Actualités
Nous Research Team Releases Hermes 4: A Family of Open-Weight AI Models with Hybrid Reasoning
Nous Research has released Hermes 4, a family of open-weight models (14B, 70B, and 405B...
Nous Research Releases Hermes Desktop: A Native Cross-Platform Front End for Hermes Agent v0.15.2 with Streaming Tool Output
Nous Research has released Hermes Desktop in public preview. It is a native application for...
Nous Research Releases Contrastive Neuron Attribution (CNA): Sparse MLP Circuit Steering Without SAE Training or Weight Modification
Instruction-tuned language models refuse harmful requests. But which part of the model is actually responsible...
Nous Research Releases ‘Hermes Agent’ to Fix AI Forgetfulness with Multi-Level Memory and Dedicated Remote Terminal Access Support
In the current AI landscape, we’ve become accustomed to the ‘ephemeral agent’—a brilliant but forgetful...
Nous Research Proposes Lighthouse Attention: A Training-Only Selection-Based Hierarchical Attention That Delivers 1.4–1.7× Pretraining Speedup at Long Context
Training large language models on long sequences has a well-known problem: attention is expensive. The...
Not Just Understanding, But Evolving: The All-New Self-Evolving JiuwenClaw Makes Its Debut
Over the past year, AI agents have evolved from merely answering questions to attempting to...
Not everything needs an LLM: A framework for evaluating when AI makes sense
The answer to ‘What customer needs requires an AI solution?’ isn’t always ‘Yes.’ LLMs are...
Not All Options Are Created Equal: Textual Option Weighting for Token-Efficient LLM-Based Knowledge Tracing
arXiv:2410.12872v2 Announce Type: replace Abstract: Large Language Models (LLMs) have recently emerged as promising tools...
Not All Needles Are Found: How Fact Distribution and Don’t Make It Up Prompts Shape Literal Extraction, Logical Inference, and Hallucination Risks in Long-Context LLMs
arXiv:2601.02023v1 Announce Type: new Abstract: Large language models (LLMs) increasingly support very long input contexts...
Non-Collaborative User Simulators for Tool Agents
arXiv:2509.23124v3 Announce Type: replace Abstract: Tool agents interact with users through multi-turn dialogues to accomplish...
NoHumansRequired: Autonomous High-Quality Image Editing Triplet Mining
arXiv:2507.14119v1 Announce Type: cross Abstract: Recent advances in generative modeling enable image editing assistants that...
NOBLE: Accelerating Transformers with Nonlinear Low-Rank Branches
arXiv:2603.06492v1 Announce Type: cross Abstract: We introduce NOBLE (Nonlinear lOw-rank Branch for Linear Enhancement), an...
