Search: “tool-use”

arXiv:2608.26882v1 Announce Type: cross Abstract: Industrial control systems (ICSs) rely on programmable logic controllers (PLCs) to connect networked computation with physical control. Tool-using lar

arXiv:2608.26563v1 Announce Type: new Abstract: Agentic (tool-using) language models are mainly trained on tool-call traces and agent trajectories during post-training. These data provide direct behav

arXiv:2608.22191v1 Announce Type: new Abstract: Software-engineering agents solve repository-level tasks through long, stochastic tool-use trajectories, and repeated attempts often find fixes missed b

arXiv:2608.23395v1 Announce Type: cross Abstract: Recent LLM-agent systems make conflicting design bets: decompose work across many narrow agents, or use one strong tool-using agent. This pilot studie

arXiv:2608.22467v1 Announce Type: new Abstract: Long-horizon language-model tasks --- multi-step reasoning and tool-using agents alike --- are limited by credit assignment. We analyze it through the p

arXiv:2608.21159v1 Announce Type: cross Abstract: Tool-using AI agents turn delegated tasks into provider effects, yet authorization often ends at admission while provider state, delivery, retry, and

arXiv:2608.17587v1 Announce Type: new Abstract: Expert-written natural language skills can improve tool-using agents, yet agent-authored skills perform 8-11 points worse than using no skill. This gap

arXiv:2608.15685v1 Announce Type: new Abstract: Tool-using video agents retrieve visual evidence before answering, but the final answer is not forced to depend on what was retrieved. The natural black

arXiv:2608.16544v1 Announce Type: cross Abstract: Agents increasingly rely on reusable skills to encode task knowledge, tool-use procedures, and validation rules. Existing skill self-evolution methods

arXiv:2608.12880v1 Announce Type: cross Abstract: Security evaluations of tool-using agents often equate stored labels with behavioral facts. We audit a preserved campaign by tracing 10,200 execution

arXiv:2608.12789v1 Announce Type: cross Abstract: Tool-using agents consume external data from sources with different levels of trust, yet tool responses rarely identify who produced each component or

arXiv:2608.13179v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) offers a verifier-bounded performance ceiling for training multi-turn tool-use agents, yet its tra

arXiv:2608.08793v1 Announce Type: new Abstract: Agent Skills package reusable instructions and assets for tool-using language-model agents. Progressive loading creates failure boundaries poorly repres

arXiv:2608.08282v1 Announce Type: new Abstract: Tool-using language-model agents face constraints whose meaning changes with observations and prior actions. We study exact sampling from the model dist

arXiv:2608.08795v1 Announce Type: cross Abstract: Tool-using large language model (LLM) agents are vulnerable to indirect prompt injection (IPI), in which malicious instructions embedded in external o

arXiv:2608.05778v1 Announce Type: new Abstract: Prompt-side playbooks can improve tool-using language agents without retraining, but their portability beyond the source setting is unclear. We study fr

arXiv:2608.06057v1 Announce Type: new Abstract: Tool-calling agents infer task state from accumulated dialogue and tool traces. In persistent interactions, however, historical traces may remain struct

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:2608.03468v1 Announce Type: new Abstract: Historical tool-use trajectories provide valuable experience for large language model (LLM) agents to plan and coordinate tool usage. Existing approache

arXiv:2608.02680v1 Announce Type: cross Abstract: Tool-using language-model agents repeatedly rediscover procedures they have already executed, producing traces that mix reusable structure with retrie

arXiv:2608.00218v1 Announce Type: new Abstract: Agentic LLMs exhibit three consequential tool-use failures: invalid arguments (validity), unnecessary calls (over-calling), and omitted calls when tools

arXiv:2608.00432v1 Announce Type: new Abstract: Deep research agents are often trained on expensive, environment-grounded tool-use trajectories that require repeated retrieval, document inspection, an

arXiv:2607.29250v1 Announce Type: new Abstract: Small language models (SLMs) are attractive for agentic deployment due to low latency, reduced cost, and on-device privacy, yet they struggle with tool-

arXiv:2607.25364v1 Announce Type: new Abstract: Tool-using agents expose structured calls but commonly attach free-form rationales. Such rationales are neither authorization nor reliable introspection

arXiv:2606.18037v2 Announce Type: replace Abstract: Tool-using LLM agents increasingly use the Model Context Protocol (MCP) to answer from heterogeneous evidence sources, including search, APIs, datab

arXiv:2509.14257v3 Announce Type: replace-cross Abstract: Large Language Model agents achieve strong performance on multi-step reasoning and tool-use tasks, but their impressive capabilities typically

arXiv:2607.20510v1 Announce Type: new Abstract: We introduce Telco-GAIA, a bilingual, multi-modal benchmark for evaluating tool-using agents on the data of a real-world telecommunications operator. Te

arXiv:2607.19913v1 Announce Type: new Abstract: Agent safety is moving from content moderation toward preventing operational failures before tool-using agents act. We propose Janus, a foresight-orient

arXiv:2607.19339v1 Announce Type: new Abstract: Long audio-video reasoning is difficult for omnimodal LLMs because the decisive evidence is often sparse, cross-modal, and too expensive to preserve wit

arXiv:2607.11098v2 Announce Type: replace-cross Abstract: Tool-using LLM agents are mostly evaluated assuming all tools work. When a tool times out, returns a week-stale value, or has its description

arXiv:2607.07820v1 Announce Type: new Abstract: Training tool-use agents to improve from their own experience remains challenging, as supervised fine-tuning relies on fixed teacher-distilled trajector

arXiv:2606.28679v1 Announce Type: cross Abstract: Tool-using LLM agents increasingly read untrusted content while holding side-effecting tools such as payments, email, CRM, and infrastructure APIs, ye

arXiv:2606.28450v1 Announce Type: cross Abstract: Large language model (LLM) agents are rapidly being integrated into real-world systems. Their autonomy and tool-use capabilities generate substantial

arXiv:2606.28270v1 Announce Type: new Abstract: The transition from static chat bots to autonomous agents--equipped with persistent memory, tool-use protocols, and multi-agent collaboration--has funda

arXiv:2606.26479v1 Announce Type: cross Abstract: Recent work (2024 to 2026) has converged on a strategy for defending tool-using LLM agents against indirect prompt injection: rather than training the

arXiv:2606.24453v1 Announce Type: new Abstract: Modern coding agents pair LLM generators with various tools, including cheap diagnostics and expensive verifiers. The tool-use decisions are typically g

arXiv:2606.23112v1 Announce Type: new Abstract: Multi-turn tool-using agents must coordinate long-horizon tool sequences while tracking dialogue state and policy constraints. Existing approaches often

arXiv:2606.19340v2 Announce Type: replace Abstract: We present ZeroDex, a zero-shot framework for long-horizon dexterous manipulation that grounds language instructions into executable 3D task plans f

arXiv:2606.12384v1 Announce Type: cross Abstract: Recent advances in agentic Reinforcement Learning (RL) have substantially improved the multi-turn tool-use capabilities of large language model agents

arXiv:2606.09315v1 Announce Type: cross Abstract: BCI-to-agent pipelines turn decoded neural activity into an authorization channel for tool-use agents, exposing a new attack surface we call brain-pro

arXiv:2606.09549v1 Announce Type: cross Abstract: Tool-using large language model (LLM) agents face two distinct security failures: unauthorized external actions and exposure of sensitive plaintext in

arXiv:2606.06787v1 Announce Type: new Abstract: Large Language Models (LLMs) show promise as tool-using agents but remain limited in long-horizon tasks that require remembering, organizing, and reusin

arXiv:2606.05711v1 Announce Type: new Abstract: Multi-agent systems built on large language models (LLMs) have become a prevailing paradigm for tackling complex reasoning, planning, and tool-use tasks

arXiv:2606.03318v1 Announce Type: new Abstract: Despite great advances in tool-use capabilities of large language models (LLMs), existing evaluation benchmarks struggle to fully align with real-world

arXiv:2606.03762v1 Announce Type: cross Abstract: Agentic reinforcement learning (RL) equips large language models (LLMs) with tool-use capabilities that substantially improve reasoning on complex tas

arXiv:2606.02240v1 Announce Type: cross Abstract: Indirect prompt injection in tool-use agents is a concrete production threat: LLM agents read from integrations (third-party services such as Gmail, S