Knowledge catalogue
Huge release from @odysseyml. Odyssey-3 Pro sets a new top score on Physics-IQ Verified, a benchmark that asks models to continue videos of real physics experiments. The robotics results stood out to
Yesterday TechCrunch published a piece about a growing problem for AI agents: websites are starting to block them. Amazon blocking Meta's Muse is the obvious example. At almost exactly the same time,
arXiv:2610.08329v1 Announce Type: new Abstract: We present an AI-assisted Lean 4 formalization of the Poincare conjecture. The project began with limited reusable formal infrastructure for the geometr
arXiv:2610.06986v1 Announce Type: new Abstract: AI research agents are increasingly used to search over programs, mathematical constructions, and proofs. However, existing systems typically optimize e
arXiv:2610.07669v1 Announce Type: cross Abstract: We assessed the value of two live human-AI interactions in a precision disease control project in California vineyards. The project tested whether 202
I've recently been working part-time on an AutoResearch-style project. The setup is roughly: humans take recent work from top-tier ML/AI conferences, turn part of it into a well-defined task with an e
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:2610.07640v1 Announce Type: new Abstract: State-of-the-art reinforcement learning agents are capable of outperforming human experts at games like chess, Go and StarCraft II. These agents do not
arXiv:2610.06651v1 Announce Type: new Abstract: Methods for generalization in model-based reinforcement learning typically assume that an agent cannot recover the latent context governing the environm
arXiv:2610.06777v1 Announce Type: cross Abstract: The CADENCE algorithm solves the Partially Observable Cooperative Guard Art Gallery Problem (POCGAGP) with formal coverage and connectivity guarantees
arXiv:2610.05456v1 Announce Type: cross Abstract: In Networked Markov Decision Processes, transition dynamics are often unknown and the state--action space grows rapidly with the number of agents. In
arXiv:2610.04433v1 Announce Type: cross Abstract: A coding agent is a language model wrapped in a harness: the system prompt, the tool set, and the context management that turn a chat model into somet
arXiv:2610.02298v1 Announce Type: cross Abstract: 3D editing methods are usually tested on a single edit, yet an asset is built through a long sequence of revisions, each of which must implement the r
Hi folks, LIVE PROJECT PAGE TLDR: Moral of the story. You need better CPU to do actual agentic coding doing real work... I've been on a mission to make my RTX5090 go brrr for past 2 months so much so
arXiv:2610.02452v1 Announce Type: new Abstract: The operation of dynamically polarized targets in nuclear physics experiments relies on continuous tuning of the microwave frequency to compensate for r
arXiv:2610.02726v1 Announce Type: new Abstract: Flow-matching-based multi-view world models generate realistic videos, but are commonly restricted to fixed camera rigs. Extending them to continuously
We're taking over a coffee shop on Union st. for 3 days of SF @Techweek_ by @a16z . The goal is to make it the busiest pop-up in the city this week. Mon to Wed, 9am to 4pm, franko & friends in the mar
HuggingFace just closed a major gap in harness engineering! (the ultimate guide to multi-harness RL) the same open-weight model can perform well inside one harness, then lose accuracy or produce inval
.@OpenRouter co-founder Alex Atallah, in his first podcast since Stripe acquired the company, joins @Replit co-founder Amjad Masad and a16z's Erik Torenberg on why the future of AI is independence and
arXiv:2512.06205v3 Announce Type: replace Abstract: The symbol grounding problem asks how a token such as cat can be about cats. We propose a framework for auditing grounding claims against a declared
arXiv:2610.01834v1 Announce Type: new Abstract: Judgment models such as jev{} return, in a single call and without reasoning text, a probability for each described option. This makes them attractive a
arXiv:2610.02196v1 Announce Type: cross Abstract: We study test-time evolution for humanoid loco-manipulation: solving tasks that a controller was never trained for by repurposing its existing skills,
arXiv:2610.00353v1 Announce Type: new Abstract: A sound judgment applies the law to established facts and weighs the circumstances in which they arose. However, existing methods swing between rigid st
arXiv:2610.02181v1 Announce Type: new Abstract: We present OmniSeek, an agentic framework that transforms an Omni Large Language Model (Omni-LLM) into an active, multi-turn reasoning agent with native
arXiv:2610.01093v1 Announce Type: cross Abstract: Spacecraft rendezvous and proximity operations (RPO) are currently planned through an expertise-intensive process in which engineers translate high-le
arXiv:2610.01257v1 Announce Type: cross Abstract: Scientific progress emerges from a longitudinal ecosystem in which researchers, institutions, funding agencies, collaboration networks, and the scient
https://huggingface.co/Wa1k3r/Qwen3.8-27b-CODER-4q_xs-24GB-262k-Optimalcardfit Qwen3.8-27B CODER — IQ4_XS imatrix · 24 GB card fit · ~262k context · MTP draft Quantized, Abliterated, and fitted by Lex
arXiv:2610.02159v1 Announce Type: new Abstract: Intrinsic rewards are designed to guide exploration in reinforcement learning by assigning value to an agent's experience, for example through predictio
arXiv:2610.02162v1 Announce Type: new Abstract: How can a world model continuously observe regions beyond the actor's current view? Video world models simulate how an environment evolves from an agent
arXiv:2609.38954v1 Announce Type: cross Abstract: Large language model (LLM) agents could help security operations centers (SOCs) investigate advanced persistent threats (APTs) by turning weak leads i
arXiv:2609.38527v1 Announce Type: new Abstract: This work evaluates the direct transfer of a co-evolved communication protocol from a 2D simulation to a 3D physical environment, without retraining the
arXiv:2609.38604v1 Announce Type: cross Abstract: Modern LLM agents increasingly tackle complex tasks through interactive, long-horizon exchanges with users, while existing benchmarks generally assume
arXiv:2609.39166v1 Announce Type: new Abstract: Persistent spatial memory enables embodied agents to navigate familiar environments across repeated visits. However, targets may move while unobserved,
arXiv:2609.39037v1 Announce Type: cross Abstract: Before a validator can be promoted to a hard gate on a deployment pipeline, it has to be shown that its firing separates outputs that reach users in w
arXiv:2609.38866v1 Announce Type: new Abstract: As preferences, goals, and facts change, LLM agents must use the current state while earlier versions remain in context. Yet they can answer with an old
arXiv:2609.35922v1 Announce Type: cross Abstract: A voice agent can handle almost every call on the words alone and still fail the few its sector's rules were written for. Emergency-call standards, fr
Welcome to the second Cloud CISO Perspectives for September 2026. Today, Alicja Cade and Nick Godfrey, senior directors, Office of the CISO, share their guidance for cybersecurity startups on how to w
i kinda wish dots was a standalone app and not part of chatgpt. as it stands, it feels like a product feature (e.g. GPTs) and not a big, exciting new release. i might understand why they did it though
arXiv:2609.37849v1 Announce Type: cross Abstract: Scientific software is increasingly required to process larger datasets while maintaining acceptable execution times. Software optimization traditiona
arXiv:2609.36478v1 Announce Type: new Abstract: The tragedy of the commons poses a multi-agent safety problem: reward-seeking agents can deplete a shared resource, and cooperation among its users does
arXiv:2606.20333v2 Announce Type: replace Abstract: Natural-language skills let agents reuse task knowledge, yet deploying a long Markdown document makes the model interpret that knowledge anew on eve
arXiv:2609.37419v1 Announce Type: new Abstract: The autonomous extraction of deep mineral deposits in abandoned underground mines is fundamentally a multi-agent integration problem. No single platform
arXiv:2609.34749v1 Announce Type: new Abstract: Real-world driving is inherently multi-agent, yet most existing driving world models generate observations from a single ego vehicle. Independently exte
arXiv:2609.32805v1 Announce Type: cross Abstract: Long tasks produce more history than an LLM agent can hold in its context, and more than it uses reliably even when the history fits. A growing line o
arXiv:2609.31901v1 Announce Type: new Abstract: Constrained general-sum dynamic games are a popular formulation for highly interactive multi-agent planning problems. In recent years, Generalized Nash
arXiv:2609.31929v1 Announce Type: new Abstract: Newton methods efficiently find Generalized Nash Equilibria (GNE) in dynamic games by solving for the KKT necessary conditions. These methods are fast a
arXiv:2609.33288v1 Announce Type: new Abstract: Embodied Question Answering (EQA) requires agents to answer natural language questions about surrounding environments from visual observations. In this
Tech YouTuber Matt Robb says that Muse gave out his home address to a total stranger this weekend, after authorizing the bot to handle his Facebook Marketplace account. That's despite Meta placing gre
arXiv:2602.12029v2 Announce Type: replace Abstract: Multi-agent systems increasingly orchestrate multiple specialized language models to solve complex real-world problems, often invoking them over a s
arXiv:2601.22419v2 Announce Type: replace-cross Abstract: Pooled testing uses one test to certify several agents as healthy when the pooled result is negative. We study a budget-constrained welfare pr
AI Engineering from Scratch is an MIT-licensed curriculum: 523 lessons across 20 phases, from linear algebra and backprop to transformers, LLMs, agents, and production serving. The code is stdlib-firs
OpenAI’s so reckless, “It is like if in … Jurassic Park they would have let all the dinosaurs roam free not only on the island but on a populated continent” What is so bad here is that they should hav
arXiv:2609.31191v1 Announce Type: cross Abstract: Data quality research has usually treated data as an input that is stored, processed, and validated. In AI-driven software-intensive systems, data als
This is one of the strongest use cases I've seen for System One models like Jev. Pay close attention if you build custom harnesses. Jev is now available as a packaged router. What is it? You send the
arXiv:2609.29958v1 Announce Type: cross Abstract: We study a matching mechanism where agents and objects are described by features rather than complete rankings. A single spectral projection reduces t
arXiv:2603.11351v2 Announce Type: replace-cross Abstract: In dynamic open-world environments, autonomous agents often encounter novelties that hinder their ability to find plans to achieve their goals
In July, OpenAI revealed that its AI agents had attacked Hugging Face without permission, sparking widespread concerns about AI safety. Since then, a string of similar incidents involving agents from
arXiv:2609.29251v1 Announce Type: new Abstract: CAR-bench evaluates whether tool-using agents stay reliable under real-world uncertainty, executing every tool inside the evaluator so that each tool-re
We announced our RSI Lab earlier this year: https://sakana.ai/rsi-lab/ Over the last two years, we have systematically shipped the foundations for autonomous R&D: ▪ LLM²: AI automating research to inv
arXiv:2609.27720v1 Announce Type: new Abstract: Spatially constrained semantic navigation requires robots to identify targets specified not only by semantic categories but also by relations to surroun