Search: “agents”

arXiv:2511.14584v3 Announce Type: replace-cross Abstract: We present ReflexGrad, a dual-process architecture for within-episode failure recovery in LLM agents without demonstrations. When agents commi

arXiv:2605.28003v1 Announce Type: new Abstract: The frontier of mathematics is defined by problems whose solutions are not yet known, yet it remains unclear whether language models can meaningfully en

arXiv:2605.27881v1 Announce Type: new Abstract: Search agents powered by large language models can autonomously decompose queries, retrieve information, and synthesize answers through multi-step reaso

arXiv:2605.28122v1 Announce Type: cross Abstract: A coding agent executes a benign task as a sequence of shell, file, and network actions, any of which can quietly exceed the authorized scope while th

arXiv:2605.27690v1 Announce Type: new Abstract: LLM agents increasingly operate through multi-turn tool use and environment interaction, where safety risks often emerge from intermediate steps long be

arXiv:2605.26542v1 Announce Type: cross Abstract: Tool-using agents increasingly operate in open-ended deployment environments, where they compose file systems, web APIs, code interpreters, and enterp

arXiv:2605.27333v1 Announce Type: new Abstract: Finance LLM agents must simultaneously block prompt-induced unauthorized actions and approve legitimate multi-step business workflows. However, boundary

arXiv:2605.27360v1 Announce Type: cross Abstract: Cellular research and development (R&D) is throttled by six structural processes that each consume months of manual engineering work per iteration: (i

arXiv:2605.26546v1 Announce Type: new Abstract: Mobile graphical user interface (GUI) agents enable AI models to autonomously operate smartphones on behalf of users. However, most existing systems foc

arXiv:2605.26186v1 Announce Type: cross Abstract: Functionality-correct repository setup aims to configure execution environments (e.g., dependencies, build scripts) to successfully execute a reposito

arXiv:2510.17790v3 Announce Type: replace-cross Abstract: Computer-use agents face a fundamental limitation. They rely exclusively on primitive GUI actions (click, type, scroll), creating brittle exec

arXiv:2605.25971v1 Announce Type: new Abstract: While AI agents demonstrate remarkable capabilities in reasoning and tool use, they remain fundamentally reactive: they compute responses only after exp

arXiv:2605.25200v1 Announce Type: new Abstract: Travel planning is a realistic task for evaluating the planning and tool-use abilities of LLM agents. However, existing benchmarks typically assume only

arXiv:2605.24598v1 Announce Type: new Abstract: Large language model (LLM) agents excel at solving complex long-horizon tasks through autonomous interaction with environments. However, their real-worl

arXiv:2605.24659v1 Announce Type: new Abstract: LLM-based agents are increasingly deployed for complex tasks requiring planning, tool use, and interaction with external services. Their reliance on unt

arXiv:2508.15760v2 Announce Type: replace-cross Abstract: Tool calling has emerged as a critical capability for AI agents. In contrast to conventional tool calling frameworks that rely on static, prov

arXiv:2605.21605v1 Announce Type: new Abstract: Open-ended image generation is no longer a simple prompt-to-image problem. High-quality generation often requires an agent to combine a model's internal

arXiv:2605.20251v2 Announce Type: cross Abstract: Existing benchmarks for LLM coding agents primarily evaluate final outcomes. While useful for measuring overall capability, these metrics provide limi

arXiv:2603.01712v2 Announce Type: replace-cross Abstract: Fine-tuning large language models for vertical domains remains labor-intensive, requiring practitioners to curate data, configure training, an

arXiv:2605.19722v1 Announce Type: cross Abstract: Do stock safety-aligned language models and their uncensored or abliterated derivatives behave differently when run as autonomous security agents? Sin

arXiv:2605.17634v1 Announce Type: cross Abstract: Prompt injection is the most critical vulnerability in deployed AI agents. Despite recent progress, we show that the prevailing defense paradigm (data

arXiv:2605.18572v1 Announce Type: new Abstract: Persuasive dialogue generation plays a vital role in decision-making, negotiation, counseling, and behavior change, yet it remains a challenging problem

arXiv:2605.16746v1 Announce Type: new Abstract: LLM agents increasingly rely on persistent state, including transcripts, summaries, retrieved context, and memory buffers, to support long-horizon inter

arXiv:2502.13957v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are transforming web search by shifting from document ranking to synthesizing answers, and are increasingly deplo

arXiv:2605.16282v1 Announce Type: cross Abstract: The rapid deployment of LLM-based autonomous agents has introduced safety risks that extend far beyond traditional LLM concerns, prompting a prolifera

arXiv:2601.17887v2 Announce Type: replace Abstract: Long-term memory enables large language model (LLM) agents to support personalized and sustained interactions. However, most work on personalized ag

arXiv:2605.16217v1 Announce Type: cross Abstract: Deep research agents have achieved remarkable progress on complex information seeking tasks. Even long ReAct style rollouts explore only a single traj

arXiv:2512.00417v5 Announce Type: replace Abstract: This paper introduces CryptoBench, the first expert-curated, dynamic benchmark designed to rigorously evaluate the real-world capabilities of Large

arXiv:2605.15777v1 Announce Type: new Abstract: Computer-Using Agents (CUAs) are rapidly extending large language models (LLMs) beyond text-based reasoning toward action execution in more complex envi

arXiv:2505.11708v3 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) agents are increasingly used to simulate sophisticated cyberattacks, but their decision-making processes remain op

arXiv:2605.15188v1 Announce Type: cross Abstract: AI agents are being increasingly deployed in dynamic, open-ended environments that require adapting to new information as it arrives. To efficiently m

arXiv:2605.13909v1 Announce Type: cross Abstract: Negotiation is a central mechanism of economic exchange, shaping markets, procurement, labor agreements, and resource allocation. It is also a canonic

arXiv:2601.18842v3 Announce Type: replace-cross Abstract: As GUI agents increasingly rely on screenshots to perceive and operate digital environments, they may inadvertently expose sensitive informati

arXiv:2603.24649v2 Announce Type: replace Abstract: Medical imaging benchmarks often evaluate VLMs on pre-selected 2D images, slices, crops, or patches, making evaluation closer to visual recognition.

arXiv:2605.13391v1 Announce Type: new Abstract: The rise of multi-modal large language models (MLLMs) is shifting remote sensing (RS) intelligence from 'see' to 'action', as OpenClaw-style frameworks

arXiv:2508.07642v3 Announce Type: replace-cross Abstract: Vision-and-Language Navigation (VLN) poses significant challenges for agents to interpret natural language instructions and navigate complex 3

arXiv:2605.12039v1 Announce Type: new Abstract: Skill libraries enable large language model agents to reuse experience from past interactions, but most existing libraries store skills as isolated entr

arXiv:2605.10787v1 Announce Type: new Abstract: Current LLM agents are proficient at calling isolated APIs but struggle with the 'last mile' of commercial software automation. In real-world scenarios,

arXiv:2605.09998v1 Announce Type: cross Abstract: Coding harnesses such as Claude Code and OpenHands wrap foundation models with tools, memory, and planning, but no equivalent exists for embodied agen

arXiv:2605.10597v1 Announce Type: cross Abstract: Benchmarks for coding agents increasingly measure source-level software repair, and cybersecurity benchmarks increasingly measure broad capture-the-fl

arXiv:2605.08717v1 Announce Type: cross Abstract: Software engineering agents are increasingly deployed in evaluable engineering environments, yet post-failure recovery remains costly, manual, and ad

arXiv:2605.09679v1 Announce Type: cross Abstract: Medical vision-language models (VLMs) and AI agents have made significant progress in learning to analyze and reason about clinical images. However, e

arXiv:2605.10332v1 Announce Type: new Abstract: Embodied agents can benefit from skills that guide object search, action execution, and state changes across diverse environments. Since embodied enviro

arXiv:2605.10347v1 Announce Type: new Abstract: Recent advances in vision-language models have enabled mobile GUI agents to perceive visual interfaces and execute user instructions, but reliable predi

arXiv:2605.08545v1 Announce Type: new Abstract: Agent benchmarks typically report only final outcomes: pass or fail. This threatens evaluation credibility in three ways. First, scores may be inflated

arXiv:2605.08941v1 Announce Type: new Abstract: The promise of AI-driven scientific discovery hinges on whether AI agents can autonomously design and execute the computational workflows that underpin