Search: “tool-use”

arXiv:2510.18383v4 Announce Type: replace-cross Abstract: Distilling the tool-use capabilities of large language models (LLMs) into small language models (SLMs) is essential for their practical applic

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:2606.16215v2 Announce Type: replace-cross Abstract: Multi-turn tool-use agents must reason, call tools, and adapt to observations across several interaction turns. Post-training such agents is c

arXiv:2604.06185v1 Announce Type: cross Abstract: Fulfilling user needs through Large Language Model multi-turn, multi-step tool-use is rarely a straightforward process. Real user interactions are inh

arXiv:2609.36887v1 Announce Type: new Abstract: Recent efforts to scale tool-use post-training have largely centered on the synthesis of executable environments, which constitute only one component of

arXiv:2608.10357v1 Announce Type: cross Abstract: Long-horizon tool-using agents must reason over user goals, domain policies, tool calls, simulator state, and delayed verifiable rewards. Reinforcemen

arXiv:2608.10042v1 Announce Type: cross Abstract: Tool-use LLMs are increasingly asked to act on users' behalf, but existing benchmarks usually focus on profile recall, style imitation, generic tool u

arXiv:2602.01334v2 Announce Type: replace Abstract: Vision tool-use reinforcement learning (RL) can equip vision language models with visual operators such as crop-and-zoom and achieves strong perform

NEW paper from Alibaba. A 30B MoE with only 3B active params matches Qwen3-235B on real tool-use workloads. AgenticQwen-30B-A3B: 50.2 average on TAU-2 + BFCL-V4 Multi-Turn. AgenticQwen-8B: 47.4. Both

arXiv:2604.09813v1 Announce Type: new Abstract: Existing synthetic tool-use corpora are primarily designed for offline supervised fine-tuning, yet reinforcement learning (RL) requires executable envir

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:2610.02330v1 Announce Type: new Abstract: Large language models (LLMs) rely on long-horizon tool invocation sequences for complex tasks, where each invocation can alter the task state and condit

arXiv:2609.05837v1 Announce Type: new Abstract: LLM-based agents are increasingly deployed in real-world applications through tool-use APIs, yet training them for specific environments remains fundame

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:2608.11977v1 Announce Type: new Abstract: Tool-using LLM agents are commonly trained and evaluated in environments where tool calls succeed reliably, yet deployed tools can fail transiently, per

arXiv:2608.06270v1 Announce Type: new Abstract: The 'thinking-with-images' paradigm equips multimodal LLMs with active visual operations such as crop-and-zoom. However, models using these operations o

arXiv:2608.02650v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on external tools to complete complex real-world tasks. However, reliable tool-use planning remains

arXiv:2607.20536v1 Announce Type: new Abstract: Tool-use agents that address day-to-day digital tasks such as ordering groceries must not only operate applications, but also interact with the user, e.

arXiv:2606.12634v2 Announce Type: replace-cross Abstract: Long-horizon tool-use reinforcement learning learns from outcome verification, but trajectory-level advantages are broadcast over reasoning, A

arXiv:2605.28224v1 Announce Type: new Abstract: Multi-trajectory inference for tool-use LLM agents - generating multiple reasoning attempts and selecting among them - benefits from transferring knowle

OpenAI: OpenAI says it paused training, evaluation, and inference with tool-use of its most capable models after a model bypassed internet restrictions during training — Summary — An agent attempting

arXiv:2609.24264v1 Announce Type: new Abstract: Tool-use agent traces identify messages and API calls, but procedural analyses also need explicit units of action and inspectable links to their evidenc

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:2609.05876v1 Announce Type: new Abstract: AI-generated image detection is increasingly open-world: new image generators produce highly realistic images that make visual artifacts harder to ident

arXiv:2609.00823v1 Announce Type: new Abstract: Long-horizon tool-use agents need not only to search and plan, but also to decide when to finalize. We study late-stage pressure states, in which an age

arXiv:2608.08557v1 Announce Type: new Abstract: Visual tool use has emerged as a fundamental capability for multimodal agents to actively acquire evidence beyond a fixed image encoding. The prevailing

Together AI gives developers a high-throughput production path for running DeepSeek V4 Flash across coding, tool-use, and agentic workloads. Start building: https://www.together.ai/models/deepseek-v4-

arXiv:2607.04686v1 Announce Type: cross Abstract: Tool calling is central to modern language model agents, but aggregate benchmark scores often hide where tool use fails. A model that never calls a ne

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:2606.06923v1 Announce Type: new Abstract: We study orchestration mechanisms for tool-using AI agents in realistic customer-service workflows over an unstructured knowledge base. We argue that de

arXiv:2605.18703v1 Announce Type: new Abstract: Equipping LLMs with tool-use capabilities via Agentic Reinforcement Learning (Agentic RL) is bottlenecked by two challenges: the lack of scalable, robus

arXiv:2609.10962v1 Announce Type: cross Abstract: Studies of the Model Context Protocol (MCP) server ecosystem draw their samples in ways that quietly select for servers that work: reference sets, pop

arXiv:2609.00052v1 Announce Type: cross Abstract: Commercial LLM APIs advertise a specific foundation model, but the served backbone may be silently substituted, quantized, or wrapped, for example to

arXiv:2608.30685v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly deployed in user-facing services that require iterative tool use under dynamic business conditions. R

arXiv:2608.07585v1 Announce Type: new Abstract: Long-video understanding requires models to efficiently acquire and reuse sparse visual evidence from long and redundant video streams. Recent video too

arXiv:2607.23722v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed as agents that interact with stateful environments over multiple steps: gathering hidden informat

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:2602.12984v2 Announce Type: replace Abstract: Scientific reasoning inherently demands integrating sophisticated toolkits to navigate domain-specific knowledge. Yet, current benchmarks largely ov

arXiv:2602.00994v2 Announce Type: replace Abstract: Agentic Reinforcement Learning (ARL) trains large language models to interleave reasoning with external tool execution to solve complex tasks. Most

arXiv:2605.14443v1 Announce Type: new Abstract: The shift toward interacting with frozen, 'black-box' Large Language Models (LLMs) has transformed prompt engineering from a heuristic exercise into a c

arXiv:2602.00933v2 Announce Type: replace-cross Abstract: The Model Context Protocol (MCP) is rapidly becoming the standard interface for Large Language Models (LLMs) to discover and invoke external t

arXiv:2512.16918v3 Announce Type: replace Abstract: Recent advances have shown that multimodal large language models (MLLMs) benefit from multimodal interleaved chain-of-thought (CoT) with vision tool

arXiv:2604.21255v1 Announce Type: new Abstract: Model distillation is a primary driver behind the rapid progress of LLM agents, yet it often leads to behavioral homogenization. Many emerging agents sh

arXiv:2604.15715v1 Announce Type: cross Abstract: The development of general-purpose agents requires a shift from executing simple instructions to completing complex, real-world productivity workflows

arXiv:2609.36201v1 Announce Type: cross Abstract: Computer-use agents (CUAs), while capable of completing computer tasks in everyday and professional workflows, can cause unintended harm even under be

arXiv:2609.00967v1 Announce Type: new Abstract: As large language models increasingly act through external tools, deciding when to call a tool has become a central problem alongside deciding how to us