Knowledge catalogue
🐡 Sakana Fugu リリース 🐡 マルチエージェントを指揮する、一つのモデル ブログ：https://sakana.ai/fugu-release/#Japanese 本日、Sakana AIは新しいプロダクト「Sakana Fugu」の提供を開始しました。Sakana Fuguは、最先端のモデル群からなるマルチエージェントシステム全体を、単一のモデルAPIとして提供します。 難しいタスク
This is a reminder that we are co-hosting a massive pickleball tournament 🏓 next Tuesday June 30th, as folks are in town for the @aiDotEngineer World Fair. Come check it out! https://luma.com/the-agen
Tried & liked it on http://archive.tw. Fugu Ultra pairs well as a advisor & planner with Composer 2.5. For scope/architecture, it’s on par with Fable orchestration. Advisor doesn’t slow the loop if th
A fundamental problem with extending Codex/Cowork/Code to all knowledge work is that they remain very 'software-brained' where the end result (the software) is what is important & that code serves as
🚨🚨🚨A research project idea! How to measure world models? Everyone's talking about world models these days. World model here, world model there. We can argue about what 'world model' actually means, an
I agree with this. Programming abstractions have moved from code to English. Markdown files within a directory are a really simple but versatile container for storing this task hierarchy The next hot
If your AI is still being sycophantic, here’s how to solve it 👀 ✅ Option 1: “here is my research paper - be critical of it please” ✅ Option 2: “here is my research paper - spin up subagents to review
arXiv:2606.11238v1 Announce Type: cross Abstract: Ship finance is a data-intensive and document-heavy segment of asset-based lending, requiring the integration of financial, technical, contractual, an
arXiv:2606.11762v1 Announce Type: cross Abstract: Large language models (LLMs) have achieved remarkable progress in language understanding, reasoning, and generation, sparking growing interest in thei
arXiv:2606.11379v1 Announce Type: new Abstract: Pre-mediation, the preparatory phase preceding direct human negotiation, plays a critical role in achieving mutually beneficial agreements, yet is often
arXiv:2606.12370v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a key component in modern large language models, yet the rollout stage remains the key bottleneck in RL trainin
arXiv:2606.11525v1 Announce Type: cross Abstract: Contrastive Reinforcement Learning (CRL) has seen recent success in a wide variety of goal-conditioned robotics tasks by learning structured represent
arXiv:2606.12291v1 Announce Type: new Abstract: Large language models (LLMs) now reach expert-level scores on medical licensing exams, encouraging the assumption that high scores imply safe medical ju
arXiv:2606.11284v1 Announce Type: cross Abstract: Real-world multi-agent systems, from traffic coordination to resource allocation, are often modeled as general-sum games where individual incentives c
arXiv:2606.11880v1 Announce Type: new Abstract: Visual localization in complex indoor environments remains a critical challenge for robotics and AR applications. Sequential localization, where pose es
arXiv:2606.11470v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved strong performance across natural language processing tasks, yet reliable reasoning remains an open challenge
arXiv:2606.10478v1 Announce Type: new Abstract: Most recent 3D reconstruction and editing systems operate on implicit and explicit representations such as NeRF, point clouds, or meshes. While these re
arXiv:2606.09931v1 Announce Type: cross Abstract: Lampson's confinement problem asks how to prevent a program that processes confidential information from leaking it to a third party. We introduce the
arXiv:2606.10389v1 Announce Type: new Abstract: Recent advances in LLM-driven code evolution have enabled automated discovery by iteratively generating and improving programs. However, applying these
arXiv:2606.10044v1 Announce Type: new Abstract: Businesses are increasingly adopting AI-enabled tools to improve productivity, reduce costs, and enhance products and services. However, the transformat
arXiv:2606.10582v1 Announce Type: cross Abstract: Generalization in emergent communication has largely focused on novel inputs or linguistic structures, yet the capacity for agents to communicate with
arXiv:2606.09935v1 Announce Type: cross Abstract: AI-powered agents are increasingly embedded in continuous integration and continuous delivery/deployment (CI/CD) pipelines to autonomously review pull
arXiv:2606.10956v1 Announce Type: new Abstract: The deployment of Large Language Model (LLM) agents for computer automation is accelerating, yet their ability to navigate complex, professional-grade p
arXiv:2606.08849v1 Announce Type: new Abstract: Urban public transport disruptions require rapid response strategies, yet existing studies rarely provide a decision support framework to compare altern
arXiv:2508.00917v2 Announce Type: replace-cross Abstract: Connected autonomous vehicles (CAVs) must simultaneously perform multiple tasks, such as perception, prediction, planning, and control, to ens
arXiv:2606.09556v1 Announce Type: new Abstract: AI Scientist agents are often evaluated as if capability were mainly a function of model quality, prompting, or reasoning scaffolds. We test a different
As frontier models (e.g. Fable 5) continue to push the task horizon of knowledge work automation, it becomes ever more important for humans to be able to audit decisions back to the source context. It
arXiv:2606.08168v1 Announce Type: cross Abstract: Leading commercial endpoint detection and response (EDR) products have shifted from operator-configured rule sets to multi-component systems where aut
arXiv:2606.08102v1 Announce Type: cross Abstract: Multi-quadruped coordination has attracted increasing attention due to its enhanced payload capacity, broader contact coverage, and improved adaptabil
arXiv:2308.07822v2 Announce Type: replace Abstract: The transformation towards renewable energy and feedstock supply in the chemical industry requires new conceptual process design approaches. Recentl
arXiv:2606.07999v1 Announce Type: new Abstract: Effective skill grounding is essential for deploying reusable skills in embodied agents, as even minor embodiment or environmental differences can rende
arXiv:2606.09663v1 Announce Type: new Abstract: Recursive self-design refers to AI-assisted modification of the mechanisms by which an AI system is built, evaluated, and improved. This paper treats Me
arXiv:2603.24925v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) systems that rely on semantic search often fail to retrieve the complete set of evidence for complex queries, p
I didn't have early access to today's Claude Fable 5 release, but I've spent the past ~5.5 hours putting it through its paces. My initial impressions are that this is something of a beast. It's slow,
Parsing a document accurately is one thing. Proving where every value came from is another. When a compliance team reviews an AI extraction, or an auditor needs to sign off on a figure pulled from a f
arXiv:2510.17947v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are improving at an exceptional rate. With the advent of agentic workflows, multi-turn dialogue has become the de
arXiv:2603.18388v2 Announce Type: replace Abstract: Automatic prompt optimization (APO) has emerged as a powerful paradigm for improving LLM performance without manual prompt engineering. Reflective A
arXiv:2606.07591v1 Announce Type: cross Abstract: AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify. We presen
arXiv:2606.08529v1 Announce Type: new Abstract: Published agent capability scores conflate what a model can do with what its scaffold lets it do, and the magnitude of this elicitation gap is not well
arXiv:2606.09227v1 Announce Type: cross Abstract: The convergence of the 2026 European Union Safe and Sustainable by Design (SSbD) framework, Corporate Sustainability Due Diligence Directive (CSDDD),
arXiv:2606.06972v1 Announce Type: new Abstract: Ensuring that agent behaviours are aligned with human moral values inevitably raises the problem of how to account for the plurality of moral perspectiv
arXiv:2606.06721v1 Announce Type: cross Abstract: Robots that operate over extended periods should not merely visit space; they should progressively understand it. Yet most 3D scene graph pipelines tr
The AI champions strategy of 2023 doesn't work in 2026. Let me give you my very hot take 🔥 (And know that this is anecdotal, and the world of AI changes every 2 heartbeats, so by the time I finish thi
AIを作るAIを作る：RSI Lab始動 https://sakana.ai/rsi-lab-jp/ Sakana AIは、再帰的自己改善(Recursive Self-Improvement、RSI)に取り組む専任の研究グループ「RSI Lab」を、東京で立ち上げます。RSIは、AIがAIそのものを作る仕組みです。 この2年間、私たちはLLM-Squared、Darwin Gödel Machi
arXiv:2606.06261v1 Announce Type: cross Abstract: O-RAN enables a disaggregated baseband stack with programmable functions that communicate over standardized open interfaces. The same openness that en
Hermes Desktop 现已支持简体中文——聊天界面完整适配简体中文。 桌面应用现在已在所有 UI 界面全面提供简体中文（Simplified Chinese / 简体中文）翻译：包括聊天窗口本身、侧边栏、设置、命令中心、cron、消息、个人资料、技能、智能体等全部内容。 英语仍为默认语言；你可以在“外观”设置中切换语言，选择后会自动保存到配置项 display.language。 Herm
This analysis from yesterday looks even more apt today — especially after we heard that the model providers have gone to Washington in search of handouts. ⚠️Why didn’t the hyperscalers wait until afte
arXiv:2606.05415v1 Announce Type: new Abstract: Real-world data spans tables, documents, and semi-structured files with implicit semantics. Querying this data requires integrating evidence across inco
This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. The Meta hack shows there’s more to AI security than Mythos On
1/ 🔥 @NoPriorsPod x @LatentSpacePod chat with @SatyaNadella at @Microsoft Build. He has the sharpest mental models of any public company CEO I've interviewed. $MSFT is at its heart still a tools compa
arXiv:2606.05080v1 Announce Type: new Abstract: Scientific and engineering progress is fundamentally a long-horizon iterative process: proposing changes, running experiments, measuring outcomes, and c
arXiv:2603.10971v2 Announce Type: replace-cross Abstract: Reinforcement learning has achieved remarkable success in domains such as Atari games, navigation, and locomotion, where exploration can often
arXiv:2606.04149v1 Announce Type: new Abstract: Learning a single policy that reaches a goal with high geometric precision while interacting safely with nearby agents poses conflicting objectives. Pre
arXiv:2606.04769v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) has emerged as a critical standard empowering Large Language Models (LLMs) to utilize external tools. In this ecosyst
here’s why i think the situation may be dire: https://x.com/GaryMarcus/status/2062369417372258652?s=20 ⚠️Why didn’t the hyperscalers wait until after the IPO in switching to pay-by-usage-charging? My
Many research labs only consider inference efficiency after the fact. Step 3.7 Flash is a 198B sparse MoE VLM designed by @StepFun_ai for inference from the start. 196B language backbone with a 1.8B v
NVIDIA’s Nemotron 3 Ultra is available on Ollama’s cloud! Try it 👇 Claude Code: ollama launch claude --model nemotron-3-ultra:cloud Hermes Agent: ollama launch hermes --model nemotron-3-ultra:cloud Op
arXiv:2603.10044v2 Announce Type: replace-cross Abstract: A safety score earned on a benchmark need not predict how the same model behaves once it is wrapped in an agentic scaffold the benchmark never
arXiv:2602.01619v2 Announce Type: replace-cross Abstract: Unsupervised Skill Discovery (USD) aims to autonomously learn a diverse set of skills without relying on extrinsic rewards. One of the most co
⚠️Why didn’t the hyperscalers wait until after the IPO in switching to pay-by-usage-charging? My guess is that *they literally could not afford to* —because it would bankrupt them. My reasoning: in “a