Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2608. 07955v1 Announce Type: new Abstract: Large vision-language models have achieved strong performance in multimodal reasoning, but they remain unreliable on fine-grained spatial tasks that demand both precise spatial perception and fine-grained geometric computation beyond end-to-end generation.
arXiv:2608. 07994v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) is essential for enterprise knowledge question answering (QA), particularly in domains with complex product documentation like telecommunications.
arXiv:2608. 08061v1 Announce Type: new Abstract: The key question in moral judgement is not simply whether someone chooses the "right" answer, but how they decide what matters most when moral principles conflict.
arXiv:2608. 08146v1 Announce Type: new Abstract: The increasing complexity of enterprise business scenarios has promoted the widespread adoption of long SKILL documents in agent systems, posing new challenges for compliance detection: large models incur substantial inference costs, while small models may fail to maintain detection accuracy.
arXiv:2608. 08127v1 Announce Type: new Abstract: The runtime of Constraint Programming (CP) solvers is highly sensitive to modeling choices, such as symmetry breaking, implied constraints, global constraints, constraint reformulation, and variable representation.
arXiv:2608. 08236v1 Announce Type: new Abstract: Multi-agent LLM systems often fail not for lack of candidate answers, but because they have no persistent mechanism for deciding which incompatible claim should currently be trusted.
arXiv:2608. 08392v1 Announce Type: new Abstract: Large language models are increasingly deployed as autonomous agents that interact with the web through browsers.
arXiv:2608. 08445v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) is widely regarded as a novel paradigm born from the limitations of large language models (LLMs)--a mechanism to ground their outputs in external knowledge.
arXiv:2608. 08467v1 Announce Type: new Abstract: The Model Context Protocol (MCP) standardizes how servers expose data and tools to Large Language Models (LLMs).
arXiv:2608. 08570v1 Announce Type: new Abstract: Rejection sampling fine-tuning (RFT) is widely used to train code agents by generating trajectories on verifiable software engineering tasks, retaining those that pass the tests, and fine-tuning on the successful rollouts.
arXiv:2608. 09124v1 Announce Type: new Abstract: Temporal decisions in language-model systems often depend on both symbolic task state and elapsed wall-clock time, such as cache expiration, job completion, quota resets, deadlines, or stale sessions.
arXiv:2608. 09254v1 Announce Type: new Abstract: LLM analytics agents are evaluated on SQL syntax accuracy, but production failures look different: questions with two valid business definitions, questions the warehouse cannot answer, deprecated columns after a schema change, and queries that execute successfully while returning the wrong business number.
arXiv:2608. 09282v1 Announce Type: new Abstract: Real-world shopping often requires constructing a basket of complementary items rather than retrieving a single product.
arXiv:2608. 09480v1 Announce Type: new Abstract: A model alone does not determine how a programming agent acts.
arXiv:2608. 09537v1 Announce Type: new Abstract: Foundation world models have made remarkable progress in planning, simulation, and embodied intelligence.
arXiv:2608. 09885v1 Announce Type: new Abstract: The safety of large language model (LLM) agents depends not only on model weights but also on the agent harness that manages context, memory, tools, permissions, and runtime control.
arXiv:2608. 05235v1 Announce Type: cross Abstract: Research agents increasingly conduct multi-round machine-learning experiments in industrial recommendation settings and retain the resulting trajectories to guide later decisions.
arXiv:2608. 09902v1 Announce Type: new Abstract: We introduce the Dark Souls Learning Environment (DSLE), a containerized platform that presents all 22 boss encounters of Dark Souls: Remastered as game-playing agent benchmarks through a Gymnasium-style interface.
arXiv:2608. 07490v1 Announce Type: cross Abstract: Large language model agents are increasingly evaluated through games, but most benchmarks emphasize final outcomes rather than how players learn from repeated interaction.
arXiv:2608. 07527v1 Announce Type: cross Abstract: Long-document understanding requires models to find and combine evidence across many pages, layouts, tables, figures, and charts.