Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2512.09944v4 Announce Type: replace Abstract: Echocardiography interpretation requires integrating multi-view temporal evidence with quantitative measurements and guideline-grounded reasoning,...
NoteVQA is a new benchmark that collects 252 real‑life visual questions from the Chinese image‑sharing platform Xiaohongshu, covering 12 topics and 7 user intents. Each question is paired with a concise expert reference and a human‑audited interleaved answer that blends text and visual evidence. The study evaluates VLMs on short‑answer correctness and interleaved answer quality using a new AgenticInterleave framework and a 12‑dimensional IVR‑12 rubric, finding that even state‑of‑the‑art models achieve only about 53% accuracy and lag behind human references in content quality.
arXiv:2609.14758v1 Announce Type: cross Abstract: Tool-augmented language models are evaluated on whether they reach the right answer, not on whether they report honestly when a tool fails to supply...
arXiv:2512.24565v4 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly serving as autonomous agents, and their utilization of external tools via the Model Context Protocol...
arXiv:2607.29397v3 Announce Type: replace Abstract: Deploying large language models in realistic server environments poses challenges, as the system needs to provide high-quality responses with low l...
arXiv:2407.02395v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used for program synthesis, yet they often generate code that is functionally plausible but ins...
arXiv:2606.17467v3 Announce Type: replace-cross Abstract: Prompt injection defenses evaluated on synthetic benchmarks do not generalize to real enterprise documents, which are longer, denser, and int...
arXiv:2609.13240v1 Announce Type: new Abstract: The AffectiveArt Multidimensional Art Emotion Understanding task asks to jointly predict an artwork's fine-grained emotion (12 classes, 1549:1 head-to-...
arXiv:2609.13294v1 Announce Type: new Abstract: Converting scientific graphics into editable representations remains a challenging problem for image-to-code generation because of their heterogeneous...
arXiv:2609.15161v1 Announce Type: cross Abstract: Large language model (LLM) driven multi-agent systems have shown promise in complex clinical reasoning, yet existing approaches rely on static strate...
arXiv:2609.15683v1 Announce Type: new Abstract: While In-Context Learning (ICL) enables models to adapt from exemplars without parameter updates, multimodal ICL remains largely underexplored, particu...
arXiv:2609.14829v1 Announce Type: cross Abstract: We introduce Enemray, a Hassaniya-centric language model that enables general-purpose interaction in Hassaniya. Enemray is trained around a stability...
arXiv:2510.25314v2 Announce Type: replace Abstract: High-fidelity large-field-of-view (LFOV) 3D sensing, essential for autonomous platforms, is hindered by the coupling of anisotropic off-axis aberra...
arXiv:2512.15971v2 Announce Type: replace Abstract: Multispectral object detection is critical for safety-sensitive applications such as autonomous driving and surveillance, where robust perception u...
arXiv:2605.28173v2 Announce Type: replace Abstract: End-to-end manga generation is a structured visual storytelling task that requires story decomposition, recurring character and scene grounding, pa...
arXiv:2609.13234v1 Announce Type: cross Abstract: Industrialized construction imposes stringent precision requirements on robotic assembly of modular components such as prefabricated window units. In...
arXiv:2609.13458v1 Announce Type: cross Abstract: Embodied language grounding requires more than identifying the referent of an instruction: recovered semantics must also control the action an agent...
arXiv:2609.14570v1 Announce Type: cross Abstract: Multi-agent LLM systems combine multiple inference calls, but prior work often confounds how calls are connected with how they are diversified. We st...
BusMA introduces a bus-based communication substrate for multi‑agent systems, enabling any agent to address others through a shared channel. The framework includes agent registration, message routing, and shared memory management, and defines four communication intents—discussion, challenge, guidance, and request for explanation—to facilitate fine‑grained interaction. Experiments with two leading LLMs on 13 tasks in visual reasoning, mathematical reasoning, and knowledge retrieval show that BusMA consistently outperforms existing hierarchical manager‑worker and router‑based message passing methods.
arXiv:2609.13422v1 Announce Type: new Abstract: LLM judges are increasingly used to evaluate and improve AI-generated outputs, yet their reliability for complex professional work remains unclear. We...