The paper explores offline large language models as decision‑support tools for air operations, where analysts must work with doctrine and imagery under limited connectivity. It presents a modular retrieval‑augmented architecture that handles both text and image inputs from technical manuals and can operate without Internet access. A pilot study with four Brazilian Air Force image analysts shows the system matches human performance on doctrinal knowledge tests while completing the task in a fraction of the time, and it highlights the high cognitive load of manual target reporting.
arXiv:2604. 09552v2 Announce Type: replace-cross Abstract: Engineering rulebooks and technical standards contain multimodal information like dense text, tables, and illustrations that are challenging for retrieval augmented generation (RAG) systems.
arXiv:2607. 01829v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly proposed for aviation business operations, from documentation and training generation to customer facing assistants.
ATP‑Bench proposes a new benchmark for evaluating agentic tool planning in multimodal large language models (MLLMs) that generate interleaved text-and-image responses. The benchmark contains 7,702 QA pairs, including 1,592 visual‑question‑answer pairs, across eight categories and 25 visual‑critical intents, all verified by humans. A Multi‑Agent MLLM‑as‑a‑Judge (MAM) system is introduced to assess tool‑call precision, missed opportunities, and overall response quality without relying on ground‑truth references.
WeAgent-MMSearch introduces a multimodal search agent that preserves retrieved images as persistent references, enabling the model to inspect, process, and cite them throughout a search trajectory. The system includes a harness (WeAgent-Harness), a post‑training method (FA‑GSPO) that recovers salvageable rollouts, and a new benchmark (VisTarget‑Bench) to evaluate image‑retrieval versus visual‑perception failures. Evaluation shows that agentic post‑training boosts performance by 19.22 points, allowing the model to outperform similarly sized open‑source models and compete with much larger ones.
arXiv:2607. 03233v1 Announce Type: cross Abstract: The rapid growth of publicly available digital information has rendered manual open-source intelligence (OSINT) analysis insufficient for modern intelligence, cybersecurity, and cyber investigation.
arXiv:2608. 06202v1 Announce Type: cross Abstract: Large language model (LLM) benchmark evaluations are routinely used to support claims about model safety, reliability, and deployment readiness.
SciDocBench is a workflow-centered benchmark for scientific document understanding that includes 124 expert-authored questions across seven capability groups and 19 subtasks in five scientific domains. Each question is evaluated under four conditions—English or Chinese, all-images-first or interleaved document representations—resulting in 496 evaluation instances. The benchmark is paired with SciDocIR, a typed evidence-graph representation, and SciDocDataset, a collection of 15K fine-tuning and 8K reinforcement-learning samples, forming an evaluation-to-training framework for scientific-document assistants.
The paper examines how skill representations influence selection in a multimodal video agent harness called Tinycloud. It compares two types of skill representations—tool-skills and workflow-skills—and two prompt surfaces—full inlined bodies and one-line listings—across three exposure regimes. The study finds that full autoload exposure consistently selects the correct skill, while partial exposure can cause lexical competition that misroutes tasks, highlighting that in-prompt exposure is not always beneficial.
arXiv:2507. 19634v4 Announce Type: replace-cross Abstract: Recent advances in large language models have laid the foundation for multimodal LLMs (MLLMs), which unify text, speech, and vision within a single framework.
MIRAGE is a controlled study that examines how multimodal personal agents use historical evidence when conversation state changes. The study keeps evidence, questions, and scoring constant while varying only the conversation state, then checks if agents can determine answerability, recover the correct source, and answer from it. Results across seven multimodal backbones show distinct failure regimes before and after compaction, heavy reliance on context continuity by open-weight models, and mixed effects of retrieval pressure on source attribution.
arXiv:2606. 05531v1 Announce Type: cross Abstract: Despite the rapid progress of Vision-Language Models (VLMs), the field lacks benchmarks that rigorously diagnose their true reasoning abilities and chart meaningful progress toward human-like multimodal intelligence.
arXiv:2605. 13527v3 Announce Type: replace Abstract: Reusable skills have become a core substrate for improving agent capabilities, yet most existing skill packages encode reusable behavior primarily as textual prompts, executable code, or learned routines.