SAGE: From Direct Answering to Evidence-Grounded Inference for Chinese Ancient Document Understanding
Read the original on arXiv AI →SAGE is a multi‑agent framework that transforms Chinese ancient document understanding from direct answer generation into evidence‑grounded inference. It orchestrates specialized agents for planning, evidence acquisition, claim verification, and bounded replanning within a shared‑state runtime, enabling evidence seeking, answer revision, and abstention when grounding is lacking. Experiments on the AncientDoc benchmark show that SAGE outperforms direct‑answering baselines across three LVLM backbones, and even a 9B‑parameter Qwen3.5 model surpasses larger monolithic LVLMs, underscoring the value of structured, evidence‑grounded inference over mere model scaling.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.