Search: “tools”

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:2609.37743v1 Announce Type: new Abstract: LLM agents performing long-horizon tasks accumulate tool results that later steps may need. Passing the full history to every invocation is costly even

arXiv:2609.35807v1 Announce Type: cross Abstract: LLM agents can make unsafe tool calls even when instructed to behave safely. Existing defenses constrain agents before execution, modify tool inputs/o

arXiv:2609.31789v1 Announce Type: cross Abstract: In this work, we explore MammoClaw, a training-free agent framework that leverages frozen MLLMs for mammography analysis. To support agentic investiga

arXiv:2609.34701v1 Announce Type: cross Abstract: Multi-agent systems (MAS) are increasingly used to automate enterprise workflows involving multiple specialized agents, external tools, and long-runni

arXiv:2609.30662v1 Announce Type: new Abstract: Large language models (LLMs) can plan, use tools, write code, and execute long-horizon workflows, yet strong local competence does not guarantee project

arXiv:2609.29341v1 Announce Type: new Abstract: Consumer-facing skincare AI must coordinate visual evidence, product information, tool use, and user-facing actions within explicit evidence and safety

arXiv:2609.29007v1 Announce Type: new Abstract: Tool-using agents are continually updated with new interaction data. After each policy update, however, previously estimated action credits may become s

arXiv:2609.19947v1 Announce Type: new Abstract: LLM-based AI agents process user requests through iterative reasoning and tool execution, often involving the invocation of remote LLM APIs with local t

arXiv:2609.18844v1 Announce Type: new Abstract: Multimodal coding agents are expected to turn visual inputs into usable artifacts, and they act through a harness, the layer of tools, context managemen

arXiv:2609.16984v1 Announce Type: new Abstract: Open-weight language models publish the strings their chat templates use to mark turns, roles and tool results, which the tokenizer maps back to the res

arXiv:2609.17419v1 Announce Type: new Abstract: Long-horizon LLM agents must maintain task state across extended sequences of observations, actions, tool calls, and intermediate beliefs. We study thes

arXiv:2609.13667v1 Announce Type: new Abstract: Geospatial agents are increasingly expected to support recurring and evolving analytical tasks rather than execute isolated workflows. In such settings,

arXiv:2609.13060v1 Announce Type: new Abstract: Diffusion Language Models (DLMs) offer promising parallel generation capabilities but lag behind autoregressive models in complex reasoning and tool-use

arXiv:2609.11987v1 Announce Type: cross Abstract: An agentic coding system couples a language model to a harness: the tools, prompts and control flow that turn a chat model into an autonomous software

arXiv:2609.09875v1 Announce Type: new Abstract: Existing evaluation frameworks mostly assess only one part of AI agents, such as task completion (AgentBench) or security robustness (AgentDojo, ASB), r

arXiv:2609.09754v1 Announce Type: new Abstract: As large language models are increasingly deployed as tool-augmented legal agents, they introduce agentic hallucinations where tool-call and reasoning e

arXiv:2609.11772v1 Announce Type: cross Abstract: Cross-cultural understanding has become increasingly important in today's highly connected, cross-national world. The success of LLM-based technologie

arXiv:2609.06128v1 Announce Type: new Abstract: Production LLM agents execute tool-calling loops, retrieval chains, and compositional workflows in multiple modes, yet execution semantics are often cou

arXiv:2609.05920v1 Announce Type: cross Abstract: Agent Skills combine instructions with files, packages, tools, models, and services, so operational identity can exceed a signed directory. Recursive

arXiv:2609.06758v1 Announce Type: new Abstract: Visual generation is evolving from generative models used through a single invocation into agentic control processes that can plan, select tools, inspec

arXiv:2609.07529v1 Announce Type: new Abstract: Tool-augmented language agents are vulnerable to indirect prompt injection (IPI). Unlike direct prompt injection, IPI hides adversarial instructions in

arXiv:2609.08025v1 Announce Type: cross Abstract: Reasoning agents increasingly rely on external tools such as web search to answer complex queries. Reinforcement learning (RL) finetuning algorithms s

arXiv:2609.07916v1 Announce Type: new Abstract: Images are important tools in various sciences. Despite the development of photo-taking tools, creating clear and image without noise remains challengin

arXiv:2608.25202v3 Announce Type: replace-cross Abstract: Spec-Driven Development (SDD) is a fast-emerging practice in which a structured natural-language specification, written by a developer, or (mo

arXiv:2609.00808v1 Announce Type: cross Abstract: As far-right actors increasingly exploit online platforms to disseminate ideology and mobilize supporters, civil society organizations (CSOs) play a v

arXiv:2609.00700v1 Announce Type: new Abstract: LLMs have been rapidly adopted across writing tasks, prompting the development of tools for detecting LLM-generated text. Yet, these tools largely measu

arXiv:2608.29464v1 Announce Type: cross Abstract: Chain-of-thought (CoT) monitoring assumes that reasoning traces faithfully record the information that shapes a model's answer. Existing faithfulness

arXiv:2608.30756v1 Announce Type: cross Abstract: Large language models (LLMs) have become an essential tool for assisting developers, yet we still lack knowledge on ways to effectively support their

arXiv:2608.30156v1 Announce Type: new Abstract: Plane geometry problem (PGP) solving has become a critical benchmark for multimodal reasoning because it requires accurate visual perception and precise

arXiv:2608.26432v1 Announce Type: cross Abstract: Voice agents must call tools and hold multi-turn dialogue entirely through speech, yet the dominant paradigm trains them in text. Existing frameworks

arXiv:2608.23035v1 Announce Type: new Abstract: As on-device LLM agents evolve into personal copilots, the mobile operating system has become a key testbed for this paradigm, making rigorous capabilit

arXiv:2608.18554v1 Announce Type: cross Abstract: Most LLM benchmarks rank models on their ability to automate work tasks. In practice, however, models are often used to assist other (human or LLM) ag

arXiv:2608.14680v1 Announce Type: new Abstract: Reliability in LLM-based agentic systems is a property of the whole execution (its tool calls, model calls, guardrails, and inter-agent messages), not o

arXiv:2608.13622v1 Announce Type: new Abstract: Open-ended real-world interaction admits multiple valid behaviors: an agent may answer directly, ask for clarification, provide progress updates, or con

arXiv:2608.11232v1 Announce Type: cross Abstract: Evaluating LLM coding agents in algorithmic trading is difficult because static benchmarks risk data contamination and numerical backtest outputs requ

arXiv:2510.20739v2 Announce Type: replace-cross Abstract: Program analysis tools often produce large volumes of candidate vulnerability reports that require costly manual review, creating a practical

arXiv:2608.09521v1 Announce Type: new Abstract: Activation-based tools are usually tied to one model's native hidden space, requiring probes, sparse autoencoders, and natural-language interpreters to

arXiv:2608.07555v1 Announce Type: new Abstract: Coding agents such as Claude Code and Codex close the software loop: a main agent manages the loop, subagents analyze and execute, tools do the work. We

arXiv:2608.06397v1 Announce Type: cross Abstract: Symbolic execution seeks to explore feasible program paths, yet a practical run may exhaust its resources while much program behaviour remains unreach

arXiv:2608.03499v1 Announce Type: new Abstract: Recent advances in persistent personal-agent frameworks are making human-centered agent networks realistic deployment targets: each user can be served b

arXiv:2608.00485v1 Announce Type: new Abstract: Recent Text-to-SQL systems increasingly rely on multi-turn interaction, execution feedback, and reinforcement learning. However, most existing methods u

arXiv:2512.06716v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly used as the core of agentic systems due to their strong reasoning, planning, and tool-use capabi

arXiv:2607.23929v1 Announce Type: new Abstract: LLM agents increasingly coordinate through persistent shared memory: one agent's write becomes another agent's premise, and eventually a tool call with

arXiv:2607.23123v1 Announce Type: new Abstract: Existing evaluations of large language models cover knowledge, reasoning, coding, and tool use, but they rarely treat a verifiable deliverable produced

arXiv:2607.21125v1 Announce Type: new Abstract: Image restoration agents have recently emerged as a flexible paradigm for handling diverse and unpredictable degradations in real-world scenarios. Exist