Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2608.28628v1 Announce Type: new Abstract: Compound drought-to-extreme-precipitation (CDEP) events are recognized in climate science as a growing driver of extreme impact, but whether this recog...
arXiv:2608.28637v1 Announce Type: new Abstract: Autonomous scientific discovery systems can generate large numbers of research ideas, experiments, and manuscripts with minimal human intervention. As...
arXiv:2608.28642v1 Announce Type: new Abstract: Knowledge graphs used by agentic systems are often treated as flat stores of extracted triples, with little record of who owns a fact, why it was admit...
arXiv:2608.28638v1 Announce Type: new Abstract: Agent skills are portable packages of instructions and resources an agent consults at deployment. Self-evolving them fails in two ways today. First, sk...
arXiv:2608.28646v1 Announce Type: new Abstract: Large language models (LLMs) can generate plausible-sounding ETF portfolios while silently violating basic KYC-style constraints on risk, fees, and div...
arXiv:2608.28662v1 Announce Type: new Abstract: Fracture detection and its clinical interpretability see notable improvements when deep vision models are integrated with agentic AI architectures. Whi...
arXiv:2608.28704v1 Announce Type: new Abstract: AI agents increasingly perform long-term reasoning, planning, tool use, memory integration, and autonomous decision making, yet erroneous intermediate...
arXiv:2608.29363v1 Announce Type: new Abstract: Enterprise data agents answer business queries by chaining many tool calls over multiple reasoning steps, routinely accumulating hundreds of thousands...
arXiv:2608.29646v1 Announce Type: new Abstract: Large language model (LLM)-based agents have shown strong potential in solving complex tasks through multi-step reasoning, yet they remain vulnerable t...
arXiv:2608.29880v1 Announce Type: new Abstract: Open-world geo-localization requires models to reason over ambiguous visual cues through multi-step reasoning and external knowledge grounding. While r...
arXiv:2608.29953v1 Announce Type: new Abstract: Flat retrieval-augmented generation treats a corpus as a bag of chunks, discarding document hierarchy and cross document structure. We introduce Search...
arXiv:2608.30650v1 Announce Type: new Abstract: LLM agents need to sustain goal-consistent reasoning across long multi-turn interactions under strict resource constraints. However, as the multi-turn...
arXiv:2608.30676v1 Announce Type: new Abstract: When medical AI systems hallucinate clinical reasoning, the consequences extend beyond incorrect answers: fabricated justifications that superficially...
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....
arXiv:2608.30897v1 Announce Type: new Abstract: World models are becoming core infrastructure for embodied intelligence, with action-conditioned video generation providing controllable predictions of...
arXiv:2608.31057v1 Announce Type: new Abstract: Agent working memory is heterogeneous. Objects such as instructions, artifacts, tool outputs, and agent-generated state play different semantic roles a...
arXiv:2608.31082v1 Announce Type: new Abstract: Valuable data remains embedded in unstructured sources: web pages, reports, contracts, filings, earnings calls, and PDFs. The big bet in enterprise AI...
arXiv:2202.06853v2 Announce Type: cross Abstract: To help facilitate a variety of simulations related to healthcare facilities in North Carolina, we have developed an agent-based model (ABM) to accur...
arXiv:2608.28609v1 Announce Type: cross Abstract: A personalized agent needs a user memory: a persistent model of who its user is. Today it is almost always text -- transcripts and captions retrieved...
arXiv:2608.30709v1 Announce Type: cross Abstract: Railway foreign object detection (RFOD) is critical to safe railway operation, yet scarce real positive samples incompletely represent task-relevant...