Knowledge catalogue
arXiv:2609.30725v1 Announce Type: new Abstract: Although effective, coding agents often incur substantial monetary costs. Their recurring cost-inefficient behaviors remain underexplored. We conduct th
arXiv:2609.31076v1 Announce Type: new Abstract: Language agents struggle to act and learn in environments that require long sequences of low-level actions. Code-based abstractions can make these agent
Misconfiguring Turnstile by skipping backend validation leaves sites exposed to bots. Turnstile Spin fixes incomplete setups by using your preferred AI coding agent to wire up server-side verification
arXiv:2609.29547v1 Announce Type: cross Abstract: Agentic AI is sold on a simple promise: the system keeps acting when the user stops watching. That promise creates an accountability inversion. As ste
arXiv:2609.29921v1 Announce Type: new Abstract: Large language model agents increasingly combine generation, decision-making, execution, and self-evaluation within a single agentic loop. Although they
I looked this for 2+ hours. Transluce’s investigation was quite clever: - OAI agents used urlquery to run code/access websites - urlquery logs all activity; this let the team find 6K+ AI actions (like
It's not 'superintelligence' that's dangerous, but the business models of OpenAI & Anthropic. They want businesses to use autonomous agents because agents chew up more tokens. But 'agency' =/= 'intell
arXiv:2609.27606v1 Announce Type: new Abstract: We introduce State-Grounded Conditioning (SGC), a design principle for user-facing LLM agents that must condition on live user state (game state, sessio
arXiv:2609.26781v1 Announce Type: new Abstract: A multi-agent system can reduce latency on complex tasks by executing work concurrently. Several pioneering harness frameworks support multi-agent syste
Skills let you encode domain-specific procedures as reusable, portable instructions for agents, but a fluent answer doesn't prove the agent picked the right skill or followed it. Learn how to measure
Impressive paper showing how much the first retrieval step matters for deep research agents. It helps to improve GPT-5.5 from 83.1% to 90.5% on BrowseComp-Plus with the same retriever and the same age
At this past week’s AGNTCon + MCPCon Europe 2026 conference in Amsterdam, the buzz around agentic artificial intelligence was palpable – but nobody was particularly worried that AI was going to kill u
Chris Metinko / Axios: Raindrop, which develops tech for monitoring AI agents to catch failures such as hallucinations and tool misuse, raised a 35M Series A led by CRV — AI agent monitoring platform
arXiv:2609.18598v1 Announce Type: cross Abstract: Self-driving laboratories can explore synthesis conditions autonomously, but their decision-making layer is typically a black-box optimizer, and the o
arXiv:2609.17930v1 Announce Type: new Abstract: As AI agents take on long, autonomous tasks, we increasingly oversee rather than perform the work, yet we still judge them almost entirely by whether th
arXiv:2609.17989v1 Announce Type: cross Abstract: Large language models (LLMs) now serve as conversational shopping assistants on platforms that also sell advertising. These AI agents face a conflict
arXiv:2609.16541v1 Announce Type: cross Abstract: We test the performance of agents for automated network intrusion response in a cyber range intended for human operator training. The range implements
Agents are coming for video production. @PooldayAI is going for this. You prompt it once, and it edits your real footage, picks the right generative model for each task, and checks its own work before
arXiv:2609.13335v1 Announce Type: cross Abstract: Large Language Models (LLMs) have enabled more natural human-robot interaction, but open-source models often exhibit unstable long-horizon reasoning a
arXiv:2609.15803v1 Announce Type: cross Abstract: Long-running AI agents create a control problem: each action they take changes the state, which in turn affects the trajectory of future actions. If t
arXiv:2609.15422v1 Announce Type: new Abstract: AI agents are provisioned the same as employee-owned hosts in many enterprise settings with a static credential set fixed at deployment which includes a
arXiv:2609.14422v1 Announce Type: new Abstract: Agentic Network Operations (NetOps) are an emerging paradigm promising to enable workload-aware, self-adjustable, and reliable autonomous networks. Whil
arXiv:2609.13582v1 Announce Type: cross Abstract: A clinical agent benchmark can report the same verdict on identical inputs while the agent files a materially different order on each run. Such agents
arXiv:2609.12655v1 Announce Type: new Abstract: Large language model agents are expected to continuously adapt to new tasks and environments over their lifetime by reusing past experience. However, ex
arXiv:2609.11318v1 Announce Type: new Abstract: Deep research agents are increasingly capable of web search, tool use, multimodal evidence analysis, and information synthesis. However, existing benchm
arXiv:2609.09849v1 Announce Type: cross Abstract: In recent years, AI agents have evolved into capable assistants that carry out multi-step tasks in digital environments. The network systems community
arXiv:2609.10892v1 Announce Type: cross Abstract: When an indirect prompt injection succeeds against an LLM agent, the compromise is visible in the agent's own behavior: a benign prefix of tool calls,
arXiv:2609.09395v1 Announce Type: new Abstract: Language models act through tools, yet practical agents face libraries containing thousands of interfaces. We introduce the tool menu as the short, orde
arXiv:2609.08944v1 Announce Type: new Abstract: Agent skills provide a lightweight way to equip frozen language-model agents with domain knowledge and procedural guidance, yet obtaining high-quality s
arXiv:2609.04556v1 Announce Type: new Abstract: Runtime traces are becoming a central substrate for understanding agentic systems, yet interpretation has focused largely on what the agent did. Workpla
Super interesting paper on proactive agents from Google DeepMind. (bookmark it) Proactive assistance usually means autocomplete. Researchers asks what it looks like when an agent offers higher-level c
Having launched an artificial intelligence-based virtual assistant in the spring, Experian plc is driving AI deeper into its operations with a commercial agent-based platform designed to bring its ris
arXiv:2606.21144v2 Announce Type: replace-cross Abstract: Long-term memory systems allow LLM agents to preserve information beyond a single context window, but most systems focus on storing and retrie
Artificial intelligence agent security startup AIR Security Inc. formally launched today with 50 million in funding to build what it calls an inline firewall for AI agents. Founded earlier this year,
arXiv:2609.00296v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly proposed for healthcare tasks such as clinical documentation, evidence retrieval, patient messaging,
arXiv:2608.30147v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly deployed in long-horizon, interactive, and stateful environments. In these settings, a single wrong a
arXiv:2608.30730v1 Announce Type: cross Abstract: Long-horizon agentic tasks go beyond chaining short tasks over more interaction turns. Their evolving dynamic environments and long-range dependencies
arXiv:2608.29309v1 Announce Type: cross Abstract: This work provides an overview of the different strategies that can be used to evaluate the performance of AI models and agents based on large languag
arXiv:2606.13120v2 Announce Type: replace Abstract: Search Agents -- large language models augmented with search tools -- have intensified the need for future-proof evaluation benchmarks. Existing ben
arXiv:2608.31022v1 Announce Type: new Abstract: AI agents in partially observable environments need to coordinate active sensing with working memory to maintain an evolving perceptual state. However,
arXiv:2608.29889v1 Announce Type: new Abstract: Programming with AI is increasingly agentic, users prompt LLMs to directly edit their code and review the changes, with adoption growing especially for
arXiv:2608.28062v2 Announce Type: replace Abstract: Multimodal search agents extend parametric knowledge with newly emerging and long-tail evidence from the open web. Yet many existing agentic search
// Memory is what breaks long-horizon agents // It's undeniable how important memory/recall is for long-horizon tasks. If you are building for long-horizon tasks, this is a great read. (bookmark it) T
arXiv:2608.27167v1 Announce Type: new Abstract: An LLM agent shown a professional-looking market panel commits to a directional call on a provably unpredictable question far more often than one asked
The internet connected billions of people and mobile devices, putting computers in every hand. Now, we’re in the middle of the next big technology shift, deploying millions of autonomous AI agents to
arXiv:2608.20566v1 Announce Type: new Abstract: AI agents extend large language models from single prompt-response interactions to long-running, goaldirected workflows that issue many model calls, inv
arXiv:2607.21596v2 Announce Type: replace Abstract: Large language model agents can adapt to complex tasks by constructing workflows at inference time, but procedures discovered in one episode are usu
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
Big-data company Cloudera Inc. says it’s going to eliminate the headaches and hassles that have slowed enterprise’s efforts to adopt artificial intelligence with today’s launch of its new Cloudera Any
arXiv:2608.17075v1 Announce Type: cross Abstract: Next-encounter ICD forecasting predicts which standardized diagnosis codes will be documented at a future visit from the longitudinal record available
'Agents = model + harness + context' is a much better mental model than treating the LLM as the entire product. The model provides capability, but the harness determines tools, permissions and behavio
arXiv:2608.12428v1 Announce Type: new Abstract: Memory is a core component of AI agents, enabling them to accumulate experience, maintain personalization, and adapt over long-term interactions. Howeve
Enterprise voice artificial intelligence company Regal Voice Inc. today unveiled an integration with Five9 Inc. that makes its autonomous AI voice agents available to customers of the contact center s
arXiv:2608.11246v1 Announce Type: new Abstract: The success of coding agents has established the harness as a paradigm: what an agent achieves depends not on the model alone, but on the infrastructure
Business and technology leaders need no convincing that the time of agentic AI is here. Organizations are rapidly adopting agents, and few executives doubt the technology’s potential to transform work
arXiv:2603.02637v2 Announce Type: replace-cross Abstract: Modern machine learning (ML) workloads increasingly rely on GPUs, yet achieving high end-to-end performance remains challenging due to depende
arXiv:2607.26393v1 Announce Type: new Abstract: Social deduction games (SDGs) such as Werewolf have become challenging testbeds for AI agents. These games require complex social skills such as reasoni
As your AI agents move from prototype to production, the challenge shifts from getting them to work to keeping them fast and efficient. Learn how to use Amazon Bedrock AgentCore Observability and Amaz
Enterprise data pipeline startup DataBahn Inc. today revealed that it has raised 40 million in new funding to accelerate development of what it calls an agentic data control plane. Founded in 2024, Da
arXiv:2607.22711v1 Announce Type: cross Abstract: LLM coding agents operate by constructing trajectories that accumulate reasoning, tool calls, and results to enable multi-step decision-making. Howeve