Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2603. 29152v2 Announce Type: replace Abstract: Metal-organic frameworks (MOFs) offer a vast design space, and as such, computational simulations play a critical role in predicting their structural and physicochemical properties.
arXiv:2608. 01742v2 Announce Type: replace Abstract: Long-term memory is critical for LLM agents operating over long-horizon interactions.
arXiv:2608. 02009v2 Announce Type: replace Abstract: Retrieval-augmented search agents answer multi-hop questions by repeatedly issuing search queries and accumulating evidence.
arXiv:2504. 01407v3 Announce Type: replace-cross Abstract: Long video understanding poses a fundamental challenge for large video-language models (LVLMs) due to the overwhelming number of frames and the risk of losing essential context through naive downsampling.
arXiv:2510. 20748v2 Announce Type: replace-cross Abstract: This paper demonstrates how reinforcement learning can explain two puzzling empirical patterns in household consumption behavior during economic downturns.
arXiv:2608. 05102v1 Announce Type: new Abstract: Long-horizon search agents must make multiple sequential actions (steps) to search, retrieve, verify, and integrate evidence to reach a final answer.
arXiv:2604. 07341v2 Announce Type: replace-cross Abstract: Most repository-level code translation and validation techniques have been evaluated on a single source-target programming language (PL) pair, owing to the complex engineering effort required to adapt new PL pairs.
arXiv:2508. 16440v2 Announce Type: replace-cross Abstract: Urban Air Mobility (UAM) envisions the widespread use of small aerial vehicles to transform transportation in dense urban environments.
arXiv:2608. 04077v1 Announce Type: new Abstract: Evaluating financial AI agents requires criteria aligned with real professional work.
arXiv:2608. 04562v1 Announce Type: new Abstract: Agent skills are increasingly optimized by automated feedback loops, producing long structured artifacts whose internal value remains unclear.
arXiv:2608. 04053v1 Announce Type: cross Abstract: Prompt injection remains a critical threat to LLM agents, yet existing defenses treat each task as a self-contained problem, independent of previous encounters.
arXiv:2608. 04458v1 Announce Type: new Abstract: Agentic AI is emerging in datacenters, but its architectural implications remain unexplored.
arXiv:2602. 06052v4 Announce Type: replace-cross Abstract: Research in artificial intelligence is shifting from model innovations and benchmark scores towards problem definition and rigorous real-world evaluation.
arXiv:2608. 04625v1 Announce Type: new Abstract: Industrial recommendation strategy iteration heavily relies on large-scale A/B experimentation.
arXiv:2608. 04651v1 Announce Type: new Abstract: Advanced materials discovery increasingly relies on machine learning and Bayesian optimization to explore large discrete design spaces under limited evaluation budgets.
arXiv:2608. 04205v1 Announce Type: new Abstract: Human evaluation of AI systems and digital products is costly, slow, and difficult to scale.
arXiv:2508. 13661v4 Announce Type: replace Abstract: Centralized Training with Decentralized Execution (CTDE) is the dominant paradigm in multi-agent reinforcement learning (MARL), enabling agents to act independently at test time while leveraging additional information during training.
arXiv:2608. 04738v1 Announce Type: new Abstract: Autonomous research agents can generate hypotheses, execute experiments, and draft manuscripts, yet their outputs often contain unsupported claims and inconsistencies between research questions, experiments, results, and conclusions.
arXiv:2608. 05033v1 Announce Type: cross Abstract: Sparse matrix kernels are fundamental to scientific computing, graph analytics, and machine learning.
arXiv:2608. 04934v1 Announce Type: cross Abstract: Training LLM agents commonly relies on supervised fine-tuning from expert trajectories or online reinforcement learning over human-specified tasks with handcrafted verifiers.