Knowledge catalogue
One of the great parts of nous portal is stuff like this Trinity-Large-Thinking, @arcee_ai's latest model, is now free on Nous Portal for the next week Sign up for Nous Portal to use it in your Hermes
arXiv:2510.26020v2 Announce Type: replace Abstract: Multi-tool-integrated reasoning enables LLM-empowered tool-use agents to solve complex tasks by interleaving natural-language reasoning with calls t
This is probably better messaging than just “own your harness.” Yes, open models will need custom harnesses, but that is a means to an end. The end is utilizing models without being handcuffed to Anth
arXiv:2508.04086v2 Announce Type: replace Abstract: Prior work synthesizes tool-use LLM datasets by first generating a user query, followed by complex tool-use annotations like depth-first search (DFS
i actually don't want this 'but you don't review compiler output either' meme to die. it's the perfect signal for being immediately able to ignore someone in this space. Interesting article on treatin
Claude Opus 4.7 just implemented an AlphaZero-style self-play pipeline from scratch. It did this on consumer hardware in three hours, then beat the Pascal Pons solver 7 of 8 as first-mover on Connect
The year of the harness 🤝 Harnesses are our most direct layer to turn a model into a great product experience for users by shaping model behavior towards a goal This matters today because models have
arXiv:2604.27942v1 Announce Type: new Abstract: Collective intelligence emerges across biological, physical, and artificial systems without central coordination, yet a unifying principle governing suc
arXiv:2604.27924v1 Announce Type: cross Abstract: Peer review is a multi-stage process involving reviews, rebuttals, meta-reviews, final decisions, and subsequent manuscript revisions. Recent advances
arXiv:2604.26956v1 Announce Type: cross Abstract: The growing use of generative AI raises ethical concerns about authorship and plagiarism. This study examines how people judge the reuse of AI-generat
arXiv:2604.27994v1 Announce Type: new Abstract: Learned driving agents often degrade when deployed in unseen environments. This paper studies a deliberately bounded instance of that problem in the CAR
I have to go out of town for a funeral thru the weekend but I am leaving everyone with one new cool feature inspired by ralph loops and Codex's upcoming /goal feature. If you use /goal <prompt>, it wi
arXiv:2604.27156v1 Announce Type: new Abstract: Rational belief revision is commonly viewed as being based on a preference order between possible worlds, with the resulting new belief set being those
arXiv:2508.05469v3 Announce Type: replace Abstract: We evaluate artificial intelligence (AI) systems without ground truth by exploiting a link between strategic gaming and information loss. Building o
arXiv:2604.27269v1 Announce Type: new Abstract: Biomedical knowledge graphs (KGs) are widely used in the life sciences, yet many are derived from unstructured documents and therefore lack schema-level
Randomized trial of an AI therapy chatbot on Mexican women found “improved mental health by 0.3 SD over 6 months with no evidence of an increase of severe cases; improved sleep, healthful behaviors, d
Receptionist robotics app built under 2 hours thanks to ml intern and reachy mini. Was fun again! Media I'm trying to build an office receptionist app for my reachy mini today with ml intern + @OpenAI
arXiv:2604.27132v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) and Multi-Agent Systems (MAS) in high-stakes domains demand reliable verification, yet centralized approaches suffer four
arXiv:2604.26509v1 Announce Type: cross Abstract: Embodied AI and robotic systems increasingly depend on scalable, diverse, and physically grounded 3D content for simulation-based training and real-wo
arXiv:2601.13969v2 Announce Type: replace Abstract: Retrieving evidence for language model queries from knowledge graphs requires balancing broad search across the graph with multi-hop traversal to fo
arXiv:2604.14858v2 Announce Type: replace Abstract: As agent systems move into increasingly diverse execution settings, trajectory-level safety evaluation and diagnosis require benchmarks that evolve
arXiv:2604.26516v1 Announce Type: cross Abstract: Offline reinforcement learning (RL) agents often fail when deployed, as the gap between training datasets and real environments leads to unsafe behavi
arXiv:2604.26591v1 Announce Type: cross Abstract: Technology mapping is a critical yet challenging stage in logic synthesis. While Large Language Models (LLMs) have been applied to generate optimizati
It's a common misconception that we can't tell who is using LLM and who is not. I'm sure we didn't catch 100% of LLM-assisted PRs over the past few months, but the kind of mistakes humans make are fun
Open Models are really smart Open Models are often way cheaper Open Models are fast for the CTOs & CFOs in the back, no need to fight, Open Models mean you can both be happy :) - potentially cutting c
amazing! it’s like talking to an ai from the past Announcing Talkie: a new, open-weight historical LLM! We trained and finetuned a 13B model on a newly-curated dataset of only pre-1930 data. Try it be
And if you have your own VT-100, check out Devin for Terminal to get started: https://x.com/cognition/status/2048821234281181302 The terminal hasn’t changed much since the 1970s. What you do with it h
arXiv:2604.24273v1 Announce Type: new Abstract: The deployment of intelligent reinforcement learning (RL) agents on resource-constrained edge devices remains a fundamental challenge due to the substan
arXiv:2604.23057v1 Announce Type: new Abstract: We investigate whether explicit belief graphs improve LLM performance in cooperative multi-agent reasoning. Through 3,000+ controlled trials across four
arXiv:2604.23728v1 Announce Type: cross Abstract: Recent advances in autonomous driving have motivated research on pedestrian intention prediction, which aims to infer future crossing decisions and ac
// From Skill Text to Skill Structure // One of the more practical skill papers I've seen this month. SKILL.md files entangle invocation interface, execution flow, and tool/resource side effects in on
* 본 아티클의 원문은 2026년 4월 23일 Google Cloud 블로그(영문)에 게재되었습니다. AI는 질문에 답하는 수준을 넘어 추론하고 행동하는 단계로 진화하고 있습니다. 오늘날의 에이전틱 시대(agentic era)를 선도하고자 하는 기업에는 이러한 새로운 요구사항에 맞춰 설계되고 최적화된 컴퓨팅 인프라가 필요합니다. 오늘 Google Cloud
arXiv:2604.23355v1 Announce Type: new Abstract: Existing LLM-based EDA agents are often isolated task-specific systems. This leads to repeated engineering effort and limited reuse of successful design
arXiv:2604.24127v1 Announce Type: cross Abstract: Unsupervised skill discovery in reinforcement learning aims to intrinsically motivate agents to discover diverse and useful behaviours. However, uncon
arXiv:2604.24696v1 Announce Type: new Abstract: Agentic artificial intelligence systems promise to accelerate scientific workflows, but neuroimaging poses unique challenges: heterogeneous modalities (
new in ml-intern: you can now actually see what's going on inside added native metric logging + trackio integration. every training run the agent kicks off now has live curves you can watch in real ti
arXiv:2604.23106v1 Announce Type: cross Abstract: Existing multi-agent Large Language Model (LLM) frameworks for code generation typically use execution feedback and improve iteratively using Input/Ou
arXiv:2602.00921v2 Announce Type: replace-cross Abstract: Optimal feedback control with implicit Hamiltonians poses a fundamental challenge for learning-based value function methods due to the absence
arXiv:2510.12826v2 Announce Type: replace-cross Abstract: As large language model (LLM) agents are deployed autonomously in diverse contexts, evaluating their capacity for strategic deception becomes
arXiv:2604.22560v1 Announce Type: cross Abstract: Graph Visual Question Answering (GVQA) for autonomous driving organizes reasoning into ordered stages, namely Perception, Prediction, and Planning, wh
arXiv:2604.22026v1 Announce Type: new Abstract: AI research pipelines now produce a growing share of publishable academic output, including work that meets existing peer-review standards for quality a
I actually switched my personal Claude subscription to this (currently using Mimo v2) Nous Portal offers everything you need to build with Hermes Agent in one easy subscription: → 300+ models from eve
NEW paper from Alibaba. A 30B MoE with only 3B active params matches Qwen3-235B on real tool-use workloads. AgenticQwen-30B-A3B: 50.2 average on TAU-2 + BFCL-V4 Multi-Turn. AgenticQwen-8B: 47.4. Both
Harrison Chase, co-founder of LangChain, expressed enthusiasm about an upcoming LangChain Interrupt conference event scheduled for two weeks from his post date. He characterized it as the best AI deve
wow another engineer on the “code is not cheap” train https://x.com/mattzcarey/status/2048102657512935626?s=46 My talk at AI Engineer “Every API is a Tool for Agents” is out on YouTube https://youtu.b
arXiv:2510.01857v3 Announce Type: replace Abstract: Current approaches to improving reasoning in large language models (LLMs) primarily rely on either supervised fine-tuning (SFT) over expert traces o
Probably the most useful advice I can give you if you run an ad agency, a marketing company, a production studio, or anything in that space. Hear me out. I’ve spent a decade talking to teams about thi
arXiv:2604.21640v1 Announce Type: cross Abstract: Autonomous underwater vehicles are required to perform multiple tasks adaptively and in an explainable manner under dynamic, uncertain conditions and
Claude Code spend had gotten to $10.95M runrate peak at SemiAnalysis But then Opus 4.7 saved me. More token effecient for tasks, smarter, and no fast mode. Thank you @AnthropicAI You saved me from ban
New Max Agency! 🎙️ @hwchase17 🎙️ @ListenLabs Co-Founder/CTO @florian_jue 🎙️ Talked to @ListenLabs co-founder + CTO @florian_jue in the latest Max Agency. Really enjoyed hearing about the architectural
arXiv:2505.07849v2 Announce Type: replace-cross Abstract: Software issue localization, the task of identifying the precise code locations (files, classes, or functions) relevant to a natural language
Three shifts in the AI stack today: - OpenAI ships GPT-5.5 as a mid-cycle drop before its IPO - Hugging Face's ML Intern beats Claude Code and Codex on research - Pliny used Claude Opus 4.7 to jailbre
arXiv:2510.08145v2 Announce Type: replace Abstract: Large Language Models (LLMs) as automatic evaluators, commonly referred to as LLM-as-a-Judge, have also attracted growing attention. This approach p
Small businesses are the backbone of the global economy. With 400 million SMBs worldwide and 36 million in the U.S. alone, they provide 50% of global employment. Now, with Google Cloud AI, they’re sca
arXiv:2604.16366v1 Announce Type: cross Abstract: Artificial intelligence (AI) tutors have become increasingly popular in learning environments. In this study, we propose an AI agent prototype framewo
arXiv:2604.16406v1 Announce Type: cross Abstract: Realistic highway simulation is critical for scalable safety evaluation of autonomous vehicles, particularly for interactions that are too rare to stu
I’ve been using ml-intern for a while, and it genuinely changed my workflow. It's super good at: - Model/Dataset discovery. - Post-Training setup iteration. - Data processing workflows. Huge shoutout
arXiv:2604.17190v1 Announce Type: new Abstract: Aerial Vision-and-Language Navigation (Aerial VLN) enables unmanned aerial vehicles (UAVs) to follow natural language instructions and navigate complex
arXiv:2601.21257v2 Announce Type: replace Abstract: Advancing beyond single monolithic language models (LMs), recent research increasingly recognizes the importance of model collaboration, where multi
As AI assistants and privacy proxies challenge the capabilities of traditional bot detection, the Web needs new models for accountability. We believe that control should remain with the client, and th