Search: “agents”

arXiv:2606.26924v1 Announce Type: cross Abstract: LLM coding harnesses grant agents broad file and shell access, yet the configuration layer that steers them -- rules files, agent definitions, IDE-spe

arXiv:2602.08222v2 Announce Type: replace Abstract: As post-training optimization becomes central to improving large language models, we observe a persistent saturation bottleneck: once models grow hi

arXiv:2603.26233v2 Announce Type: replace Abstract: As Large Language Model (LLM) agents are increasingly deployed in open-ended domains like software engineering, they frequently encounter underspeci

arXiv:2606.05872v1 Announce Type: cross Abstract: AI agents are commonly evaluated using task success, reward, latency, and cost. These metrics are useful, but they often miss important aspects of age

arXiv:2606.04555v1 Announce Type: cross Abstract: Long-horizon conversational agents need to interact with users through evolving events, tasks, and goals. Such histories are naturally temporal, yet m

arXiv:2606.02965v1 Announce Type: new Abstract: Benchmarks for autonomous agents measure whether agents complete tasks, yet this framing is systematically blind to whether an agent should have proceed

arXiv:2605.26203v1 Announce Type: cross Abstract: The success of deployed agents relies on their ability to handle open-ended user requests using their inherent capabilities, not only in solving reque

arXiv:2605.27073v1 Announce Type: new Abstract: Adaptive orchestration of heterogeneous agents requires making sequential delegation decisions under uncertain and evolving agent behaviour, e.g., coord

arXiv:2605.17721v1 Announce Type: new Abstract: Large language model (LLM)-based agents have demonstrated strong capabilities in complex reasoning and problem solving through multi-step interactions,

arXiv:2605.13527v1 Announce Type: new Abstract: Reusable skills have become a core substrate for improving agent capabilities, yet most existing skill packages encode reusable behavior primarily as te

arXiv:2605.09315v1 Announce Type: new Abstract: Recent advances in LLM agents enable systems that autonomously refine workflows, accumulate reusable skills, self-train their underlying models, and mai

arXiv:2605.10907v1 Announce Type: cross Abstract: The dominant paradigm for AI agents is an 'on-the-fly' loop in which agents synthesize plans and execute actions within seconds or minutes in response

arXiv:2605.08013v1 Announce Type: new Abstract: Command line interface (CLI) agents are emerging as a practical paradigm for agent-computer interaction over evolving filesystems, executable command li

arXiv:2605.03782v1 Announce Type: new Abstract: To navigate partially observable visual environments, recent VLM agents increasingly internalize world modeling capabilities into their policies via exp

arXiv:2604.21190v1 Announce Type: new Abstract: Understanding visual scenes requires not only recognizing objects but also reasoning about their spatial relationships. Unlike general vision-language t

arXiv:2509.06477v2 Announce Type: replace Abstract: Shortcuts such as APIs and deep-links have emerged as efficient complements to flexible GUI operations, fostering a promising hybrid paradigm for ML

arXiv:2604.13242v1 Announce Type: cross Abstract: Large language models (LLMs), particularly when integrated into agentic systems, have demonstrated human- and even superhuman-level performance across

arXiv:2604.10290v1 Announce Type: new Abstract: AI is increasingly deployed in multi-agent systems; however, most research considers only the behavior of individual models. We experimentally show that

arXiv:2603.05744v2 Announce Type: replace Abstract: Current AI-powered code assistance tools often struggle with poorly-defined problem statements that lack sufficient task context and requirements sp

arXiv:2604.06284v1 Announce Type: cross Abstract: Autonomous AI agents powered by Large Language Models can reason, plan, and execute complex tasks, but their ability to autonomously retrieve informat

arXiv:2604.07036v1 Announce Type: cross Abstract: Recently, LLM-based agents have become increasingly popular across many applications, including complex sequential decision-making problems. However,

arXiv:2610.18457v1 Announce Type: cross Abstract: Large language model (LLM) agents are becoming an integral part of the software development lifecycle, and the capabilities granted to them allow an a

arXiv:2610.14157v1 Announce Type: cross Abstract: We introduce OpenMobile-2, a near-frontier mobile agent with fully open training environments and recipes. We make three key advances: (1) Diverse env

arXiv:2610.12823v1 Announce Type: new Abstract: Web agents increasingly browse, interpret, and act on web content on behalf of users. In many realistic workflows, however, the visual evidence they con

arXiv:2610.10179v1 Announce Type: new Abstract: Search agents enable Large Language Models (LLMs) to iteratively retrieve and use information for complex multi-hop questions. Reinforcement Learning wi

arXiv:2610.06966v1 Announce Type: cross Abstract: Indirect prompt injection (IPI) hides adversarial instructions in content that large language model (LLM) agents read at runtime. As agents compose he

arXiv:2610.07816v1 Announce Type: new Abstract: Small language models (SLMs) are attractive as local agent controllers because they reduce remote inference, latency, and deployment footprint, yet stru

arXiv:2606.15034v2 Announce Type: replace Abstract: Computer-use agents can complete benign user instructions while violating important constraints of the user's environment. We introduce OSGuard, a d

arXiv:2610.05303v1 Announce Type: new Abstract: A large language model (LLM) agent solves long-horizon tasks through many reasoning-action turns, with one verification signal at termination. Deployed

arXiv:2610.04517v1 Announce Type: cross Abstract: Deep time-series forecasting models have rapidly diversified, yet adapting them to a specific task still requires extensive expert effort in model sel

arXiv:2610.06401v1 Announce Type: cross Abstract: Tool-using language-model agents are vulnerable to indirect prompt injection because they must act on untrusted external content. Existing training-ti

arXiv:2610.03014v1 Announce Type: cross Abstract: Large language model (LLM)-based agents increasingly connect model-generated decisions to security-sensitive software capabilities such as command exe

arXiv:2608.01772v2 Announce Type: replace Abstract: LLM agents increasingly run policy-bound enterprise workflows, where they must apply rules consistently and stay auditable. Deploying such an agent

arXiv:2610.01097v1 Announce Type: new Abstract: End-to-end research agents can now produce complete scientific papers, yet manuscript claims often diverge from executed experiments. This gap is struct

arXiv:2609.38411v1 Announce Type: new Abstract: Leading AI developers have reported agents acting beyond their approved limits, which a United Nations panel described as an early warning of loss of hu

arXiv:2609.38288v1 Announce Type: new Abstract: We present AREX-2, an effort to advance the self-improving capability of LLM agents, which we define as the ability to iteratively refine a solution at

arXiv:2609.39081v1 Announce Type: cross Abstract: We spent five weeks using an LLM coding agent on open problems in coding theory: finding large sets of four-letter words, such as DNA barcodes, that s

arXiv:2609.40284v1 Announce Type: cross Abstract: Computer use agents (CUAs), which use graphical user interfaces (GUIs) to complete tasks on a computer, have recently surpassed human performance on m

arXiv:2609.39352v1 Announce Type: cross Abstract: LLM agents increasingly rely on reusable Skills for complex, multi-step tasks, creating a critical supply-chain attack surface where poisoned Skill co

arXiv:2609.39765v1 Announce Type: new Abstract: Agent memory faces heterogeneous access needs: a single-hop question may require one piece of evidence, whereas a multi-hop question must combine eviden

arXiv:2609.39903v1 Announce Type: new Abstract: Scientific software presents a demanding test for computer-using agents based on visual language models (VLMs): completing a research workflow requires

arXiv:2609.39149v1 Announce Type: new Abstract: Textual skills enable large language model (LLM) based agents to accumulate reusable procedural knowledge without updating model parameters. Yet existin

arXiv:2609.38201v1 Announce Type: new Abstract: Long-running tools can dominate coding-agent latency: compilers, test suites, and repository commands take seconds to minutes while the agent idles. Thi

arXiv:2609.34210v1 Announce Type: new Abstract: Coding agents are beginning to move beyond purely digital tasks to tackle physical-world challenges, particularly in robotics. Existing robotics benchma

arXiv:2609.30604v1 Announce Type: cross Abstract: Existing computer-use agent benchmarks do not fully evaluate agents acting as assistants. A useful assistant retrieves information across complex, mul

arXiv:2609.30137v1 Announce Type: new Abstract: Customer experience (CX) agents use tools and large language models to address customer requests and guide conversational interactions with an organizat