Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2606. 07904v1 Announce Type: new Abstract: Tool-augmented large language model agents increasingly rely on external APIs, but standard tool schemas describe how to call a tool, not when the tool is causally appropriate or what task state it produces.
arXiv:2606. 09236v1 Announce Type: cross Abstract: Autonomous Racing has seen remarkable progress through deep Reinforcement Learning (RL), primarily for four-wheeled vehicles.
arXiv:2606. 09746v1 Announce Type: cross Abstract: With AI increasingly deployed in safety-critical systems, providing formal robustness guarantees for the underlying models is essential.
arXiv:2606. 08539v1 Announce Type: new Abstract: AI agents increasingly take consequential actions -- shell commands, cloud operations, and arbitrary tool-calls -- so a trust layer must decide, per action, whether to allow, warn, block, or escalate.
arXiv:2606. 08068v1 Announce Type: new Abstract: Multi-agent large language model (LLM) systems often fail to reliably outperform a single strong model equipped with best-of-N sampling.
arXiv:2606. 07557v1 Announce Type: new Abstract: Decentralized multi-agent swarm coordination on resource-constrained edge platforms remains fundamentally bottlenecked by the exponential scaling of joint action spaces and high-latency communication overhead.
arXiv:2606. 07649v1 Announce Type: cross Abstract: Long-form video generation requires systematic narrative planning and visual consistency that current short-clip methods cannot provide.
arXiv:2606. 09118v1 Announce Type: new Abstract: As LLM capabilities advance rapidly, the evaluation methods used to assess them increasingly lag behind.
arXiv:2602. 16346v4 Announce Type: replace-cross Abstract: LLM-based agents execute real-world workflows via tools and memory.
arXiv:2606. 08729v1 Announce Type: cross Abstract: Simulation plays a key role in automated robotics research supported by large language models (LLMs).
arXiv:2606. 07586v1 Announce Type: cross Abstract: Spatial neural processing units (NPUs) provide an energy-efficient platform for edge LLM inference, but efficiently deploying an LLM end-to-end on such hardware remains labor-intensive.
arXiv:2604. 01039v2 Announce Type: replace-cross Abstract: System Instructions in Large Language Models (LLMs) are commonly used to enforce safety policies, define agent behavior, and protect sensitive operational context in agentic AI applications.
arXiv:2606. 07532v1 Announce Type: cross Abstract: RLHF-trained models are systematically biased toward agreement over accuracy, a structural property of the training process.
arXiv:2603. 18388v2 Announce Type: replace Abstract: Automatic prompt optimization (APO) has emerged as a powerful paradigm for improving LLM performance without manual prompt engineering.
arXiv:2606. 09787v1 Announce Type: new Abstract: The Cloud-Edge Continuum (CEC) enables latency-critical applications by distributing resources to the far edge, but its extreme volatility makes proactive Zero Touch Management via time-series forecasting essential.
arXiv:2606. 09682v1 Announce Type: new Abstract: AutoMegaKernel (AMK) compiles a HuggingFace Llama-family model into a single persistent cooperative CUDA kernel that runs the whole forward pass in one launch, with no per-model hand-written CUDA.
arXiv:2606. 08030v1 Announce Type: cross Abstract: Agentic tutoring systems introduce a coordination challenge: multiple agents may propose different but reasonable interventions, yet only one response can be delivered to the learner.
arXiv:2606. 07866v1 Announce Type: new Abstract: Regulatory review of advanced nuclear reactor designs routinely spans more than three years and consumes hundreds of millions of dollars in combined regulator and applicant labor.
arXiv:2606. 07626v1 Announce Type: cross Abstract: Perception in dense, unstructured urban traffic remains a major challenge for autonomous driving because of the wide variety of road users, frequent occlusions, irregular motion patterns, and the lack of standardized road layouts.
arXiv:2601. 15727v3 Announce Type: replace Abstract: The performance of modern AI systems is fundamentally constrained by the quality of their underlying GPU kernels, which translate high-level algorithmic semantics into low-level hardware operations.