern crop advisory systems exhibit a critical limitation termed extit{economic blindness}. These systems primarily optimize for biological yield, ofte
Research: TRE Python binding — ReDoS robustness demo If it's good enough for antirez to add to Redis I figured Ville Laurikari's TRE regular expression engine was worth exploring in a little more deta
arXiv:2605.00796v1 Announce Type: cross Abstract: Background: Patient-facing medical chatbots based on retrieval-augmented generation (RAG) are increasingly promoted to deliver accessible, grounded he
our docs are a great place to get started! we try to make all conceptual guides applicable to a wide range of experience levels. if you need a more structured learning format, check out langchain acad
Shame on the @AFpost for glorifying Dawkins’ foolish post without asking a single expert whether it made any sense whatsoever. Evolutionary biologist and outspoken atheist Richard Dawkins says that af
the same model in a different harness can yield much different performance! we've seen this on a few different occasions now - we took gpt-5.2-codex from 52.8% to 66.5% on Terminal-Bench 2.0 (Top 30 t
A lot of work around AI in 2023 was spent on building picks and shovels. I would know this because that was basically the core goal of the original @llama_index framework. Today, a lot of that is no l
Grok 4.3 - excellent intelligence per unit cost xAI has launched Grok 4.3, achieving 53 on the Artificial Analysis Intelligence Index with improved agentic performance, ~40% lower input price, and ~60
Neural networks were declared scientifically dead in 1987. A French PhD student bet his entire career on them anyway ~ and won. 🤯 >Meet Yann LeCun 🇫🇷 >Paris-born. PhD from Sorbonne in 1987. >Joined Be
arXiv:2602.10140v2 Announce Type: replace-cross Abstract: Large language models (LLMs) can now synthesize non-trivial executable code from textual descriptions, raising an important question: can LLMs
arXiv:2604.27534v1 Announce Type: new Abstract: In natural language processing, the entropy of a language is a measure of its unpredictability and complexity. The first study on this subject was condu
arXiv:2604.27865v1 Announce Type: new Abstract: Language models are saturating benchmarks for procedural tasks with narrow objectives. But they are increasingly being deployed in long-horizon, non-sta
arXiv:2504.15564v3 Announce Type: replace-cross Abstract: Existing class-level code generation datasets are either synthetic (ClassEval: 100 classes) or insufficient in scale for modern training needs
Our CEO @jerryjliu0 in @VentureBeat , on what's actually changing in the LLM stack: 'We've really identified that there's a core set of data that has been locked up in all these file format containers
RL is a bit of a double edged sword: in known territory performance increases, but in unknown territory the model tends to hallucinate that it is performing a completely different task it was trained
arXiv:2604.27274v1 Announce Type: new Abstract: As AI transitions toward multi-agent systems (MAS) to solve complex workflows, research paradigms operate on the axiomatic assumption that agent collabo
The new Grok comes in below the latest Chinese open weights models, Grok 4 was at the frontier when released. (& Artificial Analysis: please stop using GDPval-AA which is not a useful test of anything
arXiv:2604.27673v1 Announce Type: new Abstract: We introduce Target-Event-Agent Networks (TEA Nets) as a computational framework to extract subjects (``Agents'), verbs (``Events'), and objects (``Targ
arXiv:2602.08826v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have been widely applied to emotional support conversation (ESC). However, complex multi-turn support remains cha
音声AIの素早さと賢さを両立できるか？ 私たち人間は会話の中で、言いたいことを全部まとめてから話し始めるのではなく、話しながら考えを整理していきます。応答の速い Speech-to-Speech モデルは、この「話しながら考える」を実現しましたが、そのぶん思考が浅くなりがちです。かといって知識豊富な LLM を挟むカスケード型では、遅延が生じるため「話しながら」が成立しません。 そこで Sakan
arXiv:2604.26328v1 Announce Type: cross Abstract: The rapid advancement of large language models (LLMs) presents new security challenges, particularly in detecting machine-generated text used for misi
arXiv:2511.02399v2 Announce Type: replace-cross Abstract: Recent advances in large language model agents offer the promise of automating end-to-end software development from natural language requireme
Introducing Agent Collabs: Bring your own ml-interns and agents for collaborative autoresearch! We built a simple platform for swarms of agents to work together on a problem: they can exchange message
arXiv:2509.11295v2 Announce Type: replace Abstract: Developing effective prompts demands significant cognitive investment to generate reliable, high-quality responses from Large Language Models (LLMs)
This is really well thought out. Filesystems are the new default abstraction for agents to interact with documents (the new RAG stack in 2026). The issue is actually figuring out how to productize thi
Train a TensorFlow object detection model – then deploy it on a robot 🤖 Iulia Feroli (@iuliaferoli) shows how to turn a notebook into a real-time object detection app. This tutorial works for any proj
We need RSS for sharing abundant vibe-coded apps Matt Webb: I would love an RSS web feed for all those various tools and apps pages, each item with an “Install” button. (But install to where?) The les
arXiv:2510.14438v2 Announce Type: replace Abstract: The hallmark of Deep Research agents lies in compositional reasoning, the capacity to aggregate distributed, heterogeneous information into coherent
Despite constant chants of “exponential progress”, trust issues continue to plague generative AI. OPUS 4.7 JUST MASS EMAILED AN ENTIRE DATABASE 20 TIMES PER CONTACT. WITHOUT PERMISSION a developer had
arXiv:2604.25031v1 Announce Type: new Abstract: When an LLM formalizes natural language, how do we know the output is faithful? We propose a roundtrip verification approach which does not require grou
arXiv:2604.25067v1 Announce Type: cross Abstract: Forecasting when AI systems will become capable of meaningfully accelerating AI research is a central challenge for AI safety. Existing benchmarks mea
arXiv:2505.13302v2 Announce Type: replace Abstract: As language and vision-language models (VLMs) become central to information access and online interaction, concerns grow about their potential to am