Towards a Unified Misuse Monitoring Benchmark
arXiv:2610.07089v1 Announce Type: cross Abstract: LLM agents increasingly act in multi-actor environments, exposing them to misuse from multiple sources: decomposition attacks, where a harmful request
Knowledge catalogue
arXiv:2610.07089v1 Announce Type: cross Abstract: LLM agents increasingly act in multi-actor environments, exposing them to misuse from multiple sources: decomposition attacks, where a harmful request
arXiv:2610.07570v1 Announce Type: new Abstract: In clinical practice, agreement among independent experts is treated as evidence of reliability, and multi-round consensus has become a core mechanism o
arXiv:2610.04687v2 Announce Type: replace Abstract: Answering questions over imperfect tables requires handling errors that can affect the answer. We investigate two challenges for large language mode
arXiv:2610.04878v1 Announce Type: cross Abstract: Human-agent evaluations often compress interaction into a single performance score, even when human and automated policies adapt differently over time
arXiv:2610.04929v1 Announce Type: new Abstract: Robot agents must connect their intended actions to observed outcomes while retaining the context needed to revise their choices over repeated attempts.
arXiv:2610.05270v1 Announce Type: cross Abstract: This paper investigates the real-time dispatch of a shared drone fleet for on-demand food delivery and urban road network monitoring. We consider a co
Octop is an open-source, self-hosted AI assistant. Through its multi-agent architecture, it builds an intelligent environment that is both independent and collaborative for teams, families, and indivi
arXiv:2610.06487v1 Announce Type: new Abstract: Heterogeneous multi-robot path planning is a well-studied problem in which agents with disparate kinematic and dynamic models must coordinate to achieve
arXiv:2610.02274v1 Announce Type: new Abstract: Generating useful robot-training data requires more than visually plausiblescenes: objects must support interaction, placements must remain physicallyva
arXiv:2610.01769v1 Announce Type: cross Abstract: Coding agents can generate code that appears correct but implements behavior the user never intended. This mismatch can arise when an agent silently r
Promoting Amazon Quick resources (agents, action connectors, knowledge bases, flows, and spaces) from a development to a production AWS account has been a manual, error-prone chore. This post shows ho
arXiv:2610.02788v1 Announce Type: new Abstract: Transferring robotic skills from simulation to reality requires task knowledge that remains usable across differences in perception, dynamics, and embod
Very good to see more competent labs training open-weight models. This Reflection's new Beam model seems to have strong reasoning efficiency, which I think is a big deal for long-running agents. 3-4x
arXiv:2610.00239v1 Announce Type: new Abstract: Model failover restores availability, but changes which financial institutions share decision errors. We formulate outage-contingent routing through a l
arXiv:2610.00902v1 Announce Type: cross Abstract: One way to make AI systems safe is to shape what the system is: its objective and dispositions. We take a complementary route: treat the agents' chara
Today we're unveiling Trillium Labs @trillium_labs, a new non-profit to foster the open science of frontier AI. We're building open post-training recipes and will expand into open infra to study RSI,
arXiv:2508.06980v2 Announce Type: replace Abstract: Recent and rapid advances in artificial intelligence (AI) make it increasingly important to understand the foundations of adaptive behaviour in auto
arXiv:2609.39342v1 Announce Type: cross Abstract: Intrinsic motivation plays a central role in adaptive and goal-directed behavior by conferring agents reward-independent objectives and biases useful
arXiv:2609.39148v1 Announce Type: new Abstract: AI agents can externalize what they learn from past tasks into reusable skills, such as procedures, checklists, code, or other executable artifacts, tha
arXiv:2609.39068v1 Announce Type: new Abstract: Long-context LLM agents accumulate interaction histories that strain KV-cache memory and attention computation. Although sparse attention reduces these
arXiv:2603.14733v2 Announce Type: replace Abstract: Multimodal Large Language Models have achieved strong performance in single-video understanding, yet their ability to reason across multiple videos
arXiv:2609.36392v1 Announce Type: new Abstract: In diseases where clinical guidelines are incomplete, contested, or mutually contradictory, knowledge completeness and dynamic conflict-aware synthesis
arXiv:2609.36406v1 Announce Type: new Abstract: Cell Painting is a high-content morphological profiling assay widely used for phenotype-based biological inference, with mechanism of action (MOA) predi
arXiv:2609.36675v1 Announce Type: new Abstract: Recursive self-improvement (RSI) aims to achieve compounding gains by having models improve themselves. While most existing RSI systems optimize externa
arXiv:2508.14925v2 Announce Type: replace-cross Abstract: By providing a standardized interface for LLM agents to interact with external tools, the Model Context Protocol (MCP) is quickly becoming a c
arXiv:2609.36595v1 Announce Type: cross Abstract: Visual-memory systems commonly retain or compress past observations. Robot control additionally requires interaction-derived state that no individual
Two months after the bombshell news that a swarm of its agents had broken their containment and hacked into the computers of the AI company Hugging Face, OpenAI is still putting out fires. A steady dr
arXiv:2609.35318v1 Announce Type: new Abstract: Human videos offer a scalable source of demonstrations for dexterous robot manipulation. However, existing human-to-simulation-to-robot (Human2Sim2Robot
arXiv:2609.34325v1 Announce Type: new Abstract: Vision Transformers (ViTs) incur quadratic self-attention cost in the number of tokens. Most token-reduction methods adapt token identities within a pre
arXiv:2609.33980v1 Announce Type: new Abstract: Dynamic graph anomaly detection requires repeated decisions as graph structure and class prevalence drift, yet detector benchmarks usually score a fixed
arXiv:2609.04742v1 Announce Type: cross Abstract: Running an unfamiliar nuclear-physics code is rarely difficult because of the physics alone. One must find and build the program, learn its input conv
arXiv:2609.35431v1 Announce Type: new Abstract: This paper studies low-altitude question answering (LAQA), in which distributed unmanned aerial vehicle (UAV) memories are aggregated at a ground server
We've partnered with @OpenAI to bring the new Sign in with ChatGPT experience to Nous Portal. Log into Nous Portal with ChatGPT to use your plan in Hermes Agent, with full visibility and controls in C
I don’t even know if this counts as news anymore. But it should. This weekend our team spent 48 hours investigating the rogue OpenAI agent activity that targeted the Australian government and other or
it's basically impossible for someone to just 'show you their prompt' now, because everything is about references, skills and examples I often ask my agent to look at 3 other repos I've made first, se
arXiv:2609.30578v1 Announce Type: new Abstract: Language models gain accuracy from more compute at test time, but majority voting over independent samples saturates: as samples grow, the vote converge
arXiv:2609.31234v1 Announce Type: new Abstract: Problem. Ultra-high-resolution (UHR) remote sensing with vague user intents has two bottlenecks: visual tokens are expensive, and tool calling must be f
Been doing a bunch of vibe coding lately. Had my agents host a private WoW server for me, then built out a web browser client so you can play without installing the game and it has mobile controls. Af
arXiv:2609.30123v1 Announce Type: new Abstract: Agent skills provide reusable knowledge and instructions, yet agents must repeatedly infer how to apply them and which operation should follow. This cou
arXiv:2609.29672v1 Announce Type: new Abstract: Artificial intelligence helps education most where an essential provision has been rationed by cost. For language learners that provision is a teacher's
arXiv:2609.27632v1 Announce Type: cross Abstract: We present a compliance-first architecture for AI in regulated finance that treats regulation as an orientation layer rather than a deterministic rule
It’s a big week for Meta. The company just kicked off its big Connect conference on Wednesday, and the new Muse AI agent appears to be an early hit. I’ve been using it — it is surprisingly good. CEO M
arXiv:2509.18088v2 Announce Type: replace-cross Abstract: Efficient resource allocation in multi-agent systems requires autonomous agents to coordinate their decisions while balancing system-wide obje
Just a quick PSA. llama.cpp does have prompt caching. if you are running large context lengths and have long multiturn projects, increasing -cram can provide you with massive speedups. There is a poin
arXiv:2609.27891v1 Announce Type: cross Abstract: Repository-level coding benchmarks have become the standard for evaluating coding agents, yet they inherently suffer from data leakage because they ar
Google Cloud has become the platform of choice for startups building AI. Our uniquely complete stack — including a choice of first- and third-party compute and models; our platform for building and ma
arXiv:2609.22476v1 Announce Type: cross Abstract: Transmission system operators face rising complexity from renewable integration, reduced inertia, and tighter security margins. Large language models
arXiv:2609.23957v1 Announce Type: new Abstract: Scientific agents are mostly evaluated on whether they complete tasks or recover known results; we instead study variation across repeated open-ended ca
arXiv:2511.18486v2 Announce Type: replace Abstract: Electromagnetic navigation systems (eMNS) enable a number of magnetically guided surgical procedures. A challenge in magnetically manipulating surgi
arXiv:2603.17043v2 Announce Type: replace Abstract: Physics-aware multimodal large language models (MLLMs) can localize and characterize two-dimensional (2D) material flakes from optical microscopy im
If like me you enjoyed classics like Baldur's Gate 2, this is a small fun experiment. For anyone interested: https://www.youtube.com/live/8FhPfRKTucw?si=PMIVdHbZ-31PNwZD Qwen 3.8 Flash Next has amazin
arXiv:2609.26204v1 Announce Type: cross Abstract: When a professional web developer's code fails a test, they do not simply re-read the stack trace. They open the application in a browser, click butto
arXiv:2609.24098v1 Announce Type: new Abstract: Visual Question Answering (VQA) with Multimodal Large Language Models (MLLMs) requires not only producing safe and effective responses, but also groundi
arXiv:2603.03768v2 Announce Type: replace Abstract: Full-stack human-robot collaboration (HRC) can become brittle when replacing a planner, partner model, coordination policy, or controller changes th
arXiv:2609.22925v1 Announce Type: new Abstract: Vision-language models (VLMs) provide a compelling foundation for reasoning-driven mobile navigation, offering rich contextual understanding and strong
arXiv:2609.22223v1 Announce Type: new Abstract: Long-form factuality verification is commonly implemented as a static decompose-search-verify pipeline, with separately prompted modules processing clai
Reactiv used Amazon Bedrock AgentCore to build a multi-agent AI Scheduler that autonomously refreshes Shopify merchants' mobile apps on a schedule, reducing merchant configuration time by 80% and gett
In about four weeks, Trane Technologies built an AI-powered agentic solution on Amazon Bedrock AgentCore that reduced a 20-minute, multi-screen building diagnostic workflow to a 20-second natural lang
arXiv:2609.22688v1 Announce Type: new Abstract: Generating parametric CAD models requires accurate geometry and stable feature dependencies. Existing methods face challenges in selecting geometric ref
arXiv:2609.20995v1 Announce Type: cross Abstract: Natural spoken interaction requires more than streaming ASR, language generation, and speech synthesis: a system must react to overlap without canceli