Knowledge catalogue
arXiv:2608.12104v1 Announce Type: cross Abstract: The increasing deployment of autonomous, agentic AI systems challenges traditional accountability mechanisms. Existing research predominantly frames A
arXiv:2608.11407v1 Announce Type: new Abstract: Robust traffic simulators are crucial for developing and testing autonomous vehicles to reduce the costly, labor-intensive real-world data collection pr
Very interesting new paper from Microsoft and colleagues. (bookmark it) Skill libraries are used in every major harness on the assumption that more guidance is free. This work measures what a bad skil
arXiv:2608.10526v1 Announce Type: cross Abstract: Motivated by decentralized applications, we study cooperative multi-agent bandits in continuous (Lipschitz) action spaces when the Lipschitz constant
Four small architecture decisions can cost up to 47% of a model's long-context performance. New research from Ai2, Carnegie Mellon, and the University of Washington isolates them. Normalization, GQA,
arXiv:2608.09248v1 Announce Type: new Abstract: Skill-based LLM agents select reusable procedures from an external library to solve complex tasks, yet their routing decisions rely entirely on text-lev
Nemotron 3.5 Lightning is available in LM Studio! The model is 30B MoE (3B active), can run very fast, and is trained for high volume agentic use cases. Model page: https://lmstudio.ai/models/nvidia/n
arXiv:2608.08795v1 Announce Type: cross Abstract: Tool-using large language model (LLM) agents are vulnerable to indirect prompt injection (IPI), in which malicious instructions embedded in external o
arXiv:2608.06706v1 Announce Type: cross Abstract: Latent world models plan by predicting future states from an action, but when a scene contains motion the agent does not control, they quietly go acti
Every crawl, retried job, and embedding pipeline change writes points into a vector collection. The stored data keeps moving even when the query code never changes, and the top results move with it. A
The successor to Llama is here, and Meta is revitalizing focus on open weights with their new Muse Glimmer - a leading 30B param model designed for always-on local agent use, small enough to run on a
the term “RLM” (recursive language model) got a lot of buzz this week, but this idea is not new! @a1zhang wrote the og RLM paper 10 months ago! thats like 5 agent-years! would highly recommend followi
HUD mode Hermes stops being a window you switch to and becomes a layer over the app you're both working in. Or keep it around as a little buddy agent. Ask it random things, drag it anywhere, it's your
arXiv:2608.05797v1 Announce Type: cross Abstract: Task difficulty dictates an agent's likelihood of success, and estimating it without rollouts means forecasting this directly from a task description
arXiv:2608.05245v1 Announce Type: new Abstract: Reusable skills, which encapsulate the procedural knowledge required to solve real-world professional tasks, offer LLM-based agents a path toward self-e
The backgrounds were generated with MiniMax M3. Everything else, including the full game design, was done with DeepSeek Flash. Most importantly, all of this was done inside Hermes Agent. You won't bel
this talk by openai researchers going through hugging face incident is totally insane, so much to unpack openai only realized it was their agent who hacked hugging face infra while asking hf to revoke
arXiv:2608.04942v1 Announce Type: cross Abstract: CheMLFlow is an open-source platform for building and executing end-to-end, high-throughput, and agentic workflows for scientific and technological ap
Some of you may be aware that a few weeks ago, LM Studio announced a new agent, Bionic. This is pretty much an agentic harness for both local models and paid cloud models. But most aren't aware that L
I released LLM 0.32 this morning, the most significant new version of LLM since the initial launch of the project. The new version includes support for visible reasoning traces, server-side provider t
Wired: OpenAI says one of its models exploited a website after third-party AI security lab Irregular mistakenly gave it access to the internet during evaluations — Rogue AI agents from OpenAI and Anth
Grok Build can do almost anything you can think of http://X.ai/cli Most people seriously underestimate what Grok Build can do They assume an AI coding agent is only useful for building apps or writing
arXiv:2607.26512v1 Announce Type: new Abstract: AI agents can draft claims faster than authors can check whether the cited or retrieved evidence supports them. We study evidence-ledger adjudication: a
arXiv:2607.28073v1 Announce Type: cross Abstract: In demanding professional environments and meeting review scenarios, lengthy text often imposes a high cognitive load. To facilitate efficient informa
arXiv:2607.27231v1 Announce Type: cross Abstract: Large language models (LLMs) have significantly increased the demand for efficient accelerator kernels, but kernel development remains a highly specia
arXiv:2607.26464v1 Announce Type: cross Abstract: Physical Unified Device Architecture (PUDA) is an AI-native hardware harness for self-driving laboratories (SDLs). Rather than building a human-center
arXiv:2112.07752v4 Announce Type: replace-cross Abstract: Researchers have formalized reinforcement learning (RL) in different ways. If an agent in one RL framework is to run within another RL framewo
arXiv:2607.27557v1 Announce Type: new Abstract: While Large Language Models (LLMs) demonstrate remarkable general instruction-following capabilities, they often fall short of human experts in highly s
Introducing the Parse Gateway There's been an explosion of interest in model routing - you don't always need the best model for every task. That is especially true for document parsing 📄🔀: - Some page
arXiv:2607.27201v1 Announce Type: new Abstract: World models enable a predictive substrate for planning and action, yet existing formulations merely answer a physical question: what/where it is, and h
arXiv:2607.19321v2 Announce Type: replace-cross Abstract: As AI agents begin to automate AI R&D, we need ways to assess whether their outputs are safe to deploy, even when the agents themselves may be
arXiv:2607.25042v1 Announce Type: new Abstract: The evolution of customer support systems is rapidly advancing with agentic chatbots, yet these systems face significant limitations when accessing ente
arXiv:2607.25333v1 Announce Type: cross Abstract: Specula is a push-button agentic system that generates high-quality formal specifications for large, complex system code and uses the specifications f
arXiv:2607.22642v1 Announce Type: new Abstract: Enterprise coding agents translate natural-language analytical requests into executable code over proprietary APIs, schemas, and metric definitions. Yet
arXiv:2603.14807v3 Announce Type: replace Abstract: LLM-based agents have demonstrated impressive zero-shot performance in vision-language navigation (VLN) tasks. However, most zero-shot methods prima
arXiv:2607.22652v1 Announce Type: new Abstract: Recent research has explored the integration of knowledge graphs (KGs) with large language models (LLMs) to enhance their performance on downstream know
Reuters confirms my hypothesized time line. OpenAI did not realize its AI has breached the sandbox for a week. Astounding. https://www.reuters.com/business/its-ai-agent-spent-days-hacking-company-sour
Dynamic workflows are a generalization of harnesses, automations, loops, routing, and graphs. It's the most powerful feature I have built into my agent orchestrator. Supports all kinds of patterns tha
LLaDA2.2-flash is an agent-oriented diffusion language model in the LLaDA2 series. By introducing Levenshtein Editing (with DELETE and INSERT control tokens) to diffusion language modeling, it represe
arXiv:2607.20268v1 Announce Type: new Abstract: While Large Language Models (LLMs) excel at many tasks, they frequently struggle with complex reasoning that requires long-horizon planning and iterativ
arXiv:2607.13621v1 Announce Type: new Abstract: Language-guided human following is an important capability for embodied agents, but existing benchmarks typically assume that the target person is visib
arXiv:2607.12382v1 Announce Type: new Abstract: How can an agent build a structured map of its world from nothing but an ongoing sequence of raw sensory input and its own movements, especially when na
arXiv:2607.11906v1 Announce Type: new Abstract: The development of decision-pretrained transformers, algorithm distillation, long-context meta-RL, and retrieval-augmented agents has renewed interest i
arXiv:2607.12625v1 Announce Type: new Abstract: OpenClaw has emerged as a leading agent framework for complex task automation, yet it faces insufficient cross-platform GUI interaction support and a we
arXiv:2607.12161v1 Announce Type: new Abstract: Context-reduction layers for API-based coding agents, including command-output compressors, retrieval rankers, and payload-optimizing proxies, are usual
In this post, you will learn how ScienceSoft, an Amazon Web Services (AWS) Services Partner, integrated Amazon Nova 2 Sonic with Amazon Bedrock Guardrails to build a Health Insurance Portability and A
arXiv:2607.07980v1 Announce Type: cross Abstract: Coding agents now author entire pull requests, and practitioners sharply disagree about what this does to code review: whether it becomes the bottlene
arXiv:2303.04203v4 Announce Type: replace-cross Abstract: The theory of computation was built to answer Turing's question: what is effectively calculable by an unbounded, immortal, disembodied agent f
arXiv:2511.23347v2 Announce Type: replace Abstract: An associative memory (AM) enables cue-response recall, and it has recently been recognized as a key mechanism underlying modern neural architecture
Here’s a question we hear often at Google Cloud: How do you safely run AI-generated code or untrusted binaries without putting your host application, data, and cloud credentials at risk? In other word
arXiv:2607.02329v1 Announce Type: new Abstract: Autonomous-research agents have demonstrated end-to-end LLM automation in machine-learning sandboxes where execution provides calibration. Frontier phys
arXiv:2606.30775v1 Announce Type: cross Abstract: Enterprise AI agents route user queries to specialized skills by matching queries against natural language skill descriptions. When two skills share o
arXiv:2606.31892v1 Announce Type: cross Abstract: 'Any fool can know; the point is to understand.' A well-known remark often attributed to Einstein captures a widely shared intuition: understanding is
arXiv:2606.30668v1 Announce Type: cross Abstract: What happens when LLM agents operate with no context outside a turn, minimal prompting, and simple tools? Inspired by swarm engineering, we give colle
Imagine if, as an engineer, your working memory of a codebase was wiped every time you started a new ticket Sounds ridiculous, but this is functionally what happens to agents whenever we start a new t
arXiv:2602.18767v3 Announce Type: replace-cross Abstract: In Machine-Assisted Theorem Proving, a theorem proving agent searches for a sequence of expressions and tactics that can prove a statement in
a very cool Harbor x LangSmith flow I love to help you “look at the data”: 1. you do evals or rollouts for RL 2. all reward metrics and traces and rollouts get automatically propulates into Experiment
arXiv:2606.28524v1 Announce Type: new Abstract: Recent work suggests that Large Language Models (LLMs) are sensitive to the belief states of agents described by text, as measured by the false belief t
arXiv:2606.30608v1 Announce Type: new Abstract: Articulated 3D objects are essential for interactive environments in embodied AI, robotics, and virtual reality, but reconstructing their structure and
We're all over AI Engineer World's Fair on June 29 to July 2. 🦙 📍Visit us at booth L-G47. LlamaParse demos + Fear of Docs swag 🎤 @jerryjliu0, our Founder & CEO, on agentic document parsing and shippin