Search: “tool-use”

arXiv:2602.16346v3 Announce Type: replace Abstract: LLM-based agents execute real-world workflows via tools and memory. These affordances enable ill-intended adversaries to also use these agents to ca

arXiv:2605.16821v1 Announce Type: new Abstract: The rapid evolution of Large Language Model (LLM) agents has produced diverse interaction paradigms, yet few production systems integrate multiple parad

arXiv:2605.17862v1 Announce Type: cross Abstract: Scaling on-policy distillation (OPD) for large language models (LLMs) confronts a fundamental tension: asynchronous execution is necessary for system

arXiv:2605.17946v1 Announce Type: new Abstract: Multimodal large language models are increasingly used as agent backbones that understand multimodal inputs, plan retrieval actions, invoke external too

arXiv:2602.21265v2 Announce Type: replace Abstract: We introduce ToolMATH, a math-grounded diagnostic benchmark for evaluating long-horizon tool use under controllable tool-catalog conditions. ToolMAT

arXiv:2605.16257v1 Announce Type: new Abstract: Achieving human-level manipulation requires dexterous robotic hands capable of complex object interactions. Advancing such capabilities further demands

The pure LLM debate - which I had for many years, here and elsewhere - is indeed no longer relevant. Why? Because I won; nobody uses pure LLMs anymore. Nowadays all deployed objects are neurosymbolic,

arXiv:2605.15041v1 Announce Type: new Abstract: Tool use extends large language models beyond parametric knowledge, but reliable execution requires balancing appropriate reasoning depth with strict st

arXiv:2605.13989v1 Announce Type: new Abstract: We present VectraYX-Nano, a 41.95M-parameter decoder-only language model trained from scratch in Spanish for cybersecurity, with a Latin-American focus

arXiv:2605.12652v1 Announce Type: cross Abstract: Large language models are often post-trained with sparse verifier rewards, which indicate whether a sampled trajectory succeeds but provide limited gu

arXiv:2605.11613v1 Announce Type: new Abstract: On-policy self-distillation has emerged as a promising paradigm for post-training language models, in which the model conditions on environment feedback

arXiv:2605.11853v1 Announce Type: cross Abstract: Reinforcement learning has become a widely used post-training approach for LLM agents, where training commonly relies on outcome-level rewards that pr

arXiv:2605.08887v1 Announce Type: new Abstract: Self-evolving agents present a promising path toward continual adaptation by distilling task interactions into reusable knowledge artifacts. In practice

arXiv:2604.08178v2 Announce Type: replace Abstract: In classical Reinforcement Learning from Human Feedback (RLHF), Reward Models (RMs) serve as the fundamental signal provider for model alignment. As

arXiv:2601.11258v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) face the 'knowledge cutoff' challenge, where their frozen parametric memory prevents direct internalization of ne

arXiv:2605.08498v1 Announce Type: cross Abstract: We introduce MathConstraint, a hard, adaptive benchmark for evaluating the combinatorial reasoning capabilities of LLMs. We combine constraint satisfa

arXiv:2605.08762v1 Announce Type: cross Abstract: Current omni-modal benchmarks mainly evaluate models under settings where multiple modalities are provided simultaneously, while the ability to start

arXiv:2605.08876v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed as autonomous agents that execute tool-augmented, multi-step tasks, where latency is a critical f

arXiv:2605.10848v1 Announce Type: cross Abstract: Does a lexical retriever suffice as large language models (LLMs) become more capable in an agentic loop? This question naturally arises when building

arXiv:2605.09544v1 Announce Type: new Abstract: Tool-integrated reasoning has emerged as a promising paradigm for enhancing large language models with external computation, retrieval, and execution ca

arXiv:2605.10038v1 Announce Type: new Abstract: Time series analysis underpins forecasting, monitoring, and decision making in domains such as finance and weather, where solving a task often requires

arXiv:2510.20036v2 Announce Type: replace Abstract: Large language model (LLM) agents rely on external tools to solve complex tasks, but real-world toolsets often contain redundant tools with overlapp

arXiv:2605.10832v1 Announce Type: new Abstract: Multimodal deep search requires an agent to solve open-world problems by chaining search, tool use, and visual reasoning over evolving textual and visua

arXiv:2605.07926v1 Announce Type: new Abstract: As LLM-based agents increasingly rely on external tools, it is important to evaluate their ability to sustain tool-grounded reasoning beyond familiar wo

arXiv:2605.06387v2 Announce Type: replace-cross Abstract: On-policy distillation (OPD) trains a student on its own trajectories with token-level teacher feedback and often outperforms off-policy disti

arXiv:2605.07364v1 Announce Type: new Abstract: Flight delays impose cascading operational and financial burdens across the aviation network, costing the U.S. economy billions of dollars annually by d

arXiv:2605.07177v1 Announce Type: cross Abstract: Existing multimodal search agents process target entities sequentially, issuing one tool call per entity and accumulating redundant interaction rounds

arXiv:2605.06483v2 Announce Type: replace Abstract: Signal Temporal Logic (STL) is an expressive formal language for specifying spatio-temporal requirements over real-valued, real-time signals. It has

arXiv:2605.07276v1 Announce Type: new Abstract: Code-agent RL often receives weak feedback: rollout-time signals are reliable and executable, but capture only necessary or surface conditions for task

arXiv:2605.07112v1 Announce Type: new Abstract: Agentic AI systems that invoke external tools are powerful but costly, leading developers to default to large models and overspend inference budgets. Mo

arXiv:2605.03900v1 Announce Type: new Abstract: Frontier AI systems perform best in settings with clear, stable, and verifiable objectives, such as code generation, mathematical reasoning, games, and

arXiv:2506.20911v2 Announce Type: replace Abstract: We develop a cost-efficient neurosymbolic agent to address challenging multi-turn image editing tasks such as ``Detect the bench in the image while

arXiv:2605.04135v1 Announce Type: cross Abstract: Readers of applied-domain LLM capability evaluations want to know what AI systems can currently do. That literature answers a related, but consequenti

arXiv:2605.03383v1 Announce Type: new Abstract: Lithology classification aims to infer subsurface rock types from well-logging signals, supporting downstream applications like reservoir characterizati

arXiv:2605.05040v1 Announce Type: new Abstract: On-policy distillation is an efficient alternative to reinforcement learning, offering dense token-level training signals. However, its reliance on a st

arXiv:2605.04107v1 Announce Type: cross Abstract: Production agent frameworks (OpenAI Function Calling, Anthropic Tool Use, MCP) transmit tool schemas as JSON, a format designed for machine parsing, n

arXiv:2605.01250v1 Announce Type: new Abstract: Earth Observation (EO) analysis is inherently interactive: resolving uncertainty often requires expanding the region of interest, retrieving historical

arXiv:2605.02913v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a central post-training tool for improving the reasoning abilities of large language models (LLMs). In these syst

arXiv:2605.02943v1 Announce Type: new Abstract: Clinical reasoning demands multi-step interactions -- gathering patient history, ordering tests, interpreting results, and making safe treatment decisio

arXiv:2605.00737v1 Announce Type: new Abstract: Agentic AI architectures augment LLMs with external tools, unlocking strong capabilities. However, tool use is not always beneficial; some calls may be

arXiv:2509.21723v4 Announce Type: replace Abstract: Achieving generalizable bimanual manipulation requires systems that can learn efficiently from minimal human input while adapting to real-world unce

arXiv:2603.20133v2 Announce Type: replace Abstract: Large Language Models (LLMs) achieve strong performance on many reasoning benchmarks, yet these evaluations typically focus on isolated tasks that d

arXiv:2604.25318v1 Announce Type: cross Abstract: Cutscenes are carefully choreographed cinematic sequences embedded in video games and interactive media, serving as the primary vehicle for narrative

arXiv:2604.16922v2 Announce Type: replace Abstract: Climate research is pivotal for mitigating global environmental crises, yet the accelerating volume of multi-scale datasets and the complexity of an

arXiv:2603.29957v3 Announce Type: replace-cross Abstract: Recent advances in reasoning Large Language Models (LLMs) have primarily relied on upfront thinking, where reasoning occurs before final answe

arXiv:2604.22985v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed to autonomously solve real-world tasks. A key ingredient for this is the LLM Function-Calling par