Research Papers 论文研究 4h ago Updated 31m ago 更新于 31分钟前 47

SAGE: From Direct Answering to Evidence-Grounded Inference for Chinese Ancient Document Understanding SAGE:从直接回答到基于证据的推理——中文古籍理解

SAGE reformulates Chinese ancient document understanding as evidence-grounded inference rather than direct single-pass answer generation The framework coordinates specialized agents for task-aware planning, tool-mediated evidence acquisition, claim-level verification, and bounded replanning under a constrained shared-state runtime SAGE supports bounded evidence seeking, answer revision, and abstention when grounding is insufficient Experiments on the AncientDoc benchmark show SAGE consistently o SAGE是一个基于证据的多智能体框架,将中文古籍理解从直接回答重构为基于证据的推理 框架协调专门化智能体进行任务感知规划、工具辅助证据获取、声明级验证和有界重规划 在AncientDoc基准测试上,SAGE配合Qwen3.5-9B超越更大的单体LVLM,证明结构化推理的价值 支持有界证据搜索、答案修订和证据不足时的拒绝回答机制,避免过度自信的错误输出 强调在复杂视觉-语言-历史推理任务中,证据 grounding 比单纯模型扩展更重要

62
Hot 热度
75
Quality 质量
65
Impact 影响力

Analysis 深度分析

TL;DR

  • SAGE reformulates Chinese ancient document understanding as evidence-grounded inference rather than direct single-pass answer generation
  • The framework coordinates specialized agents for task-aware planning, tool-mediated evidence acquisition, claim-level verification, and bounded replanning under a constrained shared-state runtime
  • SAGE supports bounded evidence seeking, answer revision, and abstention when grounding is insufficient
  • Experiments on the AncientDoc benchmark show SAGE consistently outperforms matched direct-answering baselines across three LVLM backbones
  • SAGE with Qwen3.5-9B surpasses much larger monolithic LVLMs on most evaluated metrics, demonstrating the value of structured inference beyond model scaling

Why It Matters

This work addresses a critical limitation in current LVLMs: their tendency to produce overconfident, weakly grounded responses when handling complex domain-specific tasks like ancient document understanding. By shifting from direct answer generation to evidence-grounded inference with multi-agent coordination, SAGE offers a scalable architecture that can achieve superior performance without requiring ever-larger models. This has broad implications for any domain where accuracy, traceability, and verifiability matter more than raw generation speed.

Technical Details

  • SAGE is a multi-agent framework that decomposes ancient document understanding into specialized agent roles: task-aware planning, tool-mediated evidence acquisition, claim-level verification, and bounded replanning
  • The system operates under a constrained shared-state runtime that enables bounded evidence seeking, iterative answer revision, and abstention when evidence grounding is insufficient
  • The approach is evaluated on the AncientDoc benchmark, testing across three different LVLM backbones with direct-answering baselines
  • Notably, SAGE powered by the relatively compact Qwen3.5-9B model outperforms much larger monolithic LVLMs on most metrics, indicating that structured reasoning architecture can compensate for model scale
  • The framework explicitly addresses the multimodal challenges of Chinese ancient documents, which require integrating visual, linguistic, and historical reasoning capabilities

Industry Insight

  • The results reinforce the growing consensus that architectural innovation in reasoning and verification can outperform brute-force model scaling, offering a cost-effective path to high-accuracy domain applications
  • The abstention mechanism—where the system can decline to answer when grounding is insufficient—is a critical design pattern for production systems where hallucination risk must be minimized, particularly in regulated or scholarly domains
  • The multi-agent, tool-mediated evidence acquisition approach generalizes beyond ancient documents to any domain requiring verifiable, traceable reasoning from complex multimodal inputs, such as legal document analysis, medical record interpretation, or scientific literature review

TL;DR

  • SAGE是一个基于证据的多智能体框架,将中文古籍理解从直接回答重构为基于证据的推理
  • 框架协调专门化智能体进行任务感知规划、工具辅助证据获取、声明级验证和有界重规划
  • 在AncientDoc基准测试上,SAGE配合Qwen3.5-9B超越更大的单体LVLM,证明结构化推理的价值
  • 支持有界证据搜索、答案修订和证据不足时的拒绝回答机制,避免过度自信的错误输出
  • 强调在复杂视觉-语言-历史推理任务中,证据 grounding 比单纯模型扩展更重要

为什么值得看

本文提出了一种将多智能体协作与证据驱动推理相结合的新范式,为复杂领域理解任务提供了可解释、可验证的解决方案。对于AI从业者而言,SAGE展示了如何通过结构化推理框架弥补单体大模型在专业领域中的幻觉和过度自信问题。

技术解析

  • 核心架构:SAGE采用多智能体协作框架,包含任务感知规划智能体、工具辅助证据获取智能体、声明级验证智能体,以及有界重规划智能体,在受约束的共享状态运行时环境中协同工作。
  • 推理范式转变:将古籍理解从"直接生成答案"重构为"基于证据的推理",支持有界证据搜索、答案修订和证据不足时的拒绝回答(abstention)。
  • 实验验证:在AncientDoc基准测试上,SAGE在三种LVLM骨干网络上均一致优于直接回答基线,其中Qwen3.5-9B配合SAGE在多数指标上超越更大的单体LVLM。
  • 关键洞察:研究表明,结构化、基于证据的推理框架可以弥补模型规模不足,在复杂视觉-语言-历史推理任务中实现更可靠、更可解释的输出。

行业启示

  • 多智能体框架正在成为解决复杂推理任务幻觉问题的有效路径,特别是在需要证据支撑的专业领域(如古籍、法律、医疗)。
  • 证据 grounding 和可验证推理应成为LVLM部署的重要考量,尤其在医疗、法律等高风险领域,拒绝回答机制比过度自信的错误输出更有价值。
  • 未来AI系统的设计应更注重推理过程的结构化和可解释性,而非单纯依赖模型规模扩展,这对资源受限场景下的模型部署具有指导意义。

Disclaimer: The above content is generated by AI and is for reference only. 免责声明:以上内容由 AI 生成,仅供参考。

Agent Agent Multimodal 多模态 Research 科学研究 LLM 大模型