---
title: "面向时序知识图谱推理的本体-图谱双智能体强化学习方法 — 司悦航 2026"
description: "The paper addresses temporal knowledge graph (TKG) extrapolation, which means forecasting missing subjects or objects of quadruples at future timestamps."
authors: ["司悦航", "曾泽凡", "王博岩", "霍静", "高阳", "黄金才"]
year: 2026
venue: "计算机研究与发展 (Journal of Computer Research and Development)"
source: "https://crad.ict.ac.cn/article/doi/10.7544/issn1000-1239.202660408"
doi: "10.7544/issn1000-1239.202660408"
licence: "Free access (crad.ict.ac.cn), no open licence stated — readonly; © 计算机研究与发展"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/papers/si-2026-ontology-graph-dual/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/si-2026-ontology-graph-dual/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2026](https://md.research.elamur.ai/free/papers/2026/page/5/) / 面向时序知识图谱推理的本体-图谱双智能体强化学习方法

# 面向时序知识图谱推理的本体-图谱双智能体强化学习方法

**Authors:** 司悦航, 曾泽凡, 王博岩, 霍静, 高阳, 黄金才 · **Year:** 2026 · **Venue:** 计算机研究与发展 (Journal of Computer Research and Development) · **Licence:** Free access (crad.ict.ac.cn), no open licence stated — readonly; © 计算机研究与发展

**Links:** [Publisher's page](https://doi.org/10.7544/issn1000-1239.202660408) · [PDF](https://crad.ict.ac.cn/cn/article/pdf/preview/10.7544/issn1000-1239.202660408.pdf) · [DOI 10.7544/issn1000-1239.202660408](https://doi.org/10.7544/issn1000-1239.202660408)

## Summary
The paper addresses temporal knowledge graph (TKG) extrapolation, which means forecasting missing subjects or objects of quadruples at future timestamps. Existing reinforcement-learning (RL) path-search methods operate only on entities. As a result, their action spaces grow rapidly with path length and their paths lack concept-level logic. Ontologies could supply that logic, but they are usually built once from training-set counts and never revised. The authors propose ODRT, which pairs two cooperating agents. An upper ontology agent walks over a concept graph that mirrors the TKG. Its history state and suggested target concepts or relations softly guide a lower graph agent, which searches entity-level paths over historical snapshots under hierarchical soft rewards. The ontology is seeded by clustering entities using LLM semantic embeddings combined with structural embeddings from a pretrained TKG model. Its edge weights are then refined end-to-end during training. On four public benchmarks, ODRT outperforms all RL-based baselines and sets the state of the art on the two encyclopedic datasets. It still trails some embedding methods on event-style data, where reusing history matters most.

## Key points
- Concepts are obtained by clustering entities. Their features combine LLM text embeddings, projected down to the structural dimension, with embeddings from a pretrained TKG reasoner such as TTransE.
- The ontology graph (concepts, the original relation set, and aggregated concept-level facts) carries no timestamps. This filters out short-lived noise and keeps patterns that stay stable over time.
- During training, the entity-to-concept mapping stays fixed, and only learnable frequency weights on ontology edges are updated. These weights start as normalized training-set counts.
- Evaluation uses link prediction on 4 public TKG datasets. ODRT is best among RL methods (e.g., TITer-style baselines) and best overall on 2 encyclopedic datasets, but weaker than some embedding models on event-based data.
- The work was published in Journal of Computer Research and Development, 63(9): 2248–2263, 2026, by authors from the National University of Defense Technology and Nanjing University.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Linguistics & languages](https://md.research.elamur.ai/free/shelves/linguistics/) · [Natural language processing](https://md.research.elamur.ai/free/shelves/nlp/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@article{2026,
  title = {{面向时序知识图谱推理的本体-图谱双智能体强化学习方法}},
  author = {司悦航 and 曾泽凡 and 王博岩 and 霍静 and 高阳 and 黄金才},
  journal = {计算机研究与发展 (Journal of Computer Research and Development)},
  year = {2026},
  doi = {10.7544/issn1000-1239.202660408},
  url = {https://doi.org/10.7544/issn1000-1239.202660408}
}
```

- [← previous 面向小规模大语言模型推理优化的推理路径排序方法](https://md.research.elamur.ai/free/papers/li-2026-reasoning-path-ranking/)
- [next → 高效提升多模态大语言模型推理能力的级联强化学习策略](https://md.research.elamur.ai/free/papers/wang-2026-cascade-reinforcement-learning/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/papers/2026/page/5/)