Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2606. 07595v1 Announce Type: cross Abstract: Vision-language agents increasingly consume screenshots, documents, and user interfaces before writing to memory, sending messages, or invoking external tools.
arXiv:2606. 07645v1 Announce Type: cross Abstract: The scarcity of hard negative samples in current vision-language datasets significantly hinders fine-grained perception.
arXiv:2606. 09756v1 Announce Type: new Abstract: Responses to perturbations are key to understanding physical systems.
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. 09563v1 Announce Type: new Abstract: As LLMs are deployed as agents, reliable monitoring requires knowing not only what they output, but which instructions are steering their behavior.
arXiv:2506. 10341v2 Announce Type: replace Abstract: Interactively learning from observation and language feedback is an increasingly studied area driven by the emergence of large language model (LLM) agents.
arXiv:2503. 14229v4 Announce Type: replace Abstract: Vision-and-Language Navigation (VLN) has been studied mainly in either discrete or continuous spaces, with little attention to dynamic, crowded environments.
arXiv:2508. 06659v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) agents often struggle to generalize to new tasks and contexts without updating their parameters, mainly because their learned representations and policies are overfit to the specifics of their training environments.
arXiv:2606. 08270v1 Announce Type: cross Abstract: University Academic Management Information Systems (ACMIS) are high-value targets for a wide spectrum of security threats including brute-force login attacks, payment fraud, privilege escalation, insider data theft, and academic integrity violations.
arXiv:2606. 08310v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as long-horizon agents with decision-making capacities.
arXiv:2606. 08151v1 Announce Type: new Abstract: Tool-using LLM agents often fail not because relevant text is absent, but because decisive evidence is not selected, compressed, or surfaced at action time.
arXiv:2601. 06077v2 Announce Type: replace-cross Abstract: This work aims to rigorously define the values of perception, prediction, communication, and common sense in decision making.
arXiv:2606. 09084v1 Announce Type: cross Abstract: Tool-using LLM agents interact with the world through actions that persist state in artifacts (e.
arXiv:2606. 07810v1 Announce Type: cross Abstract: Large language models (LLMs) are widely used as judges for evaluating model outputs, but their high cost, latency, and opacity limit scalability.
arXiv:2606. 07552v1 Announce Type: cross Abstract: Large language models exhibit innate behavioral tendencies when deployed as strategic agents -- notably a risk-averse "turtle" bias toward defensive play.
arXiv:2606. 08702v1 Announce Type: new Abstract: Recent advances have improved the adaptive capabilities of LLM-based multi-agent systems (MAS) through memory-, skill-, and learning-based approaches, yet these approaches remain challenged by noisy trajectories, insufficient modeling of memory-skill relations, and reliance on additional training or high-quality supervision.
arXiv:2605. 28831v2 Announce Type: replace-cross Abstract: Long-horizon memory question answering often requires sparse evidence from heterogeneous histories, including events, object states, visual observations, temporal relations, and causal steps.
arXiv:2606. 08234v1 Announce Type: new Abstract: LLM-based scientific agents have shown strong capacity for autonomous research, yet their safety layers remain structurally divorced from core reasoning: they inspect pipeline outputs rather than shaping the deliberation that produces them.
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. 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.