Search: “tools”

arXiv:2605.02411v1 Announce Type: cross Abstract: A semantic gap separates how users describe tasks from how tools are documented. As API ecosystems scale to tens of thousands of endpoints, static ret

arXiv:2508.04086v2 Announce Type: replace Abstract: Prior work synthesizes tool-use LLM datasets by first generating a user query, followed by complex tool-use annotations like depth-first search (DFS

arXiv:2512.22673v3 Announce Type: replace Abstract: Travel planning is a natural real-world task to test large language models' (LLMs) planning and tool-use abilities. Although prior work has studied

arXiv:2604.17256v1 Announce Type: cross Abstract: Assessing the security posture of modern computing systems typically requires the use of multiple specialized tools. These tools focus on different as

arXiv:2604.10261v1 Announce Type: new Abstract: Existing tool-use benchmarks for LLM agents are overwhelmingly linear: our analysis of six benchmarks shows 55 to 100% of instances are simple chains of

arXiv:2604.11557v1 Announce Type: new Abstract: Tool-use capability is a fundamental component of LLM agents, enabling them to interact with external systems through structured function calls. However

arXiv:2610.13335v1 Announce Type: new Abstract: Tool-using agents increasingly require a common substrate for building, training, evaluating, distilling, and maintaining agentic systems, yet existing

arXiv:2609.40048v1 Announce Type: new Abstract: Ultra-long video temporal grounding requires balancing long-range evidence search with fine-grained event understanding under a limited visual budget, y

arXiv:2609.35811v1 Announce Type: cross Abstract: Tool retrieval is a critical bottleneck for LLM-based agents operating over large, heterogeneous API ecosystems. Existing approaches face an inherent

arXiv:2609.35673v1 Announce Type: new Abstract: Tool-based image editing (image retouching) is commonly formulated with autoregressive multimodal large language models (MLLMs) that sequentially genera

arXiv:2609.32691v1 Announce Type: cross Abstract: LLM agents that invoke privileged tools are vulnerable to indirect prompt injection (IPI), in which adversarial instructions embedded in retrieved dat

arXiv:2609.28585v1 Announce Type: cross Abstract: Multi-step tool-calling LLM agents rely on host runtimes to preserve state across turns. When a runtime carries an external tool return into later mod

arXiv:2609.28693v1 Announce Type: new Abstract: Large Language Model (LLM) agents struggle to scale safely when exposed to vast enterprise toolsets. Providing an agent with access to every internal to

arXiv:2609.29073v1 Announce Type: new Abstract: Vision-Language Models (VLMs) describe scenes well but reason poorly about metric 3D structure such as absolute distances, physical sizes, or egocentric

arXiv:2609.28003v1 Announce Type: new Abstract: Small and medium-sized language models offer cost-effective executors for tool-using agents, making them attractive for local and large-scale deployment

arXiv:2609.27277v1 Announce Type: new Abstract: Time series agents answer analytical questions by calling external tools, and which tools they carry is decided by people before the agent runs. However

arXiv:2609.21967v1 Announce Type: cross Abstract: We introduce NemotronLabs VoiceChat, an open full-duplex speech-to-speech model with native tool-calling capabilities. NemotronLabs VoiceChat combines

arXiv:2609.19334v1 Announce Type: new Abstract: Full-duplex speech-to-speech (S2S) models provide natural, low-latency conversational interaction and would benefit from the ability to use external too

arXiv:2609.16098v1 Announce Type: cross Abstract: Large Language Model (LLM) agents have demonstrated impressive capabilities across a variety of domains, particularly when integrated with external to

arXiv:2602.21061v2 Announce Type: replace Abstract: Many current paths to more advanced AI depend on the assumption that large language models (LLMs) can generalize learned relationships to solve comp

arXiv:2609.12345v1 Announce Type: new Abstract: Existing agent benchmarks mainly evaluate final task success or tool-call correctness, providing limited insight into whether agents can reliably diagno

arXiv:2609.03362v1 Announce Type: new Abstract: Grasping and holding tools while using them presents a considerable challenge not only for robots but also for humans. Such a challenge is particularly

arXiv:2608.30514v1 Announce Type: cross Abstract: We present TSExplorer, a cross-platform tool for interactive annotation and exploration of time-series data. The tool enables users to inspect high-di

arXiv:2608.26623v1 Announce Type: new Abstract: LLM judges are widely used to evaluate agentic tool-calling systems, yet their reliability on structured, dependency-driven workflows remains largely un

arXiv:2608.26199v1 Announce Type: new Abstract: We ask whether AI agents powered by locally deployed large language models can reliably automate expert-defined hardware design workflows in an industry

arXiv:2608.22167v1 Announce Type: new Abstract: Reinforcement learning (RL) has become an effective way to improve the tool-use ability of large language models (LLMs), but most existing RL frameworks

arXiv:2608.16502v1 Announce Type: new Abstract: Large-scale agents increasingly rely on retrieval to access external capabilities. We study this retrieval gate in structured tools and APIs, a measurab

arXiv:2608.04007v1 Announce Type: cross Abstract: Tool-Integrated Reasoning (TIR) enables LLMs to solve complex tasks through iterative tool interactions. However, existing reinforcement learning meth

arXiv:2607.27083v1 Announce Type: new Abstract: As LLM agents increasingly depend on diverse external services such as search engines, databases, and connectors, agent harnesses face a fundamental too

arXiv:2607.17528v3 Announce Type: replace Abstract: Large language model (LLM) agents are extending electronic design automation (EDA) beyond static RTL generation toward long-horizon, tool-interactiv

arXiv:2607.05465v1 Announce Type: cross Abstract: Complex image creation and editing often require more than a single generation or editing model. A user request may involve synthesizing images, local

arXiv:2607.05780v1 Announce Type: cross Abstract: While humans readily repurpose a book, a stone, or a shoe to drive a nail, robots trained on specific tools fail to transfer the same function to nove

arXiv:2512.07287v3 Announce Type: replace-cross Abstract: As intents unfold and environments change, multi-turn agents face continuously shifting decision contexts. Although reusing past experience is

arXiv:2601.05366v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly deployed as agents that invoke external tools through structured function calls. While recent wo

arXiv:2606.26474v1 Announce Type: cross Abstract: Fine-tuning through RL reshapes the internal representations of language models to enable agentic behaviors such as tool use, yet the mechanistic basi

arXiv:2606.26027v1 Announce Type: new Abstract: Tool use enables large language models (LLMs) to perform complex tasks, and recent agentic reinforcement learning (RL) methods show promise for enhancin

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:2602.04935v3 Announce Type: replace-cross Abstract: Adapting LLM agents to domain-specific tool calling remains notably brittle under evolving interfaces. Prompt and schema engineering is easy t

arXiv:2606.06976v1 Announce Type: new Abstract: Large language model (LLM)-based agents often make suboptimal tool-use decisions, including unsupported tool invocation and hallucinated direct response

arXiv:2606.05784v1 Announce Type: new Abstract: We identify and formally characterize credit misassignment as a systematic failure mode of GRPO in tool-augmented multimodal search agents: its uniform

arXiv:2606.05728v1 Announce Type: cross Abstract: Generating executable tool plans requires selecting appropriate subsets from tool libraries, a combinatorial search problem with an exponentially larg

arXiv:2602.14849v2 Announce Type: replace-cross Abstract: LLM agents execute multi-step workflows that mutate external state through tools. Common orchestrators treat tool return as the settlement tri

arXiv:2606.00135v1 Announce Type: cross Abstract: Tool-calling is a central component of modern large language model (LLM) agents, equipping them with skills beyond their parametric knowledge. This pa

arXiv:2605.29568v1 Announce Type: new Abstract: Tool-Integrated Reasoning (TIR) extends LLM capabilities by leveraging external environments. However, existing methods lack the deliberation during seq

arXiv:2605.26037v1 Announce Type: new Abstract: We test the standard RLVR tool-use recipe -- GRPO on Qwen2.5-7B-Instruct -- on a deliberately minimal knowledge-graph tool API: four Freebase navigation

arXiv:2507.10593v3 Announce Type: replace-cross Abstract: Every LLM tool call is structurally an RPC -- a function name, JSON arguments, and a serialized result -- yet each protocol (native Python, MC