---
title: "Thought-Action Graph Reasoning — paper by Qi et al. (2026)"
description: "The authors propose the Thought-Action Graph (TAG), a two-layer store of reasoning experience. 65.7 F1 on WebQSP. 45 references."
authors: ["Zhixiao Qi", "Feng Huang", "Yunqi Zhang", "Shijie Zhang", "Qingqing Sun", "Yongfeng Huang", "Minghu Jiang", "Shuai Chen", "Tianyi Zhang"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.1572/"
doi: "10.18653/v1/2026.findings-acl.1572"
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/qi-2026-thought-action-graph-reasoning-faithful/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/qi-2026-thought-action-graph-reasoning-faithful/)

[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/45/) / Thought-Action Graph Reasoning: Faithful and Efficient Reasoning of Large Language Models via Reusing Past Experience

# Thought-Action Graph Reasoning: Faithful and Efficient Reasoning of Large Language Models via Reusing Past Experience

**Authors:** Zhixiao Qi, Feng Huang, Yunqi Zhang, Shijie Zhang, Qingqing Sun, [Yongfeng Huang](https://md.research.elamur.ai/free/en/authors/yongfeng-huang/), Minghu Jiang, Shuai Chen and [Tianyi Zhang](https://md.research.elamur.ai/free/en/authors/tianyi-zhang/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/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.findings-acl.1572/) · [PDF](https://aclanthology.org/2026.findings-acl.1572.pdf) · [DOI 10.18653/v1/2026.findings-acl.1572](https://doi.org/10.18653/v1/2026.findings-acl.1572) · [OpenAlex](https://openalex.org/W7166810286)

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

## Summary
LLMs used for knowledge graph question answering (KGQA) often hallucinate. Existing KG-augmented approaches have weaknesses. Retrieval-based pipelines generalize poorly to unfamiliar questions. Agent-based ones need many costly LLM calls. Both start every question from scratch and ignore earlier solutions. The authors propose the Thought-Action Graph (TAG), a two-layer store of reasoning experience. Successful LLM–KG trajectories are broken into small, semantically explicit operators. GPT-4o-mini converts gold SPARQL queries into meta-action-chains (MACs), which are then split into nodes and edges. The thought layer holds entities and ontology types, and the action layer holds operations like SELECT, triple patterns, FILTER and UNION. Their method, TAGR, works in two stages. It first retrieves and assembles MACs from TAG as blueprints. A fine-tuned LLM then executes them on a filtered Freebase subgraph. This moves expensive online exploration into offline retrieval and assembly. On WebQSP, CWQ and GrailQA, TAGR beats state-of-the-art baselines while using far fewer LLM calls and generated tokens. The result points toward KGQA systems that keep improving as they accumulate experience.

## Key points
- **Main scores:** TAGR reaches 93.2 Hits@1 / 65.7 F1 on WebQSP and 77.4 Hits@1 / 46.3 F1 on CWQ.
- **Ablations on KG filtering:** Without it, WebQSP Hits@1 falls to 72.4 and CWQ Hits@1 to 60.1.
- **Other ablations:** Using a reduced TAG or an unfine-tuned LLM also lowers scores, for example 86.6 and 82.2 WebQSP Hits@1.
- **Filtering and scaling:** KG filtering keeps only the top-k triples per MAC step, testing subgraphs of 200/100/50/25 triples against the original size of over 1K. Performance rises as TAG grows from WebQSP alone, to WebQSP plus CWQ, to WebQSP plus CWQ plus GrailQA training data.
- **Generalization and limitations:** Cross-dataset tests show no "diagonal advantage", suggesting strong out-of-distribution generalization. Acknowledged limitations are cold-start when little experience exists and linear, single-round execution of MACs. Code is available at github.com/THUqizx/Thought-Action_Graph_Reasoning.

*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

- [Tsinghua University](https://md.research.elamur.ai/free/en/universities/tsinghua-university/) — University, Beijing, China · 333 works · 87,019 citations
- [Beijing University of Posts and Telecommunications](https://md.research.elamur.ai/free/en/universities/beijing-university-of-posts-and-telecommunications/) — University, Beijing, China · 57 works · 32,843 citations
- [Ant Group](https://md.research.elamur.ai/free/en/companies/ant-group/) — Company, Hangzhou, China · 42 works · 1,131 citations

📚 Shelves (5): [🖥️ 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 · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 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: Zhixiao Qi, Feng Huang, Yunqi Zhang, Shijie Zhang, Qingqing Sun, Yongfeng Huang, Minghu Jiang, Shuai Chen and Tianyi Zhang. 2026. Thought-Action Graph Reasoning: Faithful and Efficient Reasoning of Large Language Models via Reusing Past Experience. Findings of the Association for Computational Linguistics: ACL 2026.

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

```bibtex
@inproceedings{qi2026thought,
  title = {{Thought-Action Graph Reasoning: Faithful and Efficient Reasoning of Large Language Models via Reusing Past Experience}},
  author = {Zhixiao Qi, Feng Huang, Yunqi Zhang, Shijie Zhang, Qingqing Sun, Yongfeng Huang, Minghu Jiang, Shuai Chen and Tianyi Zhang},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1572},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1572}
}
```

- [← previous ThinkVision at SemEval-2026 Task 6: A Transformer-Based Ensemble System for Clarity Detection](https://md.research.elamur.ai/free/en/papers/purohit-2026-thinkvision-semeval-2026-task-6/)
- [next → ThreadSumm: Summarization of Nested Discourse Threads Using Tree of Thoughts](https://md.research.elamur.ai/free/en/papers/olabisi-2026-threadsumm-summarization-nested-discourse-threads/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/45/)

## References

45 references, 17 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Maciej Besta, Nils Blach, Ales Kubicek, Robert Gerstenberger, Michal Podstawski, Lukas Gianinazzi, Joanna Gajda, Tomasz Lehmann, Hubert Niewiadomski, Piotr Nyczyk, and 1 others. 2024. Graph of thoughts: Solving elaborate problems with large language models. In Proceedings of the AAAI conference on a… [find](https://scholar.google.com/scholar?q=Maciej+Besta%2C+Nils+Blach%2C+Ales+Kubicek%2C+Robert+Gerstenberger%2C+Michal+Podstawski%2C+Lukas+Gianinazzi%2C+Joanna+Gajda%2C+Tomasz+Lehmann%2C+Hubert+Niewiadomski%2C+Piotr+Nyczyk%2C+and+1+others%2E+2024%2E+Graph+of+thought)
2. Kurt Bollacker, Colin Evans, Praveen Paritosh, Tim Sturge, and Jamie Taylor. 2008. Freebase: a collaboratively created graph database for structuring human knowledge. In Proceedings of the 2008 ACM SIG-MOD international conference on Management of data, pages 1247–1250. [find](https://scholar.google.com/scholar?q=Kurt+Bollacker%2C+Colin+Evans%2C+Praveen+Paritosh%2C+Tim+Sturge%2C+and+Jamie+Taylor%2E+2008%2E+Freebase%3A+a+collaboratively+created+graph+database+for+structuring+human+knowledge%2E+In+Proceedings+of+the+2008+ACM+SI)
3. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, and 1 others. 2020. [Language models are few-shot learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/). Advances in neural information processing systems, 33:1877–1901.
4. Mohammad Dehghan, Mohammad Alomrani, Sunyam Bagga, David Alfonso-Hermelo, Khalil Bibi, Abbas Ghaddar, Yingxue Zhang, Xiaoguang Li, Jianye Hao, Qun Liu, and 1 others. 2024. Ewek-qa: Enhanced web and efficient knowledge graph retrieval for citation-based question answering systems. In Proceedings of t… [find](https://scholar.google.com/scholar?q=Mohammad+Dehghan%2C+Mohammad+Alomrani%2C+Sunyam+Bagga%2C+David+Alfonso%2DHermelo%2C+Khalil+Bibi%2C+Abbas+Ghaddar%2C+Yingxue+Zhang%2C+Xiaoguang+Li%2C+Jianye+Hao%2C+Qun+Liu%2C+and+1+others%2E+2024%2E+Ewek%2Dqa%3A+Enhanced+web+and+ef)
5. Zixuan Dong, Baoyun Peng, Yufei Wang, Jia Fu, Xiaodong Wang, Xin Zhou, Yongxue Shan, Kangchen Zhu, and Weiguo Chen. 2025. Effiqa: Efficient question-answering with strategic multi-model collaboration on knowledge graphs. In Proceedings of the 31st International Conference on Computational Linguistic… [find](https://scholar.google.com/scholar?q=Zixuan+Dong%2C+Baoyun+Peng%2C+Yufei+Wang%2C+Jia+Fu%2C+Xiaodong+Wang%2C+Xin+Zhou%2C+Yongxue+Shan%2C+Kangchen+Zhu%2C+and+Weiguo+Chen%2E+2025%2E+Effiqa%3A+Efficient+question%2Danswering+with+strategic+multi%2Dmodel+collaboration+)
6. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, and 1 others. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). arXiv e-prints, pages arXiv–2407.
7. Yu Gu, Sue Kase, Michelle Vanni, Brian Sadler, Percy Liang, Xifeng Yan, and Yu Su. 2021. Beyond iid: three levels of generalization for question answering on knowledge bases. In Proceedings of the web conference 2021, pages 3477–3488. [find](https://scholar.google.com/scholar?q=Yu+Gu%2C+Sue+Kase%2C+Michelle+Vanni%2C+Brian+Sadler%2C+Percy+Liang%2C+Xifeng+Yan%2C+and+Yu+Su%2E+2021%2E+Beyond+iid%3A+three+levels+of+generalization+for+question+answering+on+knowledge+bases%2E+In+Proceedings+of+the+web)
8. Haoran Luo, Yikai Guo, Qika Lin, Xiaobao Wu, Xinyu Mu, Wenhao Liu, Meina Song, Yifan Zhu, Luu Anh Tuan, and 1 others. 2025a. Kbqa-o1: Agentic knowledge base question answering with monte carlo tree search. arXiv preprint arXiv:2501.18922. — [arXiv:2501.18922](https://arxiv.org/abs/2501.18922) [find](https://scholar.google.com/scholar?q=Haoran+Luo%2C+Yikai+Guo%2C+Qika+Lin%2C+Xiaobao+Wu%2C+Xinyu+Mu%2C+Wenhao+Liu%2C+Meina+Song%2C+Yifan+Zhu%2C+Luu+Anh+Tuan%2C+and+1+others%2E+2025a%2E+Kbqa%2Do1%3A+Agentic+knowledge+base+question+answering+with+monte+carlo+tree+se)
9. Haoyu Han, Yu Wang, Harry Shomer, Kai Guo, Jiayuan Ding, Yongjia Lei, Mahantesh Halappanavar, Ryan A Rossi, Subhabrata Mukherjee, Xianfeng Tang, and 1 others. 2025. Retrieval-augmented generation with graphs (graphrag). CoRR. [find](https://scholar.google.com/scholar?q=Haoyu+Han%2C+Yu+Wang%2C+Harry+Shomer%2C+Kai+Guo%2C+Jiayuan+Ding%2C+Yongjia+Lei%2C+Mahantesh+Halappanavar%2C+Ryan+A+Rossi%2C+Subhabrata+Mukherjee%2C+Xianfeng+Tang%2C+and+1+others%2E+2025%2E+Retrieval%2Daugmented+generation+with)
10. L Luo, YF Li, G Haffari, and S Pan. 2024a. Reasoning on graphs: Faithful and interpretable large language model reasoning. In ICLR 2024: The Twelfth International Conference on Learning Representations. ICLR. [find](https://scholar.google.com/scholar?q=L+Luo%2C+YF+Li%2C+G+Haffari%2C+and+S+Pan%2E+2024a%2E+Reasoning+on+graphs%3A+Faithful+and+interpretable+large+language+model+reasoning%2E+In+ICLR+2024%3A+The+Twelfth+International+Conference+on+Learning+Representation)
11. Xuming Hu, Junzhe Chen, Xiaochuan Li, Yufei Guo, Lijie Wen, Philip S Yu, and Zhijiang Guo. 2023. Do large language models know about facts? arXiv preprint arXiv:2310.05177. — [arXiv:2310.05177](https://arxiv.org/abs/2310.05177) [find](https://scholar.google.com/scholar?q=Xuming+Hu%2C+Junzhe+Chen%2C+Xiaochuan+Li%2C+Yufei+Guo%2C+Lijie+Wen%2C+Philip+S+Yu%2C+and+Zhijiang+Guo%2E+2023%2E+Do+large+language+models+know+about+facts%3F+arXiv+preprint+arXiv%3A2310%2E05177%2E+%E2%80%94+%5BarXiv%3A2310%2E05177%5D%28https%3A)
12. Linhao Luo, Zicheng Zhao, Gholamreza Haffari, Yuan-Fang Li, Chen Gong, and Shirui Pan. 2024b. Graph-constrained reasoning: Faithful reasoning on knowledge graphs with large language models. arXiv preprint arXiv:2410.13080. — [arXiv:2410.13080](https://arxiv.org/abs/2410.13080) [find](https://scholar.google.com/scholar?q=Linhao+Luo%2C+Zicheng+Zhao%2C+Gholamreza+Haffari%2C+Yuan%2DFang+Li%2C+Chen+Gong%2C+and+Shirui+Pan%2E+2024b%2E+Graph%2Dconstrained+reasoning%3A+Faithful+reasoning+on+knowledge+graphs+with+large+language+models%2E+arXiv+prep)
13. Jie Huang, Xinyun Chen, Swaroop Mishra, Huaixiu Steven Zheng, Adams Wei Yu, Xinying Song, and Denny Zhou. 2023. [Large language models cannot self-correct reasoning yet](https://md.research.elamur.ai/free/en/papers/huang-2023-large-language-models-cannot-self/). arXiv preprint arXiv:2310.01798.
14. Jinhao Jiang, Kun Zhou, Zican Dong, Keming Ye, Wayne Xin Zhao, and Ji-Rong Wen. 2023. Structgpt: A general framework for large language model to reason over structured data. arXiv preprint arXiv:2305.09645. [find](https://scholar.google.com/scholar?q=Jinhao+Jiang%2C+Kun+Zhou%2C+Zican+Dong%2C+Keming+Ye%2C+Wayne+Xin+Zhao%2C+and+Ji%2DRong+Wen%2E+2023%2E+Structgpt%3A+A+general+framework+for+large+language+model+to+reason+over+structured+data%2E+arXiv+preprint+arXiv%3A2305%2E)
15. Jinhao Jiang, Kun Zhou, Wayne Xin Zhao, Yang Song, Chen Zhu, Hengshu Zhu, and Ji-Rong Wen. 2025. [Kg-agent: An efficient autonomous agent framework for complex reasoning over knowledge graph](https://md.research.elamur.ai/free/en/papers/jiang-2025-kg-agent-efficient-autonomous-agent/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Pa…
16. Jinhao Jiang, Kun Zhou, Wayne Xin Zhao, and Ji-Rong Wen. 2022. Unikgqa: Unified retrieval and reasoning for solving multi-hop question answering over knowledge graph. arXiv preprint arXiv:2212.00959. [find](https://scholar.google.com/scholar?q=Jinhao+Jiang%2C+Kun+Zhou%2C+Wayne+Xin+Zhao%2C+and+Ji%2DRong+Wen%2E+2022%2E+Unikgqa%3A+Unified+retrieval+and+reasoning+for+solving+multi%2Dhop+question+answering+over+knowledge+graph%2E+arXiv+preprint+arXiv%3A2212%2E00959%2E)
17. Armand Joulin, Edouard Grave, Piotr Bojanowski, and Tomáš Mikolov. 2017. Bag of tricks for efficient text classification. In Proceedings of the 15th conference of the European chapter of the association for computational linguistics: volume 2, short papers, pages 427–431. [find](https://scholar.google.com/scholar?q=Armand+Joulin%2C+Edouard+Grave%2C+Piotr+Bojanowski%2C+and+Tom%C3%A1%C5%A1+Mikolov%2E+2017%2E+Bag+of+tricks+for+efficient+text+classification%2E+In+Proceedings+of+the+15th+conference+of+the+European+chapter+of+the+associati)
18. Kun Li, Tianhua Zhang, Xixin Wu, Hongyin Luo, James Glass, and Helen Meng. 2025. Decoding on graphs: Faithful and sound reasoning on knowledge graphs through generation of well-formed chains. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long P… [find](https://scholar.google.com/scholar?q=Kun+Li%2C+Tianhua+Zhang%2C+Xixin+Wu%2C+Hongyin+Luo%2C+James+Glass%2C+and+Helen+Meng%2E+2025%2E+Decoding+on+graphs%3A+Faithful+and+sound+reasoning+on+knowledge+graphs+through+generation+of+well%2Dformed+chains%2E+In+Proce)
19. Linhao Luo, Zicheng Zhao, Gholamreza Haffari, Dinh Phung, Chen Gong, and Shirui Pan. 2025b. Gfm-rag: graph foundation model for retrieval augmented generation. arXiv preprint arXiv:2502.01113. — [arXiv:2502.01113](https://arxiv.org/abs/2502.01113) [find](https://scholar.google.com/scholar?q=Linhao+Luo%2C+Zicheng+Zhao%2C+Gholamreza+Haffari%2C+Dinh+Phung%2C+Chen+Gong%2C+and+Shirui+Pan%2E+2025b%2E+Gfm%2Drag%3A+graph+foundation+model+for+retrieval+augmented+generation%2E+arXiv+preprint+arXiv%3A2502%2E01113%2E+%E2%80%94+%5BarXi)
20. Costas Mavromatis and George Karypis. 2022. Rearev: Adaptive reasoning for question answering over knowledge graphs. arXiv preprint arXiv:2210.13650. [find](https://scholar.google.com/scholar?q=Costas+Mavromatis+and+George+Karypis%2E+2022%2E+Rearev%3A+Adaptive+reasoning+for+question+answering+over+knowledge+graphs%2E+arXiv+preprint+arXiv%3A2210%2E13650%2E)
21. Costas Mavromatis and George Karypis. 2024. Gnn-rag: Graph neural retrieval for large language model reasoning. arXiv preprint arXiv:2405.20139. [find](https://scholar.google.com/scholar?q=Costas+Mavromatis+and+George+Karypis%2E+2024%2E+Gnn%2Drag%3A+Graph+neural+retrieval+for+large+language+model+reasoning%2E+arXiv+preprint+arXiv%3A2405%2E20139%2E)
22. OpenAI, :, Aaron Hurst, Adam Lerer, Adam P. Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, Aleksander M adry, Alex Baker-Whitcomb, Alex Beutel, Alex Borzunov, Alex Carney, Alex Chow, Alex Kirillov, and 401 others. 2024. [Gpt-4o system card](https://md.research.elamur.ai/free/en/papers/openai-2024-gpt-4o-system-card/).…
23. Shirui Pan, Linhao Luo, Yufei Wang, Chen Chen, Jiapu Wang, and Xindong Wu. 2024. [Unifying large language models and knowledge graphs: A roadmap](https://md.research.elamur.ai/free/en/papers/pan-2023-unifying-large-language-models-knowledge/). IEEE Transactions on Knowledge and Data Engineering, 36(7):3580–3599.
24. Boci Peng, Yun Zhu, Yongchao Liu, Xiaohe Bo, Haizhou Shi, Chuntao Hong, Yan Zhang, and Siliang Tang. 2024. [Graph retrieval-augmented generation: A survey](https://md.research.elamur.ai/free/en/papers/peng-2024-graph-retrieval-augmented-generation-survey/). ACM Transactions on Information Systems.
25. Shiyang Li, Yifan Gao, Haoming Jiang, Qingyu Yin, Zheng Li, Xifeng Yan, Chao Zhang, and Bing Yin. 2023. Graph reasoning for question answering with triplet retrieval. In ACL (Findings). [find](https://scholar.google.com/scholar?q=Shiyang+Li%2C+Yifan+Gao%2C+Haoming+Jiang%2C+Qingyu+Yin%2C+Zheng+Li%2C+Xifeng+Yan%2C+Chao+Zhang%2C+and+Bing+Yin%2E+2023%2E+Graph+reasoning+for+question+answering+with+triplet+retrieval%2E+In+ACL+%28Findings%29%2E)
26. Shuofei Qiao, Yixin Ou, Ningyu Zhang, Xiang Chen, Yunzhi Yao, Shumin Deng, Chuanqi Tan, Fei Huang, and Huajun Chen. 2023. [Reasoning with language model prompting: A survey](https://md.research.elamur.ai/free/en/papers/qiao-2022-reasoning-language-model-prompting-survey/). In Proceedings of the 61st annual meeting of the Association for Computational Linguistics (volume 1: long papers), pages 5368–…
27. Hunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. 2023. [Let’s verify step by step](https://md.research.elamur.ai/free/en/papers/lightman-2023-let-s-verify-step-step/). In The twelfth international conference on learning representations.
28. Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. 2023. [Direct preference optimization: Your language model is secretly a reward model](https://md.research.elamur.ai/free/en/papers/rafailov-2023-direct-preference-optimization-language-model/). Advances in neural information processing systems, 36:53728–53741.
29. John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv: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+arXiv+preprint+arXiv%3A1707%2E06347%2E)
30. Explore-on-graph: Incentivizing autonomous exploration of large language models on knowledge graphs with path-refined reward modeling. arXiv preprint arXiv:2602.21728. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, YK Li, and 1 others. 2024. Dee… — [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/)
31. An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, Chengpeng Li, Chengyuan Li, Dayiheng Liu, Fei Huang, Guanting Dong, Haoran Wei, Huan Lin, Jialong Tang, Jialin Wang, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Ma, and 40 others. 2024a. Qwen2 technical report. arXiv preprint arX… [find](https://scholar.google.com/scholar?q=An+Yang%2C+Baosong+Yang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chang+Zhou%2C+Chengpeng+Li%2C+Chengyuan+Li%2C+Dayiheng+Liu%2C+Fei+Huang%2C+Guanting+Dong%2C+Haoran+Wei%2C+Huan+Lin%2C+Jialong+Tang%2C+Jialin+Wang%2C+Jian+Yang%2C+Jian)
32. Xiangqing Shen, Fanfan Wang, and Rui Xia. 2025. Reason-align-respond: Aligning llm reasoning with knowledge graphs for kgqa. arXiv preprint arXiv:2505.20971. — [arXiv:2505.20971](https://arxiv.org/abs/2505.20971) [find](https://scholar.google.com/scholar?q=Xiangqing+Shen%2C+Fanfan+Wang%2C+and+Rui+Xia%2E+2025%2E+Reason%2Dalign%2Drespond%3A+Aligning+llm+reasoning+with+knowledge+graphs+for+kgqa%2E+arXiv+preprint+arXiv%3A2505%2E20971%2E+%E2%80%94+%5BarXiv%3A2505%2E20971%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs)
33. Jiashuo Sun, Chengjin Xu, Lumingyuan Tang, Saizhuo Wang, Chen Lin, Yeyun Gong, Lionel Ni, Heung-Yeung Shum, and Jian Guo. Think-on-graph: Deep and responsible reasoning of large language model on knowledge graph. In The Twelfth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Jiashuo+Sun%2C+Chengjin+Xu%2C+Lumingyuan+Tang%2C+Saizhuo+Wang%2C+Chen+Lin%2C+Yeyun+Gong%2C+Lionel+Ni%2C+Heung%2DYeung+Shum%2C+and+Jian+Guo%2E+Think%2Don%2Dgraph%3A+Deep+and+responsible+reasoning+of+large+language+model+on+know)
34. Alon Talmor and Jonathan Berant. 2018. [The web as a knowledge-base for answering complex questions](https://md.research.elamur.ai/free/en/papers/talmor-2018-web-as-knowledge-base-answering/). In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 641–651.
35. Qwen Team. 2024. Qwen2.5: A party of foundation models. [find](https://scholar.google.com/scholar?q=Qwen+Team%2E+2024%2E+Qwen2%2E5%3A+A+party+of+foundation+models%2E)
36. Guiyao Tie, Zeli Zhao, Dingjie Song, Fuyang Wei, Rong Zhou, Yurou Dai, Wen Yin, Zhejian Yang, Jiangyue Yan, Yao Su, and 1 others. 2025. A survey on post-training of large language models. arXiv e-prints, pages arXiv–2503. [find](https://scholar.google.com/scholar?q=Guiyao+Tie%2C+Zeli+Zhao%2C+Dingjie+Song%2C+Fuyang+Wei%2C+Rong+Zhou%2C+Yurou+Dai%2C+Wen+Yin%2C+Zhejian+Yang%2C+Jiangyue+Yan%2C+Yao+Su%2C+and+1+others%2E+2025%2E+A+survey+on+post%2Dtraining+of+large+language+models%2E+arXiv+e%2Dprin)
37. Keheng Wang, Feiyu Duan, Sirui Wang, Peiguang Li, Yunsen Xian, Chuantao Yin, Wenge Rong, and Zhang Xiong. 2023. Knowledge-driven cot: Exploring faithful reasoning in llms for knowledge-intensive question answering. arXiv preprint arXiv:2308.13259. — [arXiv:2308.13259](https://arxiv.org/abs/2308.13259) [find](https://scholar.google.com/scholar?q=Keheng+Wang%2C+Feiyu+Duan%2C+Sirui+Wang%2C+Peiguang+Li%2C+Yunsen+Xian%2C+Chuantao+Yin%2C+Wenge+Rong%2C+and+Zhang+Xiong%2E+2023%2E+Knowledge%2Ddriven+cot%3A+Exploring+faithful+reasoning+in+llms+for+knowledge%2Dintensive+quest)
38. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2022. [Self-consistency improves chain of thought reasoning in language models](https://md.research.elamur.ai/free/en/papers/wang-2022-self-consistency-improves-chain-thought/). arXiv preprint arXiv:2203.11171.
39. Zora Zhiruo Wang, Jiayuan Mao, Daniel Fried, and Graham Neubig. 2024. [Agent workflow memory](https://md.research.elamur.ai/free/en/papers/wang-2024-agent-workflow-memory/). arXiv preprint arXiv:2409.07429.
40. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, and 1 others. 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/). Advances in neural information processing systems, 35:24824– 24837.
41. Shiqi Yan, Yubo Chen, Ruiqi Zhou, Zhengxi Yao, Shuai Chen, Tianyi Zhang, Shijie Zhang, Wei Qiang Zhang, Yongfeng Huang, Haixin Duan, and 1 others. 2026. [find](https://scholar.google.com/scholar?q=Shiqi+Yan%2C+Yubo+Chen%2C+Ruiqi+Zhou%2C+Zhengxi+Yao%2C+Shuai+Chen%2C+Tianyi+Zhang%2C+Shijie+Zhang%2C+Wei+Qiang+Zhang%2C+Yongfeng+Huang%2C+Haixin+Duan%2C+and+1+others%2E+2026%2E)
42. Rui Yang, Haoran Liu, Edison Marrese-Taylor, Qingcheng Zeng, Yuhe Ke, Wanxin Li, Lechao Cheng, Qingyu Chen, James Caverlee, Yutaka Matsuo, and 1 others. 2024b. Kg-rank: Enhancing large language models for medical qa with knowledge graphs and ranking techniques. CoRR. [find](https://scholar.google.com/scholar?q=Rui+Yang%2C+Haoran+Liu%2C+Edison+Marrese%2DTaylor%2C+Qingcheng+Zeng%2C+Yuhe+Ke%2C+Wanxin+Li%2C+Lechao+Cheng%2C+Qingyu+Chen%2C+James+Caverlee%2C+Yutaka+Matsuo%2C+and+1+others%2E+2024b%2E+Kg%2Drank%3A+Enhancing+large+language+models)
43. Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. 2023. Tree of thoughts: Deliberate problem solving with large language models. Advances in neural information processing systems, 36:11809–11822. [find](https://scholar.google.com/scholar?q=Shunyu+Yao%2C+Dian+Yu%2C+Jeffrey+Zhao%2C+Izhak+Shafran%2C+Tom+Griffiths%2C+Yuan+Cao%2C+and+Karthik+Narasimhan%2E+2023%2E+Tree+of+thoughts%3A+Deliberate+problem+solving+with+large+language+models%2E+Advances+in+neural+inf)
44. Wen-tau Yih, Matthew Richardson, Christopher Meek, Ming-Wei Chang, and Jina Suh. 2016. [The value of semantic parse labeling for knowledge base question answering](https://md.research.elamur.ai/free/en/papers/yih-2016-value-semantic-parse-labeling-knowledge/). In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 201–206.
45. Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, and 1 others. 2023. [A survey of large language models](https://md.research.elamur.ai/free/en/papers/zhao-2023-survey-large-language-models/). arXiv preprint arXiv:2303.18223, 1(2).

*Updated 1 November 2026*