Knowledge catalogue
Hey everyone, Giving AI agents access to MCP tools or shell commands is awesome, but prompt injection is still a huge headache. If an agent reads an untrusted document containing `ignore previous inst
arXiv:2609.10854v1 Announce Type: cross Abstract: Conventional vulnerability analysis relies on either system access or dynamic interaction, all of which may be unavailable to third-party analysts aud
arXiv:2609.11030v1 Announce Type: new Abstract: AI agents increasingly act through tools and delegated authority, but general incident repositories rarely capture the mechanisms needed to compare publ
arXiv:2606.19795v2 Announce Type: replace-cross Abstract: Electronic design automation (EDA) is multi-stage and handoff-heavy, relying on transfers among humans, design artifacts, and multiple tools.
Agent skills fit well alongside documentation and remote MCP servers as ways of enabling the success of your AI workflows. They reduce context window usage for certain use cases, and they're straightf
arXiv:2609.09153v1 Announce Type: new Abstract: Large language models are increasingly deployed as agents that plan over long horizons and act through external tools. Most agents select actions throug
arXiv:2609.06835v1 Announce Type: cross Abstract: Agentic AI systems execute complex tasks through long-horizon workflows of planning, tool use, and multi-agent coordination. Task failures in these sy
arXiv:2609.05435v1 Announce Type: new Abstract: Modern language agents are expected to operate over long horizons: they ask follow-up questions, reuse worked examples, handle tool feedback, and adapt
Tool: .blend URL Viewer I'm continuing to have a lot of fun with GPT-6 Astra and Blender (see my TIL). As a big fan of the Imperial Fabergé Easter eggs, I've always thought it would be fun to make som
arXiv:2609.04280v1 Announce Type: cross Abstract: Modern LLM-based agents operate through a harness of tools, reusable skills, and specialist agents that shapes what they observe and what they can do.
Interesting details in here about how OpenAI researchers are using coding agents I'd love to know what caused the huge uptick in token spend in mid-July, was that when Astra became available to employ
Hello, I'm a bit obsessed with cache management on local LLMs. For the last few days I've been working on cache management on vLLM with my 2x DGX Spark and DeepSeek v4 Flash 0731. I felt something was
arXiv:2609.03787v1 Announce Type: new Abstract: AI agents increasingly gather evidence, invoke tools, apply constraints, and produce decisions that people or software may commit to action. A final out
arXiv:2609.03588v1 Announce Type: new Abstract: As LLMs increasingly act through tools, they must reconcile user instructions, parametric knowledge, and dynamic environmental observations before takin
Nvidia Corp. is targeting artificial intelligence agent enthusiasts with a new local distributed clustering tool called the Personal AI Router. It enables them to use any idle Mac computers or PCs lyi
arXiv:2609.03727v1 Announce Type: new Abstract: Large language model agents can plan, invoke tools, and modify external states, yet most systems still take an explicit user instruction as a fixed star
arXiv:2609.04135v1 Announce Type: new Abstract: AI agents are increasingly being developed and deployed across organizations using heterogeneous agent-development frameworks, AI models, tool interface
GPT‑6 Astra is a lightweight, high‑performance OpenAI model that can be hired for under $6 an hour and outperforms rivals on tests such as FrontierMath (97.6%) and ARC‑AGI‑3 (99.9%). The authors burne
arXiv:2609.02149v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly evolving from conversational assistants into agents capable of operating external digital environments.
arXiv:2609.01058v1 Announce Type: new Abstract: Training open-ended agents via reinforcement learning (RL) is hindered by the lack of verifiable gold answers and scalable rubrics. Moreover, even near
Anthropic publish the system prompts for their Claude consumer applications (Claude.ai and the Claude mobile apps - sadly not for Claude Cowork or Claude Code). I love that they do this, and that they
arXiv:2609.01294v1 Announce Type: new Abstract: Deep-research agents answer complex questions by interacting with search and browsing tools, yet they often search along a single evolving trajectory. O
arXiv:2609.00813v1 Announce Type: new Abstract: While reinforcement learning has enabled LLM-based search agents to invoke external tools, existing methods train under fixed budgets and cannot adapt w
arXiv:2607.09600v2 Announce Type: replace Abstract: Enhancing the reasoning capabilities of large language model (LLM) agents requires effective orchestration of diverse expert models and tools. Howev
arXiv:2608.28601v1 Announce Type: new Abstract: Interactive visualizations support conceptual understanding in undergraduate mathematics, but building them has required programming expertise most inst
Debian voted to allow developers to use AI tools in their contributions to the Linux distribution's 'development, maintenance, [and] documentation.' The new policy on AI acknowledges that 'responsible
arXiv:2603.19423v3 Announce Type: replace-cross Abstract: Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously comp
arXiv:2608.26143v1 Announce Type: cross Abstract: Memes have turned out to be a powerful tool through which individuals share their ideas concerning contemporary social and political problems. Their a
arXiv:2608.26546v1 Announce Type: new Abstract: Autonomous agents are increasingly adopted to complete complex, multi-tool workflows in real-world settings. However, existing benchmarks typically sepa
arXiv:2608.26004v1 Announce Type: cross Abstract: Agentic LLM pipelines face escalating inference costs as context accumulates across retrieval, tool use, and multi-turn interactions. To control laten
arXiv:2608.23651v1 Announce Type: cross Abstract: Agent harnesses record a failed tool call and its error message in the transcript and ask the model to continue, on the assumption that the error is c
arXiv:2608.24588v1 Announce Type: new Abstract: Large Language Model (LLM) agents increasingly solve long-horizon tasks through multi-turn interactions with users and external tools. In these settings
arXiv:2608.22963v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) are increasingly deployed as multi-step agents, where explicit reasoning supports task decomposition and tool c
Compute has always been core to the @VerneRobotics story. Getting there meant negotiating long, expensive contracts with big neoclouds, and projecting compute needs years into the future. Verne wasn't
arXiv:2608.22695v1 Announce Type: cross Abstract: Agent ecosystems now include thousands of MATS components (Models, Agents, Tools, and Skills), yet their discovery still relies on in-context routing.
arXiv:2608.21592v1 Announce Type: new Abstract: Contact-rich robotic manipulation requires an accurate model of the kinematic relationship between a robot's joints and the task features it senses. Thi
arXiv:2608.22429v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) capable of thinking with images often rely on external tools for fine-grained perception. However, this relianc
arXiv:2608.20481v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) is an open source JSON-RPC protocol that standardizes how large language models (LLMs) interact with external systems
arXiv:2608.21159v1 Announce Type: cross Abstract: Tool-using AI agents turn delegated tasks into provider effects, yet authorization often ends at admission while provider state, delivery, retry, and
arXiv:2608.21101v1 Announce Type: cross Abstract: As large language model (LLM) agents move from conversation to executing code, reading local files, and orchestrating external tools, a single agent h
Banger paper from Microsoft. It's on agent reliability in real business workflows. (bookmark it) Thinkingbox is a sandbox with isolated MCP-compatible tool sessions, plus a benchmark of 507 policy-con
arXiv:2607.13854v2 Announce Type: replace Abstract: Multimodal agents that think with images iteratively manipulate visual evidence and invoke tools across many steps. Existing reinforcement learning
arXiv:2506.05616v3 Announce Type: replace Abstract: We aim at designing language agents with greater autonomy for crystal materials discovery. While most of existing studies restrict the agents to per
arXiv:2608.20116v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used in settings where textual summaries, numerical observations, and external tool outputs may provide co
It’s never been easier to start an AI-powered startup on Google Cloud. You grab an API key from Google AI Studio at breakfast, paste it into Antigravity, and by lunch you’ll have a nascent prototype o
ChatGPT search now uses the site:operator at scale Promptwatch is part of the emerging 'GEO' space, for Generative Engine Optimization - the chatbot version of SEO, where companies offer tools and con
arXiv:2608.18136v1 Announce Type: new Abstract: Conversational agents now act for end users through tools while holding access to customer databases and internal policy documents that a caller can rea
I currently have these models available through Ollama/cloud: And I’m using Claude, Codex, OpenCode, and Ollama as my coding/agent tools. I want to learn professional vibecoding — not just asking AI t
Very interesting new work Amazon and colleagues. (bookmark it) This connects to the emerging theme of treating the corpus as part of the harness. Planning loops, tool protocols, and context management
arXiv:2608.17393v1 Announce Type: new Abstract: Reinforcement learning for coding agents increasingly relies on long-running agent harnesses to manage tool integration, repository contexts, and execut
arXiv:2608.17129v1 Announce Type: new Abstract: Vision-language Models (VLMs) excel at 2D grounding, spatial reasoning and agentic tool-based planning in static scenes. However, consider asking a home
arXiv:2608.15888v1 Announce Type: new Abstract: LLM-based agents can act on behalf of a user to access cloud services, call tools, or invoke agents. At session start, the agent's permissions are set b
arXiv:2608.15127v1 Announce Type: cross Abstract: Agentic applications are shifting AI serving from isolated model inference to long-running workloads in which LLMs coordinate tools, environments, and
Every data team knows the moment. Someone opens a table, sees a column called cust_seg_flg, and has to go ask around to find out what it means, whether it's safe to use, and whether anyone has already
arXiv:2608.15834v1 Announce Type: new Abstract: Tool-calling LLM agents navigate unfamiliar codebases with a handful of generic primitives for listing, reading and searching files (ls, cat, grep). A k
model: add Kimi-K3 text model (#26185) model: add Kimi-K3 text model Hybrid KDA (linear) + MLA (full) attention as in Kimi-Linear-48B, plus five things that architecture does not have: cross-layer res
arXiv:2604.05485v2 Announce Type: replace Abstract: LLM agents call tools, query databases, delegate tasks, and trigger external side effects. Once an agent system can act in the world, the question i
arXiv:2608.12847v1 Announce Type: new Abstract: Retrieval can identify a past trajectory that may matter, yet it does not specify how an acting agent should use that trajectory after users, entities,
I’ve experimented with Cursor, Antigravity, Claude Code/CLI, Ollama, Gemma 4B, MiniMax, Hermes Agent, and different local/cloud models. My problem isn’t knowing what these tools are—I don't know how t
arXiv:2608.12880v1 Announce Type: cross Abstract: Security evaluations of tool-using agents often equate stored labels with behavioral facts. We audit a preserved campaign by tracing 10,200 execution