Confidential — Stefan Michaelcheck Only

A Tale of Two Graphs: Separating Knowledge Exploration from Outline Structure for Open-Ended Deep Research

2026model innovationnovelmethod

Zhuofan Shi, Dongmei Zhang, Qingwei Lin, Saravan Rajmohan, Dongge Han, Jue Zhang, Fangkai Yang, Zekun Yao, Ming Ma, Victor Rühle

Open MIND

https://doi.org/10.48550/arxiv.2602.13830OpenAlex: W7129471046arXiv: 2602.13830
1
URLs Found
0
Internal Citations
10
Authors
usable
Abstract Quality
GPT-5.5 Abstract Analysis

Problems Identified (5)

OEDR evidence accumulation failures: Linear search-then-generate OEDR agents suffer lost-in-the-middle failures as accumulated evidence grows.

Outline-only knowledge gap detection: Outline-centric OEDR planning provides weak supervision for identifying missing relations and triggering targeted exploration.

Long-horizon evidence synthesis: Open-Ended Deep Research requires agents to iteratively search, connect, and synthesize evidence into structured reports.

OEDR evidence accumulation failures: Linear search-then-generate OEDR agents suffer lost-in-the-middle failures as accumulated evidence grows.

Outline-only knowledge gap detection: Outline-centric OEDR planning provides weak supervision for identifying missing relations and triggering targeted exploration.

Proposed Solutions (5)

DualGraph memory: DualGraph memory separates what the agent knows from how it writes by maintaining co-evolving outline and knowledge graphs.

Outline and knowledge graph separation: The method maintains an Outline Graph for structure and a Knowledge Graph as semantic memory storing fine-grained entities, concepts, and relations.

Topology-guided targeted search: DualGraph analyzes knowledge graph topology and outline graph structural signals to generate targeted search queries for iterative exploration and refinement.

DualGraph memory: DualGraph memory separates what the agent knows from how it writes by maintaining co-evolving outline and knowledge graphs.

Outline and knowledge graph separation: The method maintains an Outline Graph for structure and a Knowledge Graph as semantic memory storing fine-grained entities, concepts, and relations.

Results (3)

State-of-the-art benchmark gains:

DeepResearch Bench RACE score:

Dual-graph ablation support:

Research Domain

LLM agents for open-ended deep research

← Back to all papers