4 papers
-Reader: Dual Evolving Graphs for Multimodal Document QA
Yaxin Du, Junru Song, Yifan Zhou +8
Retrieval-augmented generation is a practical paradigm for question answering over long documents, but it remains brittle for multimodal reading where text, tables, and figures are…
SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents
Sheng Yin, Xianghe Pang, Yuanzhuo Ding +7
With the integration of large language models (LLMs), embodied agents have strong capabilities to understand and plan complicated natural language instructions. However, a foreseea…
VLMGuard-R1: Proactive Safety Alignment for VLMs via Reasoning-Driven Prompt Optimization
Menglan Chen, Xianghe Pang, Jingjing Dong +3
Aligning Vision-Language Models (VLMs) with safety standards is essential to mitigate risks arising from their multimodal complexity, where integrating vision and language unveils…
InfoMosaic-Bench: Evaluating Multi-Source Information Seeking in Tool-Augmented Agents
Yaxin Du, Yuanshuo Zhang, Xiyuan Yang +10
Information seeking is a fundamental requirement for humans. However, existing LLM agents rely heavily on open-web search, which exposes two fundamental weaknesses: online content…