Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2608. 11451v1 Announce Type: cross Abstract: Modern end-to-end driving agents can achieve high average performance yet still violate basic traffic rules that a human driver would never miss.
arXiv:2506. 04571v3 Announce Type: replace Abstract: Agriculture is undergoing a major transformation driven by artificial intelligence (AI), machine learning, and knowledge representation technologies.
arXiv:2608. 11274v1 Announce Type: cross Abstract: The dominant paradigm treats AI safety as a property to be instilled during model training via RLHF, DPO, or Constitutional AI.
arXiv:2608. 11597v1 Announce Type: cross Abstract: As smart port infrastructures increasingly rely on autonomous maritime devices enabled by the Internet of Things (IoT), ensuring reliable onboard navigation intelligence has become a critical challenge for safe and scalable operations in congested waterways.
arXiv:2608. 11259v1 Announce Type: cross Abstract: Many AI tutors leverage large language models (LLMs) today.
arXiv:2608. 11246v1 Announce Type: new Abstract: The success of coding agents has established the harness as a paradigm: what an agent achieves depends not on the model alone, but on the infrastructure around it.
arXiv:2608. 11349v1 Announce Type: cross Abstract: A key obstacle to deploying reinforcement learning in real-world systems is hyperparameter selection, particularly when simulators are unavailable and online experimentation is costly.
arXiv:2608. 11715v1 Announce Type: cross Abstract: The reliability of Large Language Models (LLMs) for API calling degrades in multilingual settings.
arXiv:2608. 11588v1 Announce Type: new Abstract: Mobile GUI agents remain brittle when deployed to applications absent from source training.
arXiv:2608. 11727v1 Announce Type: new Abstract: When a coding agent obeys a rule, it may simply have been going to do that anyway.
arXiv:2608. 11679v1 Announce Type: new Abstract: Digital twins are increasingly used to monitor and simulate the behavior of cyber-physical systems.
arXiv:2608. 11511v1 Announce Type: cross Abstract: In sequential decision making, an agent typically observes its environment and acts at every timestep.
arXiv:2608. 11295v1 Announce Type: cross Abstract: Open-weight LLM agents are vulnerable to backdoors installed during fine-tuning, which may be undetectable if the trigger conditions are never met during testing.
arXiv:2608. 11676v1 Announce Type: new Abstract: Heterogeneous multi-agent LLM systems, where agents are powered by different model families, can outperform homogeneous configurations by reducing redundant reasoning patterns.
arXiv:2608. 11410v1 Announce Type: new Abstract: Offline reinforcement learning (RL) offers considerable promise for optimizing ICU treatment decisions, yet standard evaluation metrics Mean Squared Error (MSE) and Fitted Q-Evaluation (FQE) assess only behavioral imitation and cannot detect Toxic Mimicry, a failure mode in which agents replicate harmful patterns such as treatment withdrawal during comfort-care transitions.
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, persistently, or silently.
arXiv:2608. 11873v1 Announce Type: new Abstract: In this work, we extend the Dependent Click Model (DCM) Bandits to a multiplayer information-asymmetric setting, where multiple agents interact with a shared ranked list and may observe multiple clicks per session, introducing new challenges for selection strategies.
arXiv:2608. 12063v1 Announce Type: cross Abstract: Integrating locomotion and manipulation is essential for robot autonomy, but scaling standard Reinforcement Learning (RL) to complex tasks is severely bottlenecked by the slow, manual process of dense reward shaping.
arXiv:2608. 12290v1 Announce Type: cross Abstract: Modern black-box Image-to-Video (I2V) models offer powerful capabilities in automated content creation, yet their lack of fine-grained control and reliability presents significant challenges in professional workflows.
arXiv:2605. 07339v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in orchestrating tools for reasoning tasks.