this & a hermes agent
Nous Research's Hermes agent framework combines a language model's contextual reasoning capabilities ('this') with an autonomous agent built on their Hermes model series, enabling tool use, multi-step
Knowledge catalogue
Nous Research's Hermes agent framework combines a language model's contextual reasoning capabilities ('this') with an autonomous agent built on their Hermes model series, enabling tool use, multi-step
arXiv:2604.09036v1 Announce Type: new Abstract: Scaling Vision-Language-Action (VLA) models requires massive datasets that are both semantically coherent and physically feasible. However, existing sce
arXiv:2604.09531v1 Announce Type: cross Abstract: Vision-language models (VLMs) still struggle with visual perception tasks such as spatial understanding and viewpoint recognition. One plausible contr
Google's Gemini Live has been integrated into the Reachy Mini robot's conversation application through a partnership between Hugging Face, Pollen Robotics, and Google. This collaboration brings advanc
Deepagents is an open-source project by LangChain that implements deep research-style agentic workflows, enabling AI agents to perform iterative, multi-step research and reasoning tasks. The repositor
Have an idea for an experiment? Hermes can now write conference-grade research papers alongside you. Media introducing Autoreason, a reasoning method inspired by @karpathy's AutoResearch which extends
This one gives a lot of perspective over the fact that memory isn't just a plugin anymore. My take is, each approach has it's tradeoffs but for me the mental model is, if the memory is more than or 80
We’re thrilled to announce @MiniMax_AI M2.7 is now available Day-0 on Fireworks for commercial use. This self-evolving agentic model delivers frontier-level performance across: → Software engineering
A report called 'KellyBench,' released by AI start-up General Reasoning, tested eight leading AI models in a virtual re-creation of the 2023–24 Premier League season, providing them with detailed hist
arXiv:2604.08260v1 Announce Type: new Abstract: Knowledge Tracing (KT) aims to predict learners' future performance from past interactions. While recent KT approaches have improved via learning item r
arXiv:2604.06173v1 Announce Type: cross Abstract: Legal QA benchmarks have predominantly focused on case law, overlooking the unique challenges of statute-centric regulatory reasoning. In statutory do
arXiv:2604.08038v1 Announce Type: new Abstract: In a real-world traffic scenario, varying-scale objects are usually distributed in a cluttered background, which poses great challenges to accurate dete
arXiv:2604.06336v1 Announce Type: cross Abstract: Graph Transformers have recently attracted attention for molecular property prediction by combining the inductive biases of graph neural networks (GNN
arXiv:2604.06284v1 Announce Type: cross Abstract: Autonomous AI agents powered by Large Language Models can reason, plan, and execute complex tasks, but their ability to autonomously retrieve informat
arXiv:2603.20698v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable potential in medical image analysis. However, their application in gastr
arXiv:2604.08369v1 Announce Type: cross Abstract: Inference-time compute scaling has emerged as a powerful technique for improving the reliability of large language model (LLM) agents, but existing me
arXiv:2604.05350v2 Announce Type: replace Abstract: Enterprise IT support interactions are fundamentally diagnostic: effective resolution requires iterative evidence gathering from ambiguous user repo
arXiv:2509.01986v4 Announce Type: replace-cross Abstract: In recent years, integrating multimodal understanding and generation into a single unified model has emerged as a promising paradigm. While th
arXiv:2412.19685v2 Announce Type: replace-cross Abstract: Existing facial forgery detection methods typically focus on binary classification or pixel-level localization, providing little semantic insi
arXiv:2604.06195v1 Announce Type: cross Abstract: Large language models often produce unsupported claims. We frame this as a misclassification error at the output boundary, where internally generated
arXiv:2604.07833v1 Announce Type: new Abstract: Embodied agents are evolving from passive reasoning systems into active executors that interact with tools, robots, and physical environments. Once gran
arXiv:2512.09928v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models have recently enabled robotic manipulation by grounding visual and linguistic cues into actions. However, most V
arXiv:2601.10198v3 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning and generation, serving as the foundation for advanced persona s
Inception has launched Mercury 2, a model providing reasoning-grade quality with low, real-time latency, making it suitable for complex applications like agentic loops, coding assistants, and RAG p...
arXiv:2604.08337v1 Announce Type: new Abstract: Current vision-language pre-training (VLP) paradigms excel at global scene understanding but struggle with instance-level reasoning due to global-only s
arXiv:2505.17209v2 Announce Type: replace Abstract: Recent advances in autonomous driving research towards motion planners that are robust, safe, and adaptive. However, existing rule-based and data-dr
arXiv:2510.13907v3 Announce Type: replace Abstract: Large language models (LLMs) are highly sensitive to prompts, but most automatic prompt optimization (APO) methods assume access to ground-truth ref
arXiv:2603.09677v3 Announce Type: replace Abstract: Addressing the challenges of fragmented task definitions and the heterogeneity of unstructured data in multimodal parsing, this paper proposes the O
arXiv:2604.08333v1 Announce Type: new Abstract: The rise of multimodal large language models (MLLMs) has sparked an unprecedented wave of applications in the field of medical imaging analysis. However
arXiv:2604.07944v1 Announce Type: new Abstract: Large language models (LLMs) have recently demonstrated strong potential for autonomous vehicle motion planning by reformulating trajectory prediction a
arXiv:2604.08031v1 Announce Type: cross Abstract: Most Human-Machine Interaction (HMI) research overlooks the maneuvering needs of passengers in autonomous driving (AD). Natural language offers an int
People in Washington get played, yet again We really should worry about cybersecurity - a lot – but Mythos is not the model these guys think it is. (See my newsletter today for three reasons why it is
arXiv:2603.10512v2 Announce Type: replace Abstract: Artificial intelligence has advanced significantly through the development of intelligent game-playing systems, providing rigorous testbeds for deci
arXiv:2510.19225v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become essential for unlocking advanced reasoning capabilities in large language models (LLMs). RL workflows i
arXiv:2604.06603v1 Announce Type: cross Abstract: Large language models (LLMs) have shown strong knowledge reserves and task-solving capabilities, but still face the challenge of severe hallucination,
arXiv:2604.08008v1 Announce Type: new Abstract: Retrieving rare and safety-critical driving scenarios from large-scale datasets is essential for building robust autonomous driving (AD) systems. As dat
In an April 9, 2026 Substack post, AI skeptic Gary Marcus argues that Anthropic's announcement of its Claude 'Mythos' model was significantly overhyped, offering three key reasons for skepticism: t...
Google released Gemma 4 in April 2025 as its most capable open-weight model family to date, built on the same research as Gemini 3 and licensed under Apache 2.0 for unrestricted commercial use, fin...
arXiv:2604.07916v1 Announce Type: new Abstract: Referring Expression Segmentation (RES) aims to segment image regions described by natural-language expressions, serving as a bridge between vision and
arXiv:2507.22025v4 Announce Type: replace Abstract: The emergence of Multimodal Large Language Models (MLLMs) has driven significant advances in Graphical User Interface (GUI) agent capabilities. Neve
arXiv:2601.21463v2 Announce Type: replace-cross Abstract: Existing speech editing detection (SED) datasets are predominantly constructed using manual splicing or limited editing operations, resulting
arXiv:2604.06728v1 Announce Type: cross Abstract: Multimodal sarcasm detection (MSD) aims to identify sarcastic intent from semantic incongruity between text and image. Although recent methods have im
Google AI's Gemma 4, released on April 2, 2026, is Google DeepMind's most capable open model family to date, purpose-built for advanced reasoning and agentic workflows . The models are available ...
arXiv:2604.06177v1 Announce Type: cross Abstract: Specialized web tasks in finance, biomedicine, and pharmaceuticals remain challenging due to missing domain priors: queries drift, evidence is noisy,
March ships Foundry Agent Service GA with private networking, GPT-5.4 and GPT-5.4 Mini, Priority Processing, Phi-4 Reasoning Vision, SDK 2.0 GA across Python, JS/TS, Java, and .NET, Fireworks AI and
Yep! @Teslaconomics @boringcompany The real reason for the “high speed rail” is money-laundering to bureaucrats, consultants & unions, not actually transport. That is where the billions spent so far h
Google's Gemma 4, launched on April 2, 2026, surpassed 10 million downloads within its first week, according to Google CEO Sundar Pichai, pushing the cumulative total for all Gemma models past 500 ...
Meta announced Muse Spark today, their first model release since Llama 4 almost exactly a year ago. It's hosted, not open weights, and the API is currently 'a private API preview to select users', but
In this post, we explore where RFT is most effective, using the GSM8K mathematical reasoning dataset as a concrete example. We then walk through best practices for dataset preparation and reward funct
Seems like a good model from Meta that is still trailing the current series of releases. The most important thing to note is that it is not open weights. That was the main reason that Meta's models we
🇮🇹🇪🇺 This is utterly unacceptable. Reports indicate that Giorgia Meloni is preparing to sideline Roberto Cingolani, CEO of Leonardo, Italy’s largest defence group. The reason? Multiple sources suggest
Writing fiction seems to be a genuine weak spot for LLMs that is not improving as rapidly as almost every other area. There may be a lot of reasons why this is happening. It would be a really interest
Hi r/LocalLLaMA. I'm on the team at Blockway (disclosure: this is our model). Two weeks ago we posted the Volundr 32B Preview here, and you were blunt about what was wrong with it. This is v1, and mos
Drama 3 officially needs an NVIDIA GPU with 48 GB. I wanted it on my RX 9070, so I built Red Curtain together with Claude. How it works: it's a 35B MoE with ~3B active per token. The FP8 experts (~32
Great paper from NVIDIA sharing an open midtraining recipe for agentic coding. NVIDIA kept SFT identical and added one midtraining stage. SWE-bench Multilingual went from 55.8 to 62.8 on Nemotron 3.5
arXiv:2610.22319v1 Announce Type: new Abstract: We placed four Gemini 4 Argon agents in a sandboxed Minecraft survival world and gave them one goal: defeat the Ender Dragon. Each agent controlled a pl
arXiv:2602.05273v2 Announce Type: replace Abstract: Enabling robots to explore and act in unfamiliar environments under ambiguous human instructions by interactively identifying task-relevant objects
arXiv:2610.22298v1 Announce Type: cross Abstract: Large language models (LLMs) can generate differential diagnoses for complex cases, but a useful second opinion must also be factually grounded, clini
arXiv:2508.02276v3 Announce Type: replace-cross Abstract: Autonomous agents, from virtual laboratories to biological data-analysis agents and co-scientists, have begun to turn scientific goals into hy
arXiv:2512.02004v4 Announce Type: replace-cross Abstract: Large Language Models (LLMs) encode factual knowledge within hidden parametric spaces that are difficult to inspect or control. While Sparse A