Knowledge catalogue
arXiv:2610.07332v1 Announce Type: cross Abstract: Long-horizon LLM agents are frequently implemented using sparse mixture-of-experts (MoE) models, yet the co-design of agentic behavior and MoE structu
arXiv:2610.08364v1 Announce Type: new Abstract: Frontier AI evaluations increasingly use open-ended, agentic, long-horizon tasks whose transcripts can span hundreds of pages of outputs and actions fro
arXiv:2610.02994v1 Announce Type: cross Abstract: LLM agents often fail mid-task due to invalid tool calls, repeated actions, or poorly grounded reasoning, and learning from these failures is a path t
arXiv:2610.03213v1 Announce Type: new Abstract: Tool-equipped AI agents use tool calls to access data and act on external systems. Horizontal growth of agentic systems increases the number of these in
Agent workload isolation is becoming a practical infrastructure challenge as research teams move beyond training models to running code and testing agents. Systems built for intensive computation must
arXiv:2508.17692v2 Announce Type: replace Abstract: Recent advances in LLM-based agents highlight the importance of their reasoning frameworks, which guide the problem-solving process in diverse ways.
arXiv:2610.01017v1 Announce Type: new Abstract: Large language models (LLMs) increasingly construct multi-agent workflows that decompose a complex task and assign specialist agents from a pool. Howeve
arXiv:2609.39140v1 Announce Type: new Abstract: Learning to complete tasks in unfamiliar environments with unknown rules remains a key challenge for LLM agents. Current LLM agents often record their d
arXiv:2609.36855v1 Announce Type: new Abstract: Multi-agent LLM systems rely on message passing among specialized agents to accomplish complex tasks. However, an upstream agent may provide useful info
arXiv:2609.34385v1 Announce Type: cross Abstract: Memory is critical for AI agents. Many existing agent-memory systems follow an Ahead-of-Time (AOT) design, constructing memory before a specific reque
arXiv:2609.24662v1 Announce Type: new Abstract: LLM-based agents increasingly operate in environments where they interact with users, tools, and external systems. Yet most security evaluations assume
arXiv:2609.18929v1 Announce Type: cross Abstract: In multi-agent environments, coordinating agents to prevent interference and ensure robust individual performance is a critical challenge. Previous re
arXiv:2609.17221v1 Announce Type: cross Abstract: Autonomous Software Engineering Agents (SWE-Agents) excel in deterministic coding tasks but struggle with Architecture 0, the nascent system design ph
arXiv:2609.14824v1 Announce Type: new Abstract: The emergence of large language models (LLMs) and large multimodal models (LMMs) has enabled a new class of agentic systems capable of integrating natur
arXiv:2604.07487v2 Announce Type: replace Abstract: Large language model agents rely on effective model context to obtain task-relevant information for decision-making. Many existing context engineeri
arXiv:2606.20041v2 Announce Type: replace-cross Abstract: We propose an AI economist agent for economic and financial scenario analysis. Scenario design often requires analysts to assess emerging risk
arXiv:2609.09647v1 Announce Type: new Abstract: Agentic systems are rapidly moving to production, where they read untrusted inputs, call tools with real permissions, and act autonomously, expanding th
Executive Summary Since the release of our May 2026 report detailing adversarial misuse of artificial intelligence (AI), Google Threat Intelligence Group (GTIG) has observed forward leaning adversarie
arXiv:2609.05190v1 Announce Type: new Abstract: In this paper we illustrate a novel architecture generating interpretable behavior and explanations. We refer to this architecture as the Mirror Agent M
arXiv:2609.02371v1 Announce Type: new Abstract: With the proliferation of LLM agents, the ability to understand and diagnose failures in agents is essential to achieving superior effectiveness and tru
arXiv:2608.28977v1 Announce Type: new Abstract: Several works have investigated the influence of graph topology on cooperation among artificial agents, while the majority of the literature has focused
arXiv:2606.17092v2 Announce Type: replace-cross Abstract: Agentic systems are increasingly integrated with geographic information systems (GIS), where multi-agent coordination enables complex conversa
**Vertical Advantage: Transforming Industries with Lakebase and Agentic AI** The article details how Lakebase’s unified data‑lake platform, coupled with Agentic AI’s autonomous decision‑making agents,
arXiv:2608.23691v1 Announce Type: new Abstract: We study autonomous mathematical discovery in the Station, an open-world multi-agent environment in which AI agents from different model families pursue
arXiv:2608.23858v1 Announce Type: cross Abstract: The Agent Payments Protocol (AP2), introduced by Google, enables large language model (LLM)-driven shopping agents to authorize and execute payments o
A few weeks ago I shared Agent Quest, my open-source experiment that turns Claude Code and Codex sessions into heroes living inside a small 2D world. The original idea was mainly about making it easie
arXiv:2608.17975v1 Announce Type: cross Abstract: Programmatic representations provide a compelling paradigm for 3D content creation, enabling fine-grained edits, interpretability, and explicit struct
arXiv:2608.16900v1 Announce Type: cross Abstract: Language-model agents increasingly produce quantum-science results; we ask whether the same agentic paradigm can also scrutinize them in an auditable,
arXiv:2608.12355v1 Announce Type: cross Abstract: Recent progress in AI coding agent research has led to rapid improvements in agents' ability to autonomously perform complex software engineering task
This week we launched the world's most accurate document extraction agent over real-world documents. Introducing LlamaExtract Agentic Plus 💫 . It is a complete document extraction model+harness engine
Grok 4.6 is now one of the top models in the world for agentic workflows It ranks #1 on the Artificial Analysis Agentic Index, tied with Claude Opus 5 Max Agentic AI is about more than answering quest
Knowledge is rather abstract and philosophical. So what does it mean from an agentic context? How does providing the right knowledge at the right time to an agent increase its accuracy, task completio
arXiv:2608.08604v1 Announce Type: new Abstract: Multi-agent reinforcement learning (MARL) is a powerful framework for solving complex collaborative tasks, but it relies heavily on well-defined global
arXiv:2608.06410v1 Announce Type: new Abstract: Automated agent design improves agent harnesses through iterative revision, evaluation, and feedback summarization. Existing methods are largely candida
arXiv:2608.07346v1 Announce Type: new Abstract: With the rapid advancement of large language models (LLMs), harnesses have become essential infrastructure for deploying agents across a wide range of d
arXiv:2608.06891v1 Announce Type: new Abstract: Agent skills provide reusable procedural knowledge that helps agents solve specialized tasks. As their use expands, evaluating skill quality becomes inc
In the modern data landscape, query performance tuning and managing system price-performance is challenging, especially as the number of agentic workloads increase. Even for experienced developers and
arXiv:2603.21194v2 Announce Type: replace-cross Abstract: Multi-agent discussions have been widely adopted, motivating growing efforts to develop attacks that expose their vulnerabilities. In this wor
How fast is artificial intelligence advancing? Behind the scenes at OpenAI Group PBC, AI agents are fluent, technically precise and occasionally profane in their extensive conversations…with each othe
arXiv:2608.00030v1 Announce Type: new Abstract: Specialised retrieval agents typically surface higher quality results than general-purpose search, but selecting the optimal agent for a given query rem
arXiv:2603.17445v5 Announce Type: replace-cross Abstract: When a multi-agent system produces an incorrect or harmful answer, who is accountable if execution logs and agent identifiers are unavailable?
i'll say it plainly, hermes agent desktop is the best agentic app i've used, and i'm a little mad i didn't find it sooner. it auto see the models i'm serving, laguna s 2.1 sitting on my dgx spark and
Increasing the adoption of generative AI across the enterprise requires you to do more than deploy a generic chatbot with a custom wrapper. Interacting with business-critical databases demands absolut
arXiv:2607.24280v1 Announce Type: new Abstract: Agentic search enables large language models to solve knowledge-intensive tasks by interleaving multi-step reasoning with retrieval, yet optimizing this
A skill cut agent costs by 44% and latency by 56%, but also reduced answer completeness. Here’s how tracing, evals, and a long-running agent exposed and corrected the regression. The post How to impro
just watched @yoheinakajima's Active Graph talk at AI Engineer. not a code call graph but the agent run itself is the graph: goals, tasks, evidence, decisions, all projected from an append-only event
Very cool idea to convert memory to skills. (bookmark it) Most agent memory systems retrieve past traces as passive context. MSCE turns them into executable skills instead. The training-free framework
arXiv:2607.12619v1 Announce Type: new Abstract: The rapid emergence of LLM-powered autonomous and semi-autonomous agents is reshaping software systems from static, request-response components into goa
arXiv:2607.12823v1 Announce Type: new Abstract: Interaction with AI agents has become one of the most frequent activities of everyday digital life. Whether conversing with an assistant, working with a
arXiv:2406.07089v4 Announce Type: replace Abstract: Recent advances in Multimodal Large Language Models (MLLMs) have shown promise for remote sensing tasks such as visual question answering and scene
arXiv:2607.04292v1 Announce Type: new Abstract: Ransomware has evolved into a complex, adaptive, and fast-moving adversary category in which static signatures and monolithic classifiers fail to genera
arXiv:2607.04395v1 Announce Type: new Abstract: Recent agentic approaches to LLM-based kernel generation have achieved impressive results on CUDA. For emerging AI accelerators such as AWS Trainium and
arXiv:2505.21550v2 Announce Type: replace-cross Abstract: Collaborative agentic AI is projected to transform entire industries by enabling AI-powered agents to autonomously perceive, plan, and act wit
arXiv:2606.28666v1 Announce Type: cross Abstract: Agent-based AI has enabled the automation of tasks by exposing application tools and resources to large language models (LLMs). However, to improve sc
arXiv:2606.23032v2 Announce Type: replace Abstract: Finance Agent v2 (by Vals AI) has emerged as the reference benchmark for evaluating both Anthropic Claude and OpenAI ChatGPT frontier language model
arXiv:2606.11537v1 Announce Type: new Abstract: Financial and tabular question answering requires more than fluent reasoning: answers must be grounded in the exact facts, formulas, units, signs, and s
arXiv:2606.03544v1 Announce Type: new Abstract: Self-improving language agents are typically evaluated in isolation: an agent attempts a task, receives feedback, and iteratively refines its own behavi
arXiv:2605.29191v1 Announce Type: cross Abstract: Non-uniform scaling control of formation enables multi-agent systems to adjust their shape by scaling with different ratios along different coordinate
arXiv:2605.28816v1 Announce Type: new Abstract: World models for interactive video generation have largely focused on single-agent settings, where future observations are generated from a single contr
arXiv:2605.20563v1 Announce Type: cross Abstract: Recent advances in multi-agent systems have shown great potential for solving complex tasks. However, when multiple agents edit a shared codebase conc