Knowledge catalogue
arXiv:2507.00938v4 Announce Type: replace-cross Abstract: Foundation models now enable autonomous agents to interact with real-world websites, but existing benchmarks emphasize general-purpose browsin
arXiv:2609.27770v1 Announce Type: new Abstract: Autonomous web agents, powered by Large Language Models (LLMs), have garnered significant attention for automating various web-based tasks with multi-st
arXiv:2607.11039v2 Announce Type: replace-cross Abstract: Young job seekers frequently explore their career possibilities by browsing peers' posts that share job-seeking experiences. However, static b
arXiv:2609.24115v1 Announce Type: new Abstract: Tool-calling LLM agents are increasingly deployed in enterprise applications. However, effective evaluation and optimization require high-quality, diver
arXiv:2609.22691v1 Announce Type: new Abstract: An enduring and richly elaborated dichotomy in cognitive neuroscience is that of human behavior control mechanisms, divided into habitual versus goal-di
arXiv:2605.11269v2 Announce Type: replace-cross Abstract: Modern gravitational wave astronomy relies on modeling tasks that often require months of graduate-level effort, including building fast wavef
arXiv:2609.22724v1 Announce Type: cross Abstract: Mobile agents powered by foundation models now automate complex, multi-step workflows on real devices, but their trajectories can violate app-specific
Database security controls are moving closer to enterprise data as artificial intelligence creates new access paths around traditional application defenses. The aim is to enforce authorization regardl
arXiv:2609.24859v1 Announce Type: cross Abstract: The ideation phase of participatory AI risk assessment often starts with a blank slate or a limited list of predefined risks, making it difficult to s
arXiv:2609.24161v1 Announce Type: cross Abstract: As LLM agents increasingly interact with external tools through standardized protocols such as MCP, tool-interface design becomes a critical yet under
Must-read papers of the week ▪️ JEPA-Anything ▪️ Modality-Autoregressive World-Action Models ▪️ In-Context Robot Learning with VLM Agents ▪️ Dream-RSI: Recursive Self-Improvement through Evolving Worl
arXiv:2609.21386v1 Announce Type: cross Abstract: Comprehensive video understanding is crucial for advancing artificial intelligence toward the intricate dynamics of the physical world. While recent a
You can now automate EDD (eval-driven development) with Coding Harness Agents > build a baseline LLM-based application > score every change with judge evals > keep what improves, reject what regresses
Is there a middle ground between total bans & zero oversight? Marcus is right that we rushed into agents without fixing basic sandboxing first. Perhaps the most important warning I ever issued was thi
arXiv:2609.19569v1 Announce Type: cross Abstract: Disease severity classification for genetic conditions is subjective and labor-intensive, creating bottlenecks in genomic screening, where commercial
The revamped projects feature in Claude Code allows users to run multiple agents under the same roof, with a shared memory, goals, and library of files and artifacts. Similar to Grok Bot and other too
arXiv:2609.17842v1 Announce Type: cross Abstract: Conversational visual analytics (CVA) agents powered by large language models generate visualizations and natural-language explanations from open-ende
arXiv:2609.18326v1 Announce Type: new Abstract: Unmanned aerial vehicles (UAVs) extend embodied intelligence into continuous three-dimensional space, where perception, reasoning, physical embodiment,
arXiv:2609.18435v1 Announce Type: new Abstract: Automating biological research requires general-purpose, reproducible robot systems that allow individual wet-lab researchers to delegate robot tasks wi
arXiv:2609.16093v1 Announce Type: new Abstract: A shopping conversation has many routes to the same cart, and a task-success rate reduces all of them to one score. We build a deterministic and reprodu
Agentic AI workflows using NVIDIA Omniverse libraries automate preparation of Blender scenes for robotics simulation by adding semantic labels, sensor definitions, physics properties and validating th
arXiv:2609.16436v1 Announce Type: cross Abstract: Simulations based on large language models (LLMs) have proven to be powerful for understanding human behavior, making them valuable additions to the s
arXiv:2601.00290v3 Announce Type: replace Abstract: Clinical trials constitute a critical yet exceptionally challenging and costly stage of drug development (2.6B per drug), where protocols are encode
Runtime security startup Eve Security Inc. wants to help stop dangerous artificial intelligence agents in their tracks after raising 4.5 million in funding today. The round, which was led by Run Ventu
Salesforce Inc. unveiled AIforce today during its Dreamforce user conference, a new artificial intelligence interface layer that brings the power of the company’s platform to where people use AI agent
arXiv:2609.12896v1 Announce Type: new Abstract: LLM-based agents rely on heterogeneous interaction capabilities to accomplish complex tasks. Existing approaches often distribute these capabilities acr
arXiv:2609.11243v1 Announce Type: new Abstract: Autonomous research agents are increasingly expected to search the literature, analyze experimental evidence, and generate scientific hypotheses. These
arXiv:2609.09212v1 Announce Type: cross Abstract: This paper presents an end-to-end evaluation framework for image-triggered command injection against computer-use agents (CUAs). The goal is to test w
arXiv:2609.09678v1 Announce Type: new Abstract: Clinical diagnosis agents must decide not only what test to request next, but also when to diagnose or defer. Existing agent benchmarks largely evaluate
arXiv:2609.09219v1 Announce Type: cross Abstract: AI research agents combine prior knowledge, public sources, and experimental feedback to produce useful results. The Discovery Certification Protocol
Parmy Olson / Bloomberg: Only 4% of the startups in YC's 2026 spring batch had a native mobile app as their main product, down from 15% in 2013, as startups focus on AI and agents — Artificial intelli
arXiv:2609.08589v1 Announce Type: cross Abstract: Recent large language models can emit task-progress signals that agent frameworks use to decide whether a task should continue or stop, yet whether a
Swiss artificial intelligence startup Typewise AG today launched Nova, a system designed to build, run and continuously improve customer-service AI agents without requiring dedicated operations specia
Researchers reported in September 2026 that OpenAI’s rogue AI agents accessed at least twelve additional online sites, including university servers, Wikipedia, and text‑sharing platforms. These sites
Threat actors used a multi-agent artificial intelligence framework to compromise thousands of credentials in under six hours, Google LLC’s Google Threat Intelligence Group said in a report released to
arXiv:2609.04438v1 Announce Type: new Abstract: Long-horizon multimodal agents should remember not only what happened but also who participated. This capability depends on linking recurring faces, voi
arXiv:2609.03467v1 Announce Type: cross Abstract: Large language models (LLMs) are increas- ingly deployed as long-horizon conversational agents, motivating growing interest in mem- ory systems. Howev
arXiv:2601.07468v2 Announce Type: replace Abstract: Memory enables Large Language Model (LLM) agents to perceive, store, and use information from past dialogues, which is essential for personalization
arXiv:2609.02885v1 Announce Type: new Abstract: Recent web agents use world models for test-time action selection by sampling candidate actions, predicting the resulting web states, and ranking them w
Learn how to run parallel agents in the GitHub Copilot app, and experience the moment it stops feeling scary and starts feeling powerful. The post GitHub Copilot app for Beginners: Run several agents
I have a few AI subscriptions and I kept running into the same problem. I had powerful models available, but I struggled to use them in real life in an organized way. I looked at projects like OpenCla
arXiv:2609.01852v1 Announce Type: new Abstract: Persistent memory supports personalized agents, but a stale stored fact can override current authoritative evidence without warning. We study when this
CrowdStrike Holdings Inc. today announced three additions to its Falcon platform: an identity provider built for artificial intelligence agents, a rebuilt investigation layer that runs multiple Charlo
arXiv:2609.00935v1 Announce Type: cross Abstract: Deep Research agents tackle knowledge-intensive tasks through multi-round retrieval and decision-oriented generation. However, these agents suffer fro
Finally, a good paper testing if graph memory actually beats flat retrieval for long-term agents. (bookmark this one) Researchers extract each conversational turn into typed nodes and attributed edges
arXiv:2609.00434v1 Announce Type: new Abstract: Evaluating task-oriented dialogue agents requires judging not merely whether a reply reads well but whether each turn advances the underlying workflow s
arXiv:2608.29621v1 Announce Type: cross Abstract: Long-horizon story-driven video generation requires a production agent to coordinate narrative decomposition, state tracking, shot design, prompt cons
arXiv:2608.31005v1 Announce Type: new Abstract: Existing long-video agents acquire evidence through one uniform behavior, ignoring whether the required evidence is concentrated, requires broad occurre
arXiv:2608.30303v1 Announce Type: new Abstract: Search agents reduce hallucination by grounding answers in retrieved web evidence. Yet reliance on retrieval also creates an attack surface: poisoned co
arXiv:2608.27911v1 Announce Type: new Abstract: Agents with smaller language-model backbones are less expensive but can drift into persistent failure modes, whereas those with larger backbones are gen
Ethan Mollick / One Useful Thing: The Hugging Face and Mythos 5 incidents show AI agents can self-organize, raising questions about how much agency they should have and when to seek human input — From
Dwarkesh Patel / Dwarkesh Podcast: OpenAI's Hugging Face incident report says AI agents used exploits to gain full admin access to OpenAI's own research cluster supporting its VM environments — The wh
arXiv:2608.26189v1 Announce Type: new Abstract: Tool-using agents fail two ways: choosing the wrong tool, or forming wrong arguments, and an early failure of either kind can silently corrupt everythin
arXiv:2608.27427v1 Announce Type: cross Abstract: Large language model (LLM) agents in governed organizations must let the persona (instructions, tone, self-presentation) evolve freely, while keeping
arXiv:2608.23622v1 Announce Type: new Abstract: Large language models (LLMs) have shown strong capabilities in reasoning, planning, and tool use, but many scientific and engineering tasks require more
METR: METR and Redwood detail how ~1,200 OpenAI agents coordinated cheating on an unsanctioned board, sending 70K+ messages and files, and ~700 attacked Hugging Face — Redaction summary statement: Exc
arXiv:2608.23635v1 Announce Type: cross Abstract: Large language models (LLMs) rely on tool calling as a fundamental agent capability, enabling them to invoke external systems and complete tasks beyon
arXiv:2608.21830v1 Announce Type: new Abstract: Graphical User Interface (GUI) agents powered by Multimodal Large Language Models (MLLMs) have shown strong potential for automating tasks across divers
arXiv:2608.23336v1 Announce Type: new Abstract: Developing competitive deep learning baselines for medical imaging remains a highly iterative process requiring literature review, implementation, exper
arXiv:2608.21690v1 Announce Type: new Abstract: LLM agents increasingly take on long-running tasks whose history grows far beyond a single model context window. Existing approaches compress earlier in