Explainable Innovation Engine: Dual-Tree Agent-RAG with Methods-as-Nodes and Verifiable Write-Back

TL;DR

This paper introduces an explainable, controllable retrieval-augmented generation system that uses a hierarchical, traceable method-based knowledge structure with verification to enhance innovation and factual accuracy.

Contribution

It proposes a novel Dual-Tree Agent-RAG architecture with methods-as-nodes, provenance tracking, and verification, enabling explainable and verifiable multi-step synthesis.

Findings

Consistent performance improvements over baseline in six domains

Largest gains observed in derivation-heavy tasks

Effective pruning enhances quality and efficiency

Abstract

Retrieval-augmented generation (RAG) improves factual grounding, yet most systems rely on flat chunk retrieval and provide limited control over multi-step synthesis. We propose an Explainable Innovation Engine that upgrades the knowledge unit from text chunks to methods-as-nodes. The engine maintains a weighted method provenance tree for traceable derivations and a hierarchical clustering abstraction tree for efficient top-down navigation. At inference time, a strategy agent selects explicit synthesis operators (e.g., induction, deduction, analogy), composes new method nodes, and records an auditable trajectory. A verifier-scorer layer then prunes low-quality candidates and writes validated nodes back to support continual growth. Expert evaluation across six domains and multiple backbones shows consistent gains over a vanilla baseline, with the largest improvements on derivation-heavy settings, and ablations confirm the complementary roles of provenance backtracking and pruning. These results suggest a practical path toward controllable, explainable, and verifiable innovation in agentic RAG systems. Code is available at the project GitHub repository https://github.com/xiaolu-666113/Dual-Tree-Agent-RAG.