DocBench
PulseAugur coverage of DocBench — every cluster mentioning DocBench across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New DocSkill framework enhances multilingual document QA with adaptive reasoning
Researchers have introduced DocSkill, a new agentic framework designed to improve multilingual multi-hop document question answering. This framework utilizes a learned skill-orchestration policy to adaptively acquire an…
-
DocPilot framework enhances long visual document understanding with agentic training
Researchers have introduced DocPilot, a novel agentic framework designed to enhance the understanding of long and complex visual documents. This framework supports sophisticated orchestration of evidence gathering throu…
-
New TAP-RAG framework improves multimodal QA on long documents
Researchers have introduced TAP-RAG, a novel framework designed to enhance multimodal question answering over long documents. This system employs a Task-Aware Policy Controller (TAPC) that analyzes queries to determine …
-
New frameworks integrate vision, language, and graphs for AI
Two new research papers introduce frameworks for integrating multimodal data into graph learning and retrieval systems. The first, OMG-VLM, uses vision-language models to learn from graphs with heterogeneous text and im…
-
New framework learns to dynamically orchestrate AI retrievers for document reasoning
Researchers have developed a novel framework for multimodal document reasoning agents that learns to dynamically orchestrate various retrieval methods. This failure-driven evolution approach allows a meta-agent to adapt…
-
MARDoc framework enhances multimodal long document QA with structured memory
Researchers have introduced MARDoc, a novel framework designed to improve question answering for long, multimodal documents. This system utilizes three specialized agents: an Explorer for retrieval, a Refiner for proces…