pith. machine review for the scientific record. sign in

arxiv: 2604.26176 · v1 · submitted 2026-04-28 · 💻 cs.DB · cs.CL

Recognition: unknown

CacheRAG: A Semantic Caching System for Retrieval-Augmented Generation in Knowledge Graph Question Answering

Yushi Sun , Lei Chen
Authors on Pith no claims yet

Pith reviewed 2026-05-07 13:44 UTC · model grok-4.3

classification 💻 cs.DB cs.CL
keywords semantic cachingretrieval-augmented generationknowledge graph question answeringlarge language modelsplan cachingintermediate semantic representationmaximal marginal relevance
0
0 comments X

The pith

CacheRAG adds semantic caching to turn stateless LLM planners for knowledge graph questions into continual learners.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

Current LLM systems for answering questions over knowledge graphs generate retrieval plans from scratch for each query, much like a database that never reuses prior optimization work. This leads to repeated schema misunderstandings and incomplete information pulls. CacheRAG addresses the issue by storing successful past plans in a semantic cache and retrieving them for new questions. The system achieves this with three principles: an interface that lets users ask in plain language while safely adapting to the graph's structure, a retrieval method that favors structural variety among cached examples, and controlled expansion of searches that stays within fixed limits. If the approach works, LLM-based systems over structured data gain the ability to improve with repeated use rather than restarting every time.

Core claim

CacheRAG is a cache-augmented architecture for LLM-based KGQA that converts stateless planners into continual learners through a schema-agnostic ISR interface for natural-language interaction, a two-layer hierarchical index paired with MMR for diverse cached example retrieval, and deterministic bounded subgraph operators for safe recall improvement, yielding measurable gains in accuracy and truthfulness over baselines on standard benchmarks.

What carries the argument

The three design principles of schema-agnostic ISR interface, MMR-based diversity retrieval on Domain-to-Aspect index, and bounded heuristic subgraph expansion.

If this is right

  • Higher accuracy on knowledge graph question answering tasks.
  • Greater truthfulness in answers produced by the language model.
  • Fewer schema hallucinations during query planning.
  • Broader retrieval coverage achieved within strict computational bounds.
  • Safer translation of natural language questions into executable graph queries.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same caching pattern could extend to other retrieval-augmented generation settings to accumulate experience across sessions.
  • Diversity-focused retrieval may prove more useful than frequency-based methods when the goal is varied reasoning rather than simple repetition.
  • Systems built this way could handle gradual schema evolution in knowledge graphs without requiring complete resets.
  • Integration with existing database-style optimizers might further reduce the cost of initial plan generation.

Load-bearing premise

The three design principles can be put into practice without creating new failure modes or requiring extensive manual tuning of cache policies.

What would settle it

A benchmark run dominated by queries with low similarity to any cached examples, verifying whether accuracy and truthfulness fall back to non-cached baseline levels.

Figures

Figures reproduced from arXiv: 2604.26176 by Lei Chen, Yushi Sun.

Figure 1
Figure 1. Figure 1: Comparison of stateless LLM execution (baseline) and CacheRAG (our approach) on a KGQA task. (a) Input: natural view at source ↗
Figure 2
Figure 2. Figure 2: Illustration of retrieval path expansion for the running example. (a) Direct prompting: LLM incorrectly checks view at source ↗
Figure 3
Figure 3. Figure 3: The overall pipeline of CacheRAG, featuring a view at source ↗
Figure 4
Figure 4. Figure 4: The two-layer cache structure for multi-domain view at source ↗
Figure 5
Figure 5. Figure 5: Scalability Experiments. 5.11 Time and Memory Complexity and Scalability We analyze the time and memory complexity of CacheRAG us￾ing the formal bounds defined in Section 4. For semantic caching, the hierarchical index routing takes O (1) dictionary lookup time, while the MMR scheduling takes O (𝑏 log𝑏) time, utilizing O (𝑁) total space (where 𝑏 ≪ 𝑁 is the localized bucket size and 𝑁 is the global cache si… view at source ↗
Figure 6
Figure 6. Figure 6: The parameter 𝜆’s sensitivity of CacheRAG on CRAG dataset. • CBR [6]: CBR is a neuro-symbolic method. It retrieves similar question cases, reuses their logical form components, and revises the generated form using KB embeddings to handle complex KBQA and unseen relations. Note that since the API-based CRAG dataset does not support SPARQL querying, so we ran them only on SPARQL-based datasets. A.4 Parameter… view at source ↗
Figure 7
Figure 7. Figure 7: The multi-KG domain routing accuracy of different view at source ↗
read the original abstract

The integration of Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) has significantly advanced Knowledge Graph Question Answering (KGQA). However, existing LLM-driven KGQA systems act as stateless planners, generating retrieval plans in isolation without exploiting historical query patterns: analogous to a database system that optimizes every query from scratch without a plan cache. This fundamental design flaw leads to schema hallucinations and limited retrieval coverage. We propose CacheRAG, a systematic cache-augmented architecture for LLM-based KGQA that transforms stateless planners into continual learners. Unlike traditional database plan caching (which optimizes for frequency), CacheRAG introduces three novel design principles tailored for LLM contexts: (1) Schema-agnostic user interface: A two-stage semantic parsing framework via Intermediate Semantic Representation (ISR) enables non-expert users to interact purely in natural language, while a Backend Adapter grounds the LLM with local schema context to compile executable physical queries safely. (2) Diversity-optimized cache retrieval: A two-layer hierarchical index (Domain $\rightarrow$ Aspect) coupled with Maximal Marginal Relevance (MMR) maximizes structural variety in cached examples, effectively mitigating reasoning homogeneity. (3) Bounded heuristic expansion: Deterministic depth and breadth subgraph operators with strict complexity guarantees significantly enhance retrieval recall without risking unbounded API execution. Extensive experiments on multiple benchmarks demonstrate that CacheRAG significantly outperforms state-of-the-art baselines (e.g., +13.2% accuracy and +17.5% truthfulness on the CRAG dataset).

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 0 minor

Summary. The paper proposes CacheRAG, a semantic caching architecture for LLM-based Knowledge Graph Question Answering (KGQA) that converts stateless planners into continual learners. It introduces three design principles: (1) a schema-agnostic two-stage semantic parsing framework using an Intermediate Semantic Representation (ISR) with a Backend Adapter for safe query compilation, (2) a two-layer hierarchical index (Domain → Aspect) combined with Maximal Marginal Relevance (MMR) for diversity-optimized cache retrieval, and (3) bounded heuristic expansion using deterministic depth and breadth subgraph operators with complexity guarantees. The central claim is that this system significantly outperforms state-of-the-art baselines, with reported gains of +13.2% accuracy and +17.5% truthfulness on the CRAG dataset across multiple benchmarks.

Significance. If the performance claims are substantiated by rigorous experiments, CacheRAG could meaningfully advance KGQA systems by adapting database-style plan caching to LLM contexts, addressing schema hallucinations and limited coverage through reuse of historical patterns. The emphasis on schema-agnostic interfaces and bounded operations is a practical strength for deployment, and the work bridges database caching concepts with semantic retrieval in a novel way.

major comments (1)
  1. §5 (or equivalent Experiments section): The abstract reports specific quantitative gains (+13.2% accuracy, +17.5% truthfulness on CRAG) but provides no description of the experimental protocol, baseline implementations, statistical significance tests, error analysis, or ablation studies. This absence is load-bearing for the central outperformance claim, as the gains cannot be verified or reproduced from the given information.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their thoughtful review and constructive feedback on our manuscript. We address the major comment below and commit to a substantial revision of the experimental section to ensure full transparency, reproducibility, and substantiation of our claims.

read point-by-point responses

  1. Referee: [—] §5 (or equivalent Experiments section): The abstract reports specific quantitative gains (+13.2% accuracy, +17.5% truthfulness on CRAG) but provides no description of the experimental protocol, baseline implementations, statistical significance tests, error analysis, or ablation studies. This absence is load-bearing for the central outperformance claim, as the gains cannot be verified or reproduced from the given information.

    Authors: We agree that the current description of the experimental protocol is insufficient to support the central performance claims. In the revised manuscript, we will substantially expand Section 5 (Experiments) to include: (1) a complete experimental protocol detailing datasets, evaluation metrics, hardware, and LLM configurations; (2) explicit descriptions of baseline implementations, including any adaptations made to ensure fair comparison; (3) statistical significance testing (e.g., paired t-tests or bootstrap methods with reported p-values and confidence intervals); (4) a dedicated error analysis section breaking down failure cases; and (5) comprehensive ablation studies isolating the contribution of each CacheRAG component (ISR parsing, hierarchical caching with MMR, and bounded expansion). These additions will enable verification and reproduction of the reported +13.2% accuracy and +17.5% truthfulness gains on CRAG and other benchmarks. revision: yes

Circularity Check

0 steps flagged

No significant circularity in derivation chain

full rationale

The paper describes a system architecture for CacheRAG with three design principles (schema-agnostic ISR, MMR-based retrieval, bounded heuristic expansion) and reports empirical performance gains on benchmarks such as CRAG. No equations, first-principles derivations, fitted parameters presented as predictions, or self-citation chains appear in the provided text. All central claims reduce to experimental outcomes rather than any definitional or self-referential reduction.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 1 invented entities

The central claim rests on the unstated premise that historical query patterns exist and are reusable without introducing new hallucinations, plus the assumption that MMR and bounded operators can be implemented with strict complexity guarantees.

axioms (1)
  • domain assumption Historical query patterns in KGQA are sufficiently similar to new queries that cached plans improve accuracy without additional verification steps.
    Implicit in the claim that stateless planners are a fundamental flaw and that caching transforms them into continual learners.
invented entities (1)
  • Intermediate Semantic Representation (ISR) no independent evidence
    purpose: Schema-agnostic translation layer between natural language and executable queries.
    Introduced as part of the two-stage parsing framework; no independent evidence supplied in abstract.

pith-pipeline@v0.9.0 · 5573 in / 1293 out tokens · 50118 ms · 2026-05-07T13:44:20.183890+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

38 extracted references · 18 canonical work pages · 3 internal anchors

  1. [1]

    Wikidata Query Blazegraph

    2022. Wikidata Query Blazegraph. Retrieved Nov 18, 2025 from https://github. com/wikimedia/wikidata-query-blazegraph?tab=readme-ov-file

    2022

  2. [2]

    Shubham Agarwal, Sai Sundaresan, Subrata Mitra, Debabrata Mahapatra, Archit Gupta, Rounak Sharma, Nirmal Joshua Kapu, Tong Yu, and Shiv Saini. 2025. Cache-craft: Managing chunk-caches for efficient retrieval-augmented genera- tion.Proceedings of the ACM on Management of Data3, 3 (2025), 1–28

    2025

  3. [3]

    Manuel Borroto, Francesco Ricca, Bernardo Cuteri, and Vito Barbara. 2022. SPARQL-QA enters the QALD challenge. InProceedings of the 7th Natural Lan- guage Interfaces for the Web of Data (NLIWoD) co-located with the 19th European Semantic Web Conference, Hersonissos, Greece, Vol. 3196. 25–31. https://ceur- ws.org/Vol-3196/paper3.pdf

    2022

  4. [5]

    Zi-Yuan Chen, Chih-Hung Chang, Yi-Pei Chen, Jijnasa Nayak, and Lun-Wei Ku. 2019. UHop: An Unrestricted-Hop Relation Extraction Framework for Knowledge-Based Question Answering. InProceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguis- tics: Human Language Technologies, Volume 1 (Long and Short Papers)...

    work page doi:10.18653/v1/n19-1031 2019

  5. [6]

    Rajarshi Das, Manzil Zaheer, Dung Thai, Ameya Godbole, Ethan Perez, Jay-Yoon Lee, Lizhen Tan, Lazaros Polymenakos, and Andrew Mccallum. 2021. Case-based Reasoning for Natural Language Queries over Knowledge Bases. InProceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 9594–9611. doi:10.18653/v1/2021.emnlp-main.755

    work page doi:10.18653/v1/2021.emnlp-main.755 2021

  6. [7]

    Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, et al. 2024. The llama 3 herd of models.arXiv preprint arXiv:2407.21783(2024). doi:10.48550/arXiv.2407.21783

    work page internal anchor Pith review doi:10.48550/arxiv.2407.21783 2024

  7. [8]

    Wolfgang Fahl, Tim Holzheim, Andrea Westerinen, Christoph Lange, and Stefan Decker. 2022. Getting and hosting your own copy of Wikidata.. InWikidata@ ISWC

    2022

  8. [9]

    Goetz Graefe and William J McKenna. 1993. The volcano optimizer generator: Ex- tensibility and efficient search. InProceedings of IEEE 9th international conference on data engineering. IEEE, 209–218

    1993

  9. [10]

    Yu Gu, Xiang Deng, and Yu Su. 2023. Don’t Generate, Discriminate: A Proposal for Grounding Language Models to Real-World Environments. InProceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 4928–4949. doi:10.18653/v1/2023.acl-long.270

    work page doi:10.18653/v1/2023.acl-long.270 2023

  10. [11]

    Yu Gu and Yu Su. 2022. ArcaneQA: Dynamic Program Induction and Con- textualized Encoding for Knowledge Base Question Answering. InProceedings of the 29th International Conference on Computational Linguistics. 1718–1731. https://aclanthology.org/2022.coling-1.148/

    2022

  11. [12]

    Xixin Hu, Xuan Wu, Yiheng Shu, and Yuzhong Qu. 2022. Logical form generation via multi-task learning for complex question answering over knowledge bases. InProceedings of the 29th International Conference on Computational Linguistics. 1687–1696. https://aclanthology.org/2022.coling-1.145/

    2022

  12. [13]

    Aaron Hurst, Adam Lerer, Adam P Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, et al. 2024. Gpt-4o system card.arXiv preprint arXiv:2410.21276(2024). doi:10.48550/arXiv. 2410.21276

    work page internal anchor Pith review doi:10.48550/arxiv 2024

  13. [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. InProceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 9237–9251. doi:10.18653/v1/2023.emnlp-main.574

    work page doi:10.18653/v1/2023.emnlp-main.574 2023

  14. [15]

    Chao Jin, Zili Zhang, Xuanlin Jiang, Fangyue Liu, Shufan Liu, Xuanzhe Liu, and Xin Jin. 2025. Ragcache: Efficient knowledge caching for retrieval-augmented generation.ACM Transactions on Computer Systems44, 1 (2025), 1–27

    2025

  15. [17]

    Yunshi Lan and Jing Jiang. 2020. Query Graph Generation for Answering Multi- hop Complex Questions from Knowledge Bases. InProceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 969–974. doi:10.18653/ v1/2020.acl-main.91

    2020

  16. [18]

    Yunshi Lan, Shuohang Wang, and Jing Jiang. 2019. Knowledge base question answering with topic units.(2019). InProceedings of the Twenty-Eighth Interna- tional Joint Conference on Artificial Intelligence. 5046–5052. https://www.ijcai. org/proceedings/2019/0701.pdf

    2019

  17. [19]

    Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Cheng- gang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, et al. 2024. Deepseek-v3 technical report.arXiv preprint arXiv:2412.19437(2024)

    work page internal anchor Pith review arXiv 2024

  18. [20]

    Hanwen Liu, Qihan Zhang, Ryan Marcus, and Ibrahim Sabek. 2025. Serag: Self- evolving rag system for query optimization. (2025)

    2025

  19. [21]

    Kangqi Luo, Fengli Lin, Xusheng Luo, and Kenny Zhu. 2018. Knowledge base question answering via encoding of complex query graphs. InProceedings of the 2018 conference on empirical methods in natural language processing. 2185–2194. doi:10.18653/v1/D18-1242

    work page doi:10.18653/v1/d18-1242 2018

  20. [22]

    Shengjie Ma, Chengjin Xu, Xuhui Jiang, Muzhi Li, Huaren Qu, Cehao Yang, Jiaxin Mao, and Jian Guo. 2025. Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation. InThe Thirteenth International Conference on Learning Representations. https: //openreview.net/forum?id=oFBu7qaZpS

    2025

  21. [23]

    Barlas Oguz, Xilun Chen, Vladimir Karpukhin, Stan Peshterliev, Dmytro Okhonko, Michael Schlichtkrull, Sonal Gupta, Yashar Mehdad, and Scott Yih. 2022. UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open- Domain Question Answering. InFindings of the Association for Computational Linguistics: NAACL 2022. 1535–1546. doi:10.1865...

    work page doi:10.18653/v1/2022.findings-naacl.115 2022

  22. [24]

    Jie Ouyang, Yucong Luo, Mingyue Cheng, Daoyu Wang, Shuo Yu, Qi Liu, and Enhong Chen. 2024. Revisiting the solution of meta kdd cup 2024: Crag.arXiv preprint arXiv:2409.15337(2024). https://openreview.net/forum?id=PUzLjWIgqC

    work page arXiv 2024

  23. [25]

    Yiheng Shu, Zhiwei Yu, Yuhan Li, Börje Karlsson, Tingting Ma, Yuzhong Qu, and Chin-Yew Lin. 2022. TIARA: Multi-grained Retrieval for Robust Question Answering over Large Knowledge Base. InProceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 8108–8121. doi:10.18653/v1/ 2022.emnlp-main.555

    work page doi:10.18653/v1/ 2022

  24. [26]

    Jiashuo Sun, Chengjin Xu, Lumingyuan Tang, Saizhuo Wang, Chen Lin, Yeyun Gong, Lionel Ni, Heung-Yeung Shum, and Jian Guo. 2024. Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph. InThe Twelfth International Conference on Learning Representations. https: //openreview.net/forum?id=nnVO1PvbTv

    2024

  25. [27]

    Alon Talmor and Jonathan Berant. 2018. The Web as a Knowledge-Base for Answering Complex Questions. InProceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), Marilyn Walker, Heng Ji, and Amanda Stent (Eds.). Association for Computational Linguis...

    work page doi:10.18653/v1/n18-1059 2018

  26. [28]

    Ricardo Usbeck, Xi Yan, Aleksandr Perevalov, Longquan Jiang, Julius Schulz, Angelie Kraft, Cedric Möller, Junbo Huang, Jan Reineke, Axel-Cyrille Ngonga Ngomo, Muhammad Saleem, and Andreas Both. 2023. QALD-10: The 10th chal- lenge on question answering over linked data.Semantic Web(2023). https: //api.semanticscholar.org/CorpusID:265577096

    2023

  27. [29]

    Yikuan Xia, Jiazun Chen, and Jun Gao. 2024. Winning Solution For Meta KDD Cup’24.arXiv preprint arXiv:2410.00005(2024). https://openreview.net/forum? id=oWNPeoP1uC

    work page arXiv 2024

  28. [30]

    Tianbao Xie, Chen Henry Wu, Peng Shi, Ruiqi Zhong, Torsten Scholak, Michihiro Yasunaga, Chien-Sheng Wu, Ming Zhong, Pengcheng Yin, Sida I Wang, et al. 2022. UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models. InProceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 602–6...

    work page doi:10.18653/v1/2022.emnlp- 2022

  29. [31]

    Silei Xu, Shicheng Liu, Theo Culhane, Elizaveta Pertseva, Meng-Hsi Wu, Sina Semnani, and Monica Lam. 2023. Fine-tuned LLMs Know More, Hallucinate Less with Few-Shot Sequence-to-Sequence Semantic Parsing over Wikidata. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 5778–5791. doi:10.18653/v1/2023.emnlp-main.353

    work page doi:10.18653/v1/2023.emnlp-main.353 2023

  30. [32]

    Ling Yang, Zhaochen Yu, Tianjun Zhang, Shiyi Cao, Minkai Xu, Wentao Zhang, Joseph E Gonzalez, and Bin Cui. 2024. Buffer of thoughts: Thought-augmented reasoning with large language models.Advances in Neural Information Processing Systems37 (2024), 113519–113544

    2024

  31. [33]

    Xiao Yang, Kai Sun, Hao Xin, Yushi Sun, Nikita Bhalla, Xiangsen Chen, Sajal Choudhary, Rongze Daniel Gui, Ziran Will Jiang, Ziyu Jiang, Lingkun Kong, Brian Moran, Jiaqi Wang, Yifan Ethan Xu, An Yan, Chenyu Yang, Eting Yuan, Hanwen Zha, Nan Tang, Lei Chen, Nicolas Scheffer, Yue Liu, Nirav Shah, Rakesh Wanga, Conference acronym ’XX, June 03–05, 2018, Woodst...

    work page arXiv 2018

  32. [34]

    Xi Ye, Semih Yavuz, Kazuma Hashimoto, Yingbo Zhou, and Caiming Xiong

  33. [35]

    InProceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

    RNG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering. InProceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 6032–6043. doi:10.18653/v1/2022.acl-long.417

    work page doi:10.18653/v1/2022.acl-long.417 2022

  34. [36]

    Scott Wen-tau Yih, Ming-Wei Chang, Xiaodong He, and Jianfeng Gao. 2015. Se- mantic parsing via staged query graph generation: Question answering with knowledge base. InProceedings of the Joint Conference of the 53rd Annual Meet- ing of the ACL and the 7th International Joint Conference on Natural Language Processing of the AFNLP. https://aclanthology.org/...

    2015

  35. [37]

    Wen-tau Yih, Matthew Richardson, Christopher Meek, Ming-Wei Chang, and Jina Suh. 2016. The value of semantic parse labeling for knowledge base question an- swering. InProceedings of the 54th Annual Meeting of the Association for Computa- tional Linguistics (Volume 2: Short Papers). 201–206. https://aclanthology.org/P16- 2033.pdf

    2016

  36. [38]

    Donghan Yu, Sheng Zhang, Patrick Ng, Henghui Zhu, Alexander Hanbo Li, Jun Wang, Yiqun Hu, William Yang Wang, Zhiguo Wang, and Bing Xiang. 2022. DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Bases. InThe Eleventh International Conference on Learning Representations. https://openreview.net/pdf?id=XHc5zRPxqV9

    2022

  37. [39]

    Jiayi Zhang, Jinyu Xiang, Zhaoyang Yu, Fengwei Teng, Xiong-Hui Chen, Jiaqi Chen, Mingchen Zhuge, Xin Cheng, Sirui Hong, Jinlin Wang, et al. 2025. AFlow: Automating Agentic Workflow Generation. InThe Thirteenth International Con- ference on Learning Representations

    2025

  38. [40]

    Initial KG descriptions

    Lingxi Zhang, Jing Zhang, Yanling Wang, Shulin Cao, Xinmei Huang, Cuiping Li, Hong Chen, and Juanzi Li. 2023. FC-KBQA: A Fine-to-Coarse Composition Framework for Knowledge Base Question Answering. InProceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 1002–1017. doi:10.18653/v1/2023.acl-long.57 C...

    work page doi:10.18653/v1/2023.acl-long.57 2023