Knowledge catalogue
arXiv:2608.04053v1 Announce Type: cross Abstract: Prompt injection remains a critical threat to LLM agents, yet existing defenses treat each task as a self-contained problem, independent of previous e
Temporal policies in Amazon Bedrock AgentCore let you define stateful rules that evaluate authorization based on an agent's session history. Learn how to enforce workflow sequencing, prevent data fabr
arXiv:2608.03502v1 Announce Type: new Abstract: Large Language Models (LLMs) have recently shown strong capabilities in reasoning, planning, and tool-use, enabling new forms of autonomous agents. Howe
arXiv:2608.03403v1 Announce Type: new Abstract: The performance bottleneck of agents is increasingly shifting from model capability to the robustness of their execution processes. Tools play a central
Learn how Arize Signal turns production traces into ranked issues, proposed fixes, regression datasets, and reviewable pull requests for AI agents. The post How to debug production AI agents with Sign
arXiv:2608.01347v1 Announce Type: new Abstract: Large reasoning models used as coding agents incur costs from deliberation, tool calls, and repeated agent turns, yet the causal effect of prompt wordin
arXiv:2607.29626v1 Announce Type: new Abstract: As LLMs evolve from code completion systems into autonomous scientific agents, evaluating their ability to conduct experiments has become increasingly i
arXiv:2607.19338v2 Announce Type: replace Abstract: Coding agents increasingly operate in executable environments where a failed attempt produces actionable feedback rather than merely an incorrect an
arXiv:2607.29320v1 Announce Type: new Abstract: Graphical user interface (GUI) agents based on large language models are increasingly deployed across mobile, web, and desktop environments. However, ex
arXiv:2607.28037v1 Announce Type: new Abstract: As LLM-based agents are deployed in complex, multi-step workflows, a critical evaluation gap has emerged: most existing benchmarks judge only final outc
arXiv:2607.26367v1 Announce Type: new Abstract: An important skill in theoretical physics is to recognize when a new problem can be transformed into a known model. We study this skill as an AI-agent t
arXiv:2607.27690v1 Announce Type: new Abstract: We introduce LabEvolver, a training-free framework that equips safe and grounded wet-lab agents with episodic memory from execution experience. LabEvolv
arXiv:2607.26300v1 Announce Type: new Abstract: AI agents are increasingly adept at tackling complex, long-running tasks. With the rapid surge of autonomous capabilities, human oversight is systematic
arXiv:2607.26998v1 Announce Type: cross Abstract: Large language model (LLM) agents automate penetration testing through an observation-action loop, selecting actions based on observations returned by
Computer-use AI agents struggle with multi-step workflows like email and customer support. Echoverse trains agents in realistic environments rather than simply providing more training tasks, helping t
NVIDIA’s AI Red Team found common failure modes in enterprise AI agents: weak access controls, unrestricted code execution via tools, unprotected network egress, and exposure of plaintext secrets. The
arXiv:2607.25718v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly rely on invoking external tools to complete real-world tasks. Tool retrieval, which selects a small tas
arXiv:2607.22688v1 Announce Type: new Abstract: Post-training agents for automated AI research requires optimizing not only model parameters, but also the runtime harness that shapes how research traj
arXiv:2607.23722v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed as agents that interact with stateful environments over multiple steps: gathering hidden informat
arXiv:2607.24097v1 Announce Type: new Abstract: Memory-augmented LLM agents typically answer queries by retrieving relevant memories and feeding them directly to an answer model. This retrieval-as-evi
arXiv:2607.24588v1 Announce Type: new Abstract: Early warning of extreme weather is essential for mitigating the societal, economic, and environmental risks posed by hazardous weather events. However,
arXiv:2607.22165v1 Announce Type: cross Abstract: LLM-based database agents show promise, but differing task scopes, testbeds, and metrics hinder comparison. We identify four gaps between evaluation a
arXiv:2607.21887v1 Announce Type: cross Abstract: Foreign language anxiety (FLA) can be a major barrier to second language acquisition (SLA), especially in conversational contexts. With the proliferat
arXiv:2607.20468v1 Announce Type: new Abstract: AI agents are increasingly used to automate research and development tasks, yet existing benchmarks typically evaluate them on prescribed workflows or n
Enterprise AI ambition is far outpacing the readiness of the enterprise AI stack, and the growing rift between proof-of-concept deployments and production-scale agent operations is where most organiza
arXiv:2607.21557v1 Announce Type: new Abstract: Modern AI agents rely on elaborate inference harnesses such as Claude Code, Codex, and OpenClaw to drive multi-turn reasoning, tool use, and access to e
arXiv:2601.06487v3 Announce Type: replace-cross Abstract: Reinforcement learning has substantially improved the performance of LLM agents on tasks with verifiable outcomes, but it still struggles on o
Apple ML shows LLM world-model simulation can generate API-agent training trajectories from specs alone—no executable environments required.
With more agents comes more complexity — an issue Temporal Technologies Inc. aims to address. Founded in 2019, Temporal offers an open-source durable execution platform that ensures artificial intelli
arXiv:2607.13085v1 Announce Type: cross Abstract: Recent autonomous penetration testing papers report high benchmark scores while adding multi-component security harnesses around frontier LLMs. Becaus
arXiv:2601.12349v3 Announce Type: replace-cross Abstract: Large multimodal model powered GUI agents are emerging as high-privilege operators on mobile platforms, entrusted to perceive screen content a
arXiv:2607.12680v1 Announce Type: new Abstract: Existing vision-language navigation methods often couple a VLM with waypoint decoders to produce multi-step action plans, but they typically lack an exp
arXiv:2607.07753v1 Announce Type: cross Abstract: Modelling psychological disorders in artificial agents offers both a testbed for computational psychiatry and a lens on the failure modes of affective
OpenSWE is one of our most widely used agents throughout the company. Since July 1st it's been tagged over 700 times in Slack! This doesn't even count the reviewer agent, tagging it in GitHub, or tagg
arXiv:2601.02871v3 Announce Type: replace Abstract: Task-oriented proactive dialogue agents play a pivotal role in recruitment, particularly for steering conversations towards specific business outcom
arXiv:2607.08681v1 Announce Type: new Abstract: As agentic AI systems are increasingly applied to cyber-physical environments, their evaluation requires assessment of both task performance and trustwo
arXiv:2607.05174v1 Announce Type: new Abstract: Language agents, i.e., LLM agents, progress rapidly and are increasingly deployed in production environments. This trend underscores the urgent need for
arXiv:2607.03162v1 Announce Type: new Abstract: LLM-powered agents struggle with personalization when users issue raw, underspecified queries. In this setting, agents must infer latent intent, extract
arXiv:2607.05378v1 Announce Type: new Abstract: Long-horizon agentic LLMs are increasingly limited by finite context windows, as extended interaction trajectories can exceed the maximum context length
deepagents is our newest open source project - an open source, model agnostic agent harness this is maybe the most important academy course we've launched 🎓 New course launch from LangChain Academy: I
arXiv:2607.04334v1 Announce Type: new Abstract: Multimodal GUI agents read an interface through two redundant channels: the rendered pixels of a screenshot and a serialized structure such as a DOM or
arXiv:2607.02975v1 Announce Type: new Abstract: Effective agency in social environments depends on when an agent seeks knowledge, when it acts, and whether its actions are justified by acquired inform
arXiv:2607.04617v1 Announce Type: new Abstract: Long-lived AI agents require continuity across interactions, but continuity cannot be obtained by simply extending the prompt window. An agent must pres
arXiv:2607.03726v1 Announce Type: new Abstract: While current AI agents support increasingly long context windows, tool use, and skill execution for long-horizon tasks, they still require memory syste
arXiv:2607.02814v1 Announce Type: cross Abstract: Personal agents will increasingly negotiate on behalf of users: splitting costs with other personal agents, appealing platform decisions, escalating s
arXiv:2607.05277v1 Announce Type: cross Abstract: Defenses that provide security guarantees against prompt injection attacks rely on strict isolation between trusted instructions and untrusted data. I
arXiv:2607.05189v1 Announce Type: cross Abstract: Persistent personal agents combine long-term memory with access to users' external environments, enabling personalized foreground assistance and proac
Andrew Qu from Vercel discusses how AI agents represent a fundamentally different category of software compared to traditional applications, exploring their unique characteristics and implications for
arXiv:2603.08316v3 Announce Type: replace-cross Abstract: Modern vision-language-model (VLM) based graphical user interface (GUI) agents are expected not only to execute actions accurately but also to
arXiv:2606.30863v1 Announce Type: new Abstract: Agents typically assume an expert user -- one with well-formed preferences about what they want -- and default to clarifying questions whenever the task
Code-writing AI agents can solve complex problems more effectively than agents using other approaches, but deploying them requires executing potentially untrusted generated code within sandboxed or is
arXiv:2601.20334v2 Announce Type: replace-cross Abstract: Robotic manipulation has increasingly adopted vision-language-action (VLA) models, which achieve strong performance but typically require task
This post likely discusses how to evaluate AI agents built with LangChain using Harbor, a tool for testing and monitoring. It covers practical approaches for assessing agent performance, reliability,
arXiv:2606.29823v1 Announce Type: cross Abstract: The database community has repeatedly advanced the state of the art by recognizing that new workloads demand new system architectures. We argue that l
arXiv:2603.02491v3 Announce Type: replace-cross Abstract: As artificial agents become increasingly capable, what internal structure is necessary for an agent to act competently under uncertainty? Clas
Mike Wheatley / SiliconANGLE: Baz releases Baz Planner, which uses four specialized AI agents to analyze code at the planning stage, and extends its seed funding by 9M to 17M — Agentic coding startup
In this post, you learn how to debug production agent failures using built-in observability capabilities. We walk through common failure patterns, show how to analyze agent behavior with traces and me
i've been using cursor mobile on the go for the last weeks, and having access to all cloud agents from everywhere is really nice go on a walk, get an idea, dictate it in the app come back from walk to
💪deep agents harness The AI SDK Harness API now supports @OpenCode and @LangChain Deep Agents through a single unified interface. Use 𝙷𝚊𝚛𝚗𝚎𝚜𝚜𝙰𝚐𝚎𝚗𝚝 to run any supported runtime without changing your ap
arXiv:2606.26294v1 Announce Type: cross Abstract: Self-improving agents are state-of-the-art (SOTA) on agentic coding benchmarks and have recently been extended to general domains. However, their sear