---
title: "TRN-R1-Zero — paper by Liu et al. (2026) — summary and ideas"
description: "The paper addresses zero-shot node classification on text-rich networks (TRNs). 41 references."
authors: ["Yilun Liu", "Ruihong Qiu", "Zi Huang"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.823/"
doi: "10.18653/v1/2026.acl-long.823"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/liu-2026-trn-r1-zero-text-rich/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/liu-2026-trn-r1-zero-text-rich/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/46/) / TRN-R1-Zero: Text-rich Network Reasoning via LLMs with Reinforcement Learning Only

# TRN-R1-Zero: Text-rich Network Reasoning via LLMs with Reinforcement Learning Only

**Authors:** [Yilun Liu](https://md.research.elamur.ai/free/en/authors/yilun-liu/), Ruihong Qiu and Zi Huang · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.acl-long.823/) · [PDF](https://aclanthology.org/2026.acl-long.823.pdf) · [DOI 10.18653/v1/2026.acl-long.823](https://doi.org/10.18653/v1/2026.acl-long.823) · [OpenAlex](https://openalex.org/W7166880989)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
The paper addresses zero-shot node classification on text-rich networks (TRNs). These are graphs whose nodes carry text, such as citation, hyperlink, social and co-purchase networks. Existing approaches fall short in different ways. GNNs need a fixed label set. Encoder-style LLM methods use the model only to produce embeddings. Recent reasoning-oriented methods distil chain-of-thought traces from large reasoning models.

TRN-R1-Zero instead post-trains a base LLM purely with reinforcement learning, with no SFT and no externally generated CoT. Each prompt contains the target node's text, a randomly sampled set of neighbour texts (capped by width and truncated by depth, which also acts as data augmentation) and the candidate labels. The model then reasons and outputs a class ID. Training uses a neighbour-aware variant of GRPO. A margin gain score estimates how much the neighbours actually help the prediction and rescales the advantage accordingly, which pushes the model toward relational reasoning.

Across the four TRN domains, the method transfers zero-shot to new domains and even to edge- and graph-level tasks after node-only training. It also produces much shorter reasoning than distillation-based rivals.

## Key points
- The pipeline is RL-only, unlike GraphWiz, Graph-NPH-R1 and Graph-R1, which rely on CoT data from larger models such as GPT-4, QwQ-32B or DeepSeek-R1.
- Against Graph-R1 (14B), the 7B TRN-R1-Zero scores higher accuracy on both benchmarks:
  - Cora: 72.59 vs 68.15.
  - WikiCS: 73.63 vs 73.25.
- Its reasoning traces are far shorter: about 153 vs 930 tokens on Cora and 129 vs 1129 on WikiCS.
- In a supervised setting it still beats GCN and LLaGA:
  - Citeseer: 77.74 vs 76.45 and 76.73.
  - History: 86.71 vs 84.23 and 85.56.
- The code is released at github.com/superallen13/TRN-R1-Zero. The authors note a limitation: RL gains are limited when the base LLM lacks the necessary domain knowledge from pre-training.

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

## Institutions

- [The University of Queensland](https://md.research.elamur.ai/free/en/universities/the-university-of-queensland/) — University, Brisbane, Australia · 14 works · 4,603 citations

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [⚛️ Physics and Astronomy](https://md.research.elamur.ai/free/en/shelves/physics-and-astronomy/) · 44 works · [⚛️ Statistical and Nonlinear Physics](https://md.research.elamur.ai/free/en/shelves/physics-and-astronomy/statistical-and-nonlinear-physics/) · 40 works

🧭 Topics (2): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works · [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,426 works

## Cite

Cite as: Yilun Liu, Ruihong Qiu and Zi Huang. 2026. TRN-R1-Zero: Text-rich Network Reasoning via LLMs with Reinforcement Learning Only. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

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

```bibtex
@inproceedings{liu2026trn,
  title = {{TRN-R1-Zero: Text-rich Network Reasoning via LLMs with Reinforcement Learning Only}},
  author = {Yilun Liu, Ruihong Qiu and Zi Huang},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.823},
  url = {https://doi.org/10.18653/v1/2026.acl-long.823}
}
```

- [← previous Triviality Corrected Endogenous Reward](https://md.research.elamur.ai/free/en/papers/wang-2026-triviality-corrected-endogenous-reward/)
- [next → Trustworthy and Explainable Causal Representation Learning in Transformers](https://md.research.elamur.ai/free/en/papers/liu-2026-trustworthy-explainable-causal-representation-learning/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/46/)

## References

41 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Mislav Balunovic, Jasper Dekoninck, Ivo Petrov, Nikola Jovanovic, and Martin T. Vechev. 2025. Matharena: Evaluating llms on uncontaminated math competitions. CoRR, abs/2505.23281. [find](https://scholar.google.com/scholar?q=Mislav+Balunovic%2C+Jasper+Dekoninck%2C+Ivo+Petrov%2C+Nikola+Jovanovic%2C+and+Martin+T%2E+Vechev%2E+2025%2E+Matharena%3A+Evaluating+llms+on+uncontaminated+math+competitions%2E+CoRR%2C+abs%2F2505%2E23281%2E)
2. Parishad BehnamGhader, Vaibhav Adlakha, Marius Mosbach, Dzmitry Bahdanau, Nicolas Chapados, and Siva Reddy. 2024. [LLM2vec: Large language models are secretly powerful text encoders](https://md.research.elamur.ai/free/en/papers/behnamghader-2024-llm2vec-large-language-models-secretly/). In COLM.
3. Nuo Chen, Yuhan Li, Jianheng Tang, and Jia Li. 2024a. Graphwiz: An instruction-following language model for graph computational problems. In KDD. [find](https://scholar.google.com/scholar?q=Nuo+Chen%2C+Yuhan+Li%2C+Jianheng+Tang%2C+and+Jia+Li%2E+2024a%2E+Graphwiz%3A+An+instruction%2Dfollowing+language+model+for+graph+computational+problems%2E+In+KDD%2E)
4. Runjin Chen, Tong Zhao, Ajay Kumar Jaiswal, Neil Shah, and Zhangyang Wang. 2024b. Llaga: Large language and graph assistant. In ICML. [find](https://scholar.google.com/scholar?q=Runjin+Chen%2C+Tong+Zhao%2C+Ajay+Kumar+Jaiswal%2C+Neil+Shah%2C+and+Zhangyang+Wang%2E+2024b%2E+Llaga%3A+Large+language+and+graph+assistant%2E+In+ICML%2E)
5. Zhaoling Chen, Robert Tang, Gangda Deng, Fang Wu, Jialong Wu, Zhiwei Jiang, Viktor K. Prasanna, Arman Cohan, and Xingyao Wang. 2025. [Locagent: Graph-guided LLM agents for code localization](https://md.research.elamur.ai/free/en/papers/chen-2025-locagent-graph-guided-llm-agents/). In ACL.
6. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. [BERT: pre-training of deep bidirectional transformers for language understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). In NAACL.
7. Yi Fang, Dongzhe Fan, Sirui Ding, Ninghao Liu, and Qiaoyu Tan. 2025. Uniglm: Training one unified language model for text-attributed graphs embedding. In WSDM. [find](https://scholar.google.com/scholar?q=Yi+Fang%2C+Dongzhe+Fan%2C+Sirui+Ding%2C+Ninghao+Liu%2C+and+Qiaoyu+Tan%2E+2025%2E+Uniglm%3A+Training+one+unified+language+model+for+text%2Dattributed+graphs+embedding%2E+In+WSDM%2E)
8. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Peiyi Wang, Qihao Zhu, Runxin Xu, Ruoyu Zhang, Shirong Ma, Xiao Bi, and 1 others. 2025. Deepseekr1 incentivizes reasoning in llms through reinforcement learning. Nature. [find](https://scholar.google.com/scholar?q=Daya+Guo%2C+Dejian+Yang%2C+Haowei+Zhang%2C+Junxiao+Song%2C+Peiyi+Wang%2C+Qihao+Zhu%2C+Runxin+Xu%2C+Ruoyu+Zhang%2C+Shirong+Ma%2C+Xiao+Bi%2C+and+1+others%2E+2025%2E+Deepseekr1+incentivizes+reasoning+in+llms+through+reinforceme)
9. Pengcheng He, Xiaodong Liu, Jianfeng Gao, and Weizhu Chen. 2021. [Deberta: decoding-enhanced bert with disentangled attention](https://md.research.elamur.ai/free/en/papers/he-2020-deberta-decoding-enhanced-bert-disentangled/). In ICLR.
10. Xiaoxin He, Xavier Bresson, Thomas Laurent, Adam Perold, Yann LeCun, and Bryan Hooi. 2024a. Harnessing explanations: LLM-to-LM interpreter for enhanced text-attributed graph representation learning. In ICLR. [find](https://scholar.google.com/scholar?q=Xiaoxin+He%2C+Xavier+Bresson%2C+Thomas+Laurent%2C+Adam+Perold%2C+Yann+LeCun%2C+and+Bryan+Hooi%2E+2024a%2E+Harnessing+explanations%3A+LLM%2Dto%2DLM+interpreter+for+enhanced+text%2Dattributed+graph+representation+learning%2E+I)
11. Xiaoxin He, Yijun Tian, Yifei Sun, Nitesh V. Chawla, Thomas Laurent, Yann LeCun, Xavier Bresson, and Bryan Hooi. 2024b. [G-retriever: Retrieval-augmented generation for textual graph understanding and question answering](https://md.research.elamur.ai/free/en/papers/he-2024-g-retriever-retrieval-augmented-generation/). In NeurIPS.
12. Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. [Lora: Low-rank adaptation of large language models](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/). In ICLR.
13. Hanxu Hu, Hongyuan Lu, Huajian Zhang, Yun-Ze Song, Wai Lam, and Yue Zhang. 2024. Chain-of-symbol prompting for spatial reasoning in large language models. In COLM. [find](https://scholar.google.com/scholar?q=Hanxu+Hu%2C+Hongyuan+Lu%2C+Huajian+Zhang%2C+Yun%2DZe+Song%2C+Wai+Lam%2C+and+Yue+Zhang%2E+2024%2E+Chain%2Dof%2Dsymbol+prompting+for+spatial+reasoning+in+large+language+models%2E+In+COLM%2E)
14. Xuanwen Huang, Kaiqiao Han, Yang Yang, Dezheng Bao, Quanjin Tao, Ziwei Chai, and Qi Zhu. 2024. Can GNN be good adapter for llms? In WWW. [find](https://scholar.google.com/scholar?q=Xuanwen+Huang%2C+Kaiqiao+Han%2C+Yang+Yang%2C+Dezheng+Bao%2C+Quanjin+Tao%2C+Ziwei+Chai%2C+and+Qi+Zhu%2E+2024%2E+Can+GNN+be+good+adapter+for+llms%3F+In+WWW%2E)
15. Carlos E Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik R Narasimhan. 2024. [SWE-bench: Can language models resolve real-world github issues?](https://md.research.elamur.ai/free/en/papers/jimenez-2024-swe-bench-can-language-models/) In ICLR.
16. Thomas N. Kipf and Max Welling. 2017. [Semi-supervised classification with graph convolutional networks](https://md.research.elamur.ai/free/en/papers/kipf-2016-semi-supervised-classification-graph-convolutional/). In ICLR.
17. Lecheng Kong, Jiarui Feng, Hao Liu, Chengsong Huang, Jiaxin Huang, Yixin Chen, and Muhan Zhang. 2024. Gofa: A generative one-for-all model for joint graph language modeling. In ICLR. [find](https://scholar.google.com/scholar?q=Lecheng+Kong%2C+Jiarui+Feng%2C+Hao+Liu%2C+Chengsong+Huang%2C+Jiaxin+Huang%2C+Yixin+Chen%2C+and+Muhan+Zhang%2E+2024%2E+Gofa%3A+A+generative+one%2Dfor%2Dall+model+for+joint+graph+language+modeling%2E+In+ICLR%2E)
18. Yuhan Li, Peisong Wang, Zhixun Li, Jeffrey Xu Yu, and Jia Li. 2024a. Zerog: Investigating cross-dataset zero-shot transferability in graphs. In KDD. [find](https://scholar.google.com/scholar?q=Yuhan+Li%2C+Peisong+Wang%2C+Zhixun+Li%2C+Jeffrey+Xu+Yu%2C+and+Jia+Li%2E+2024a%2E+Zerog%3A+Investigating+cross%2Ddataset+zero%2Dshot+transferability+in+graphs%2E+In+KDD%2E)
19. Yuhan Li, Peisong Wang, Xiao Zhu, Aochuan Chen, Haiyun Jiang, Deng Cai, Wai Kin (Victor) Chan, and Jia Li. 2024b. Glbench: A comprehensive benchmark for graph with large language models. In NeurIPS. [find](https://scholar.google.com/scholar?q=Yuhan+Li%2C+Peisong+Wang%2C+Xiao+Zhu%2C+Aochuan+Chen%2C+Haiyun+Jiang%2C+Deng+Cai%2C+Wai+Kin+%28Victor%29+Chan%2C+and+Jia+Li%2E+2024b%2E+Glbench%3A+A+comprehensive+benchmark+for+graph+with+large+language+models%2E+In+NeurIPS%2E)
20. Yilun Liu, Ruihong Qiu, and Zi Huang. 2023. Cat: Balanced continual graph learning with graph condensation. In ICDM. [find](https://scholar.google.com/scholar?q=Yilun+Liu%2C+Ruihong+Qiu%2C+and+Zi+Huang%2E+2023%2E+Cat%3A+Balanced+continual+graph+learning+with+graph+condensation%2E+In+ICDM%2E)
21. Yilun Liu, Ruihong Qiu, and Zi Huang. 2025a. Gcon-denser: Benchmarking graph condensation. In CIKM. [find](https://scholar.google.com/scholar?q=Yilun+Liu%2C+Ruihong+Qiu%2C+and+Zi+Huang%2E+2025a%2E+Gcon%2Ddenser%3A+Benchmarking+graph+condensation%2E+In+CIKM%2E)
22. Yilun Liu, Ruihong Qiu, Yanran Tang, Hongzhi Yin, and Zi Huang. 2025b. PUMA: efficient continual graph learning for node classification with graph condensation. TKDE. [find](https://scholar.google.com/scholar?q=Yilun+Liu%2C+Ruihong+Qiu%2C+Yanran+Tang%2C+Hongzhi+Yin%2C+and+Zi+Huang%2E+2025b%2E+PUMA%3A+efficient+continual+graph+learning+for+node+classification+with+graph+condensation%2E+TKDE%2E)
23. Zichen Liu, Changyu Chen, Wenjun Li, Penghui Qi, Tianyu Pang, Chao Du, Wee Sun Lee, and Min Lin. 2025c. [Understanding r1-zero-like training: A critical perspective](https://md.research.elamur.ai/free/en/papers/liu-2025-understanding-r1-zero-like-training/). arXiv preprint arXiv:2503.20783.
24. Nils Reimers and Iryna Gurevych. 2019. [Sentence-bert: Sentence embeddings using siamese bert-networks](https://md.research.elamur.ai/free/en/papers/reimers-2019-sentence-bert-sentence-embeddings-siamese/). In EMNLP.
25. John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. CoRR, abs/1707.06347. [find](https://scholar.google.com/scholar?q=John+Schulman%2C+Filip+Wolski%2C+Prafulla+Dhariwal%2C+Alec+Radford%2C+and+Oleg+Klimov%2E+2017%2E+Proximal+policy+optimization+algorithms%2E+CoRR%2C+abs%2F1707%2E06347%2E)
26. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Mingchuan Zhang, Y. K. Li, Y. Wu, and Daya Guo. 2024. [Deepseekmath: Pushing the limits of mathematical reasoning in open language models](https://md.research.elamur.ai/free/en/papers/shao-2024-deepseekmath-pushing-limits-mathematical-reasoning/). CoRR, abs/2402.03300.
27. Jiabin Tang, Yuhao Yang, Wei Wei, Lei Shi, Lixin Su, Suqi Cheng, Dawei Yin, and Chao Huang. 2024a. Graphgpt: Graph instruction tuning for large language models. In SIGIR. [find](https://scholar.google.com/scholar?q=Jiabin+Tang%2C+Yuhao+Yang%2C+Wei+Wei%2C+Lei+Shi%2C+Lixin+Su%2C+Suqi+Cheng%2C+Dawei+Yin%2C+and+Chao+Huang%2E+2024a%2E+Graphgpt%3A+Graph+instruction+tuning+for+large+language+models%2E+In+SIGIR%2E)
28. Yanran Tang, Ruihong Qiu, Yilun Liu, Xue Li, and Zi Huang. 2024b. Casegnn: Graph neural networks for legal case retrieval with text-attributed graphs. In ECIR. [find](https://scholar.google.com/scholar?q=Yanran+Tang%2C+Ruihong+Qiu%2C+Yilun+Liu%2C+Xue+Li%2C+and+Zi+Huang%2E+2024b%2E+Casegnn%3A+Graph+neural+networks+for+legal+case+retrieval+with+text%2Dattributed+graphs%2E+In+ECIR%2E)
29. Xixi Wu, Yifei Shen, Fangzhou Ge, Caihua Shan, Yizhu Jiao, Xiangguo Sun, and Hong Cheng. 2025a. When do LLMs help with node classification? a comprehensive analysis. In ICML. [find](https://scholar.google.com/scholar?q=Xixi+Wu%2C+Yifei+Shen%2C+Fangzhou+Ge%2C+Caihua+Shan%2C+Yizhu+Jiao%2C+Xiangguo+Sun%2C+and+Hong+Cheng%2E+2025a%2E+When+do+LLMs+help+with+node+classification%3F+a+comprehensive+analysis%2E+In+ICML%2E)
30. Xixi Wu, Yifei Shen, Caihua Shan, Kaitao Song, Siwei Wang, Bohang Zhang, Jiarui Feng, Hong Cheng, Wei Chen, Yun Xiong, and Dongsheng Li. 2024. Can graph learning improve planning in llm-based agents? In NeurIPS. [find](https://scholar.google.com/scholar?q=Xixi+Wu%2C+Yifei+Shen%2C+Caihua+Shan%2C+Kaitao+Song%2C+Siwei+Wang%2C+Bohang+Zhang%2C+Jiarui+Feng%2C+Hong+Cheng%2C+Wei+Chen%2C+Yun+Xiong%2C+and+Dongsheng+Li%2E+2024%2E+Can+graph+learning+improve+planning+in+llm%2Dbased+agents%3F+)
31. Yicong Wu, Guangyue Lu, Yuan Zuo, Huarong Zhang, and Junjie Wu. 2025b. Graph-r1: Incentivizing the zero-shot graph learning capability in llms via explicit reasoning. In EMNLP. [find](https://scholar.google.com/scholar?q=Yicong+Wu%2C+Guangyue+Lu%2C+Yuan+Zuo%2C+Huarong+Zhang%2C+and+Junjie+Wu%2E+2025b%2E+Graph%2Dr1%3A+Incentivizing+the+zero%2Dshot+graph+learning+capability+in+llms+via+explicit+reasoning%2E+In+EMNLP%2E)
32. Li Zhong, Zilong Wang, and Jingbo Shang. 2024. Debug like a human: A large language model debugger via verifying runtime execution step by step. In ACL. [find](https://scholar.google.com/scholar?q=Li+Zhong%2C+Zilong+Wang%2C+and+Jingbo+Shang%2E+2024%2E+Debug+like+a+human%3A+A+large+language+model+debugger+via+verifying+runtime+execution+step+by+step%2E+In+ACL%2E)
33. Yanran Tang, Ruihong Qiu, Yilun Liu, Xue Li, and Zi Huang. 2026. LEXA: legal case retrieval via graph contrastive learning with contextualised LLM embeddings. World Wide Web (WWW), 29(2):20. [find](https://scholar.google.com/scholar?q=Yanran+Tang%2C+Ruihong+Qiu%2C+Yilun+Liu%2C+Xue+Li%2C+and+Zi+Huang%2E+2026%2E+LEXA%3A+legal+case+retrieval+via+graph+contrastive+learning+with+contextualised+LLM+embeddings%2E+World+Wide+Web+%28WWW%29%2C+29%282%29%3A20%2E)
34. Yanran Tang, Ruihong Qiu, Hongzhi Yin, Xue Li, and Zi Huang. 2024c. Caselink: Inductive graph learning for legal case retrieval. In SIGIR. [find](https://scholar.google.com/scholar?q=Yanran+Tang%2C+Ruihong+Qiu%2C+Hongzhi+Yin%2C+Xue+Li%2C+and+Zi+Huang%2E+2024c%2E+Caselink%3A+Inductive+graph+learning+for+legal+case+retrieval%2E+In+SIGIR%2E)
35. Danny Wang, Ruihong Qiu, Guangdong Bai, and Zi Huang. 2025a. Text meets topology: Rethinking out-of-distribution detection in text-rich networks. In EMNLP. [find](https://scholar.google.com/scholar?q=Danny+Wang%2C+Ruihong+Qiu%2C+Guangdong+Bai%2C+and+Zi+Huang%2E+2025a%2E+Text+meets+topology%3A+Rethinking+out%2Dof%2Ddistribution+detection+in+text%2Drich+networks%2E+In+EMNLP%2E)
36. Duo Wang, Yuan Zuo, Fengzhi Li, and Junjie Wu. 2024. Llms as zero-shot graph learners: Alignment of gnn representations with llm token embeddings. NeurIPS. [find](https://scholar.google.com/scholar?q=Duo+Wang%2C+Yuan+Zuo%2C+Fengzhi+Li%2C+and+Junjie+Wu%2E+2024%2E+Llms+as+zero%2Dshot+graph+learners%3A+Alignment+of+gnn+representations+with+llm+token+embeddings%2E+NeurIPS%2E)
37. Haoyu Wang, Shikun Liu, Rongzhe Wei, and Pan Li. 2025b. Model generalization on text attribute graphs: Principles with large language models. In ICML. [find](https://scholar.google.com/scholar?q=Haoyu+Wang%2C+Shikun+Liu%2C+Rongzhe+Wei%2C+and+Pan+Li%2E+2025b%2E+Model+generalization+on+text+attribute+graphs%3A+Principles+with+large+language+models%2E+In+ICML%2E)
38. Heng Wang, Shangbin Feng, Tianxing He, Zhaoxuan Tan, Xiaochuang Han, and Yulia Tsvetkov. 2023. Can language models solve graph problems in natural language? In NeurIPS. [find](https://scholar.google.com/scholar?q=Heng+Wang%2C+Shangbin+Feng%2C+Tianxing+He%2C+Zhaoxuan+Tan%2C+Xiaochuang+Han%2C+and+Yulia+Tsvetkov%2E+2023%2E+Can+language+models+solve+graph+problems+in+natural+language%3F+In+NeurIPS%2E)
39. Yuyao Wang, Bowen Liu, Jianheng Tang, Nuo Chen, Yuhan Li, Qifan Zhang, and Jia Li. 2025c. Graph-r1: Unleashing LLM reasoning with np-hard graph problems. CoRR, abs/2508.20373. — [arXiv:2508.20373](https://arxiv.org/abs/2508.20373) [find](https://scholar.google.com/scholar?q=Yuyao+Wang%2C+Bowen+Liu%2C+Jianheng+Tang%2C+Nuo+Chen%2C+Yuhan+Li%2C+Qifan+Zhang%2C+and+Jia+Li%2E+2025c%2E+Graph%2Dr1%3A+Unleashing+LLM+reasoning+with+np%2Dhard+graph+problems%2E+CoRR%2C+abs%2F2508%2E20373%2E+%E2%80%94+%5BarXiv%3A2508%2E20373%5D%28htt)
40. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. 2022. [Chain-of-thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). In NeurIPS.
41. Felix Wu, Amauri H. Souza Jr., Tianyi Zhang, Christopher Fifty, Tao Yu, and Kilian Q. Weinberger. 2019. Simplifying graph convolutional networks. In ICML. [find](https://scholar.google.com/scholar?q=Felix+Wu%2C+Amauri+H%2E+Souza+Jr%2E%2C+Tianyi+Zhang%2C+Christopher+Fifty%2C+Tao+Yu%2C+and+Kilian+Q%2E+Weinberger%2E+2019%2E+Simplifying+graph+convolutional+networks%2E+In+ICML%2E)

*Updated 1 November 2026*