Yuxin Zhang, Lu Chen, Kai Yu, Hanchong Zhang, Hanqi Li, Liangtai Sun, Tiancheng Huang, Ruisheng Cao, Zhangyi Kang, Shuai Fan, Yuxun Miao
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.
The increasing number of academic papers poses significant challenges for researchers to efficiently acquire key details. While retrieval augmented generation (RAG) shows great promise in large language model (LLM) based automated question answering, previous works often isolate neural and symbolic retrieval despite their complementary strengths. Moreover, conventional single-view chunking neglects the rich structure and layout of PDFs, e.g., sections and tables. In this work, we propose NeuSym-RAG, a hybrid neural symbolic retrieval framework which combines both paradigms in an interactive process. By leveraging multi-view chunking and schemabased parsing, NeuSym-RAG organizes semistructured PDF content into both the relational database and vectorstore, enabling LLM agents to iteratively gather context until sufficient to generate answers. Experiments on three full PDF-based QA datasets, including a self-annotated one AIRQA-REAL, show that NeuSym-RAG stably defeats both the vectorbased RAG and various structured baselines, highlighting its capacity to unify both retrieval schemes and utilize multiple views.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2505.19754")
get_code_for_paper("2505.19754")
have("2505.19754")
Connect an agent — have() is free.