# SAGE: From Direct Answering to Evidence-Grounded Inference for Chinese Ancient Document Understanding

arXiv: https://arxiv.org/abs/2608.24011 · HTML: https://mlsanity.com/paper/2608.24011/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 19 references that are in the map.
- First posted on arXiv 25 Aug 2026.

## Builds on (most cited first, 12 of 12)

- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding](https://mlsanity.com/paper/2412.10302/) (2024)
- [MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations](https://mlsanity.com/paper/2407.01523/) (2024)
- [OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning](https://mlsanity.com/paper/2501.00321/) (2024)
- [Benchmarking Vision-Language Models on Chinese Ancient Documents: From OCR to Knowledge Reasoning](https://mlsanity.com/paper/2509.09731/) (2025)
- [AnchiBERT: A Pre-Trained Model for Ancient ChineseLanguage Understanding and Generation](https://mlsanity.com/paper/2009.11473/) (2020)
- [WenyanGPT: A Large Language Model for Classical Chinese Tasks](https://mlsanity.com/paper/2504.20609/) (2025)
- [AC-EVAL: Evaluating Ancient Chinese Language Understanding in Large Language Models](https://mlsanity.com/paper/2403.06574/) (2024)
- [F`ux`i: A Benchmark for Evaluating Language Models on Ancient Chinese Text Understanding and Generation](https://mlsanity.com/paper/2503.15837/) (2025)

## Abstract (arXiv)

Chinese ancient document understanding demands complex visual, linguistic, and historical reasoning. Current Large Vision-Language Models (LVLMs) typically rely on an opaque, single-pass generation paradigm, often producing overconfident and weakly grounded responses. To address this, we propose SAGE, an evidence-grounded multi-agent framework that reformulates Chinese ancient document understanding as evidence-grounded inference rather than direct answer generation. SAGE coordinates specialized agents for task-aware planning, tool-mediated evidence acquisition, claim-level verification, and bounded replanning under a constrained shared-state runtime. This design supports bounded evidence seeking, answer revision, and abstention when grounding is insufficient. Experiments on the AncientDoc benchmark show that SAGE consistently outperforms matched direct-answering baselines across three LVLM backbones. Remarkably, SAGE with Qwen3.5-9B surpasses much larger monolithic LVLMs on most evaluated metrics, highlighting the importance of structured, evidence-grounded inference beyond model scaling.