Search: “agents”

arXiv:2610.13494v1 Announce Type: new Abstract: Existing LLM-based agent approaches for long-horizon machine learning engineering (MLE) often use context engineering, implemented through custom harnes

arXiv:2608.20195v1 Announce Type: cross Abstract: Technical documentation is written for human developers, but an increasing share of software changes is now authored by autonomous coding agents. Whic

arXiv:2604.10547v1 Announce Type: new Abstract: We introduce Agent^2 RL-Bench, a benchmark for evaluating agentic RL post-training -- whether LLM agents can autonomously design, implement, and run com

arXiv:2608.09934v1 Announce Type: cross Abstract: Large language model (LLM) agents improve task performance by decomposing problems into role-specialized behaviors. However, their practical deploymen

arXiv:2610.04836v1 Announce Type: new Abstract: Remote sensing agents rely on perception, measurement, and raster analysis tools to solve Earth observation tasks. We refer to their judgments and quant

arXiv:2609.39065v1 Announce Type: cross Abstract: LLM agents increasingly rely on installable skills, which are packages of instructions, code, and resources that equip them with task-specific capabil

arXiv:2608.30478v1 Announce Type: new Abstract: Cognitive language agents have achieved substantial progress by equipping language models with memory, tools, and decision-making procedures, enabling a

arXiv:2608.26626v1 Announce Type: cross Abstract: This report presents a framework to help organisations, policymakers and researchers reason about the risks that emerge when AI agents interact with e

arXiv:2604.28043v1 Announce Type: new Abstract: We present Collaborative Agent Reasoning Engineering (CARE), a disciplined methodology for engineering Large Language Model (LLM) agents in scientific d

arXiv:2609.11060v1 Announce Type: new Abstract: Persistent memory is entering production-oriented agent platforms to help long-horizon agents accumulate experience across sessions. Yet a post-task cur

arXiv:2607.25816v1 Announce Type: new Abstract: Large language model agents often spend substantial wall-clock time waiting for tool call results. Tool-call speculation can hide this latency by predic

arXiv:2509.21842v2 Announce Type: replace Abstract: Travel planning (TP) agent has recently worked as an emerging building block to interact with external tools/resources for travel itinerary generati

arXiv:2603.16663v5 Announce Type: replace-cross Abstract: The AIED community envisions AI evolving 'from tools to teammates,' yet most research still examines AI agents primarily through one-on-one hu

arXiv:2604.15840v1 Announce Type: new Abstract: Reinforcement learning for LLM agents is typically conducted on a static data distribution, which fails to adapt to the agent's evolving behavior and le

arXiv:2609.07131v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly achieve long-horizon tasks by combining foundation models with explicit skills and implicit procedural

arXiv:2608.04066v1 Announce Type: new Abstract: How do you verify a long-horizon agent when its own state and self-reports are exactly what you cannot trust? We present an agent instrument built so th

arXiv:2607.15715v2 Announce Type: replace Abstract: Large language model (LLM) agents are increasingly used for complex information-extraction tasks, yet it remains unclear whether agentic components

arXiv:2607.05120v1 Announce Type: cross Abstract: AI agents act on behalf of user prompts, consuming external data and taking actions based on the agent context. Prior research on AI agent security ha

arXiv:2606.31229v1 Announce Type: new Abstract: Ideation plays a pivotal role in scientific discovery. Recent LLM, especially AI Scientist systems, show promising potential for automated ideation. How

arXiv:2604.22750v1 Announce Type: new Abstract: The wide adoption of AI agents in complex human workflows is driving rapid growth in LLM token consumption. When agents are deployed on tasks that requi

arXiv:2604.17609v1 Announce Type: new Abstract: LLM-based agents are assumed to integrate environmental observations into their reasoning: discovering highly relevant but unexpected information should

arXiv:2610.13361v1 Announce Type: cross Abstract: As the production of software passes into the hands of software itself, coding agents are increasingly commissioned to build agents fitted to their us

arXiv:2610.01618v1 Announce Type: new Abstract: Agent evaluations increasingly go beyond a single success rate, reporting metrics such as cost, consistency, and robustness. Yet they typically treat th

arXiv:2609.36730v1 Announce Type: new Abstract: Agents increasingly build on code written by other agents, and they reimplement rather than reuse, growing the codebases later agents must work in. To m

arXiv:2608.27260v1 Announce Type: new Abstract: LLM agents increasingly rely on generated interaction data to learn how to interact with external environments. Agentic data generation must maintain co

arXiv:2608.18104v1 Announce Type: new Abstract: Large language model (LLM)-based agents are increasingly becoming self-evolving systems that persist across interactions, maintain memories, use tools,

arXiv:2607.19595v1 Announce Type: cross Abstract: Large language model (LLM) agents are vulnerable to security risks, such as prompt injection attacks from untrusted context that manipulate downstream

arXiv:2606.04455v1 Announce Type: new Abstract: Current AI benchmarks evaluate agents on task execution within human-designed workflows. These evaluations fundamentally fail to measure a critical next

arXiv:2507.10644v4 Announce Type: replace Abstract: The Web of Agents (WoA) transforms the document-centric Web into an environment of autonomous agents acting on users' behalf, a vision newly tractab

arXiv:2605.08828v1 Announce Type: new Abstract: Large language model agents increasingly operate through environment-facing scaffolds that expose files, web pages, APIs, and logs. These observations i

arXiv:2607.12254v1 Announce Type: new Abstract: Large language model (LLM) agents can increasingly plan, use tools, maintain memory, and execute long-horizon tasks. These advances motivate two linked

arXiv:2602.04284v2 Announce Type: replace Abstract: Managing agent context (e.g., thought and observation) during multi-turn agent-environment interactions is an emerging strategy to improve agent eff

arXiv:2604.27882v1 Announce Type: new Abstract: Recent advances in agentic AI are shifting automation from discrete tools to proactive multi-agent systems that coordinate multi-specialized capabilitie

arXiv:2608.10915v1 Announce Type: new Abstract: After an older adult misses a medication dose, a software agent can send another reminder and an embodied agent can bring the medication. Yet neither ex

arXiv:2607.13718v1 Announce Type: cross Abstract: As AI agents gain prevalance, users are increasingly exposed to the risks such systems entail. Prompt injection attacks, as well as hallucination, can

arXiv:2605.16035v1 Announce Type: cross Abstract: AI agents are increasingly deployed to act autonomously in the world, yet there is still no reliable way to trace a harmful agent back to the account

arXiv:2508.00414v3 Announce Type: replace Abstract: General AI Agents are increasingly recognized as foundational frameworks for the next generation of artificial intelligence, enabling complex reason

arXiv:2610.13092v1 Announce Type: new Abstract: AI agents depend on repeated decisions to accomplish tasks, with large language models (LLMs) commonly serving as their core decision makers. The recent

arXiv:2609.03438v1 Announce Type: new Abstract: Graphical user interface (GUI) agents are increasingly used to execute natural-language instructions on user interfaces, yet real users may issue infeas

arXiv:2608.26237v1 Announce Type: cross Abstract: Capture-the-Flag (CTF) benchmarks are widely used to assess the offensive security capabilities of autonomous language-model agents. Evaluations rely

arXiv:2606.07867v2 Announce Type: replace Abstract: Are tool-calling LLM agents equally safe throughout a conversation? We discover they are not: agents are most vulnerable at the very start of a sess

arXiv:2608.15403v1 Announce Type: cross Abstract: You will die eventually. Your agents may not. An AI agent operating on decentralized blockchain infrastructure has no concept of death; it can only go

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:2607.26637v1 Announce Type: new Abstract: Deployed LLM agents increasingly keep their long-term memory as a filesystem: a directory tree of markdown files that the agent itself reads, writes, an

arXiv:2510.04452v3 Announce Type: replace-cross Abstract: Computer use agents (or 'agents') are generative AI that automates actions within user interfaces from user commands. Current research focuses

arXiv:2607.13157v1 Announce Type: new Abstract: Agent memory is a systems problem for long-horizon agents. Practical deployments require retention of task state across extended conversations, recovery