pith. sign in

arxiv: 2605.23280 · v1 · pith:ZM5JKEKXnew · submitted 2026-05-22 · 💻 cs.DB

BCTuner: LLM-Guided Monte Carlo Tree Search for Efficient Blockchain Knob Tuning

Yaoyi Deng , Chongyang Tao , Mingxuan Li , Xuelian Lin , Han Sun , Mingchao Wan , Shuai Ma This is my paper

Pith reviewed 2026-05-25 02:40 UTC · model grok-4.3

classification 💻 cs.DB
keywords blockchain knob tuningLLM-guided searchMonte Carlo Tree Searchconfiguration optimizationHyperledger Fabricthroughput improvementpermissioned blockchainsadaptive pruning
0
0 comments X

The pith

LLM-guided Monte Carlo Tree Search tunes blockchain knobs to deliver up to 211% throughput gains using 8x fewer system interactions.

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

The paper establishes that organizing multi-source tuning knowledge for LLM reasoning over knob semantics and constraints, then using that to guide a Monte Carlo Tree Search over incremental configuration trajectories with adaptive pruning, produces more efficient tuning than prior methods. A sympathetic reader would care because each configuration trial requires full deployment and distributed benchmarking, so reducing the number of trials directly lowers the cost of finding high-performance settings in complex systems where knobs interact across the transaction pipeline. BCTuner builds configurations step by step rather than generating complete ones at once and discards low-potential branches before evaluation. If the central claim holds, the approach narrows the gap between high-level knob logic and the numerical search requirements of tuning tools.

Core claim

BCTuner organizes multi-source tuning knowledge to support LLM-based reasoning over knob semantics, constraints, and deployment context. It formulates tuning as a Monte Carlo Tree Search process over structured action trajectories, where configurations are incrementally constructed, validated, evaluated, and refined. BCTuner applies adaptive pruning to discard infeasible or low-potential branches before system evaluation. On Hyperledger Fabric and ChainMaker under diverse workloads and network settings, this yields up to 211.38% throughput improvement over default configurations, up to 20% better performance than the state-of-the-art tuning method, and up to 8x fewer interactions with the区块链

What carries the argument

LLM-guided Monte Carlo Tree Search over structured action trajectories that incrementally constructs and prunes configuration paths using knowledge-guided reasoning.

If this is right

  • Achieves up to 211.38% throughput improvement over default configurations.
  • Outperforms the state-of-the-art blockchain tuning method by up to 20% in performance.
  • Requires up to 8x fewer interactions with the blockchain system.
  • Demonstrates results on Hyperledger Fabric and ChainMaker across diverse workloads and network settings.

Where Pith is reading between the lines

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

  • The incremental trajectory construction could transfer to tuning other distributed systems where parameter couplings make isolated prediction difficult.
  • If the LLM component remains stable across model versions, the method may support repeated tuning as blockchain software evolves without rebuilding heuristics from scratch.
  • Adaptive pruning before evaluation might lower overall resource use in any search-based optimizer that faces expensive objective evaluations.

Load-bearing premise

LLM reasoning over knob semantics, constraints, and context produces reliable guidance for the search without introducing systematic errors that would require many additional real evaluations to correct.

What would settle it

A controlled experiment on the same Hyperledger Fabric and ChainMaker setups that measures BCTuner requiring more than one-eighth the interactions of the baseline method or failing to reach at least 20% higher performance than the prior state-of-the-art tuner.

Figures

Figures reproduced from arXiv: 2605.23280 by Chongyang Tao, Han Sun, Mingchao Wan, Mingxuan Li, Shuai Ma, Xuelian Lin, Yaoyi Deng.

Figure 1
Figure 1. Figure 1: System Overview of BCTuner. Formally, let 𝑠 denote a search state, where each state corre￾sponds to a configuration 𝐶, and let 𝑎 ∈ A denote a tuning action. We construct a search tree T, in which each node represents a state 𝑠, and each edge corresponds to an action that transforms one state into another. Applying action 𝑎𝑡 to state 𝑠𝑡 yields the next state 𝑠𝑡+1 = 𝛿 (𝑠𝑡 , 𝑎𝑡 ), where 𝛿 denotes the state tr… view at source ↗
Figure 2
Figure 2. Figure 2: Tuning performance comparison under the Small￾Bank workload across different network architectures [PITH_FULL_IMAGE:figures/full_fig_p009_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Tuning performance comparison under the Simple workload across different network architectures. lines denote the median TPS, and the shaded regions show the observed TPS fluctuation across the three runs. 5.2 Tuning Effectiveness and Efficiency This subsection evaluates the proposed method BCTuner against Default, GPTuner, Athena, SMAC, and GP under different work￾loads and Fabric network architectures to … view at source ↗
Figure 4
Figure 4. Figure 4: Tuning performance comparison on ChainMaker [PITH_FULL_IMAGE:figures/full_fig_p011_4.png] view at source ↗
read the original abstract

Knob tuning plays a critical role in improving the performance of permissioned blockchains. However, efficient tuning remains challenging due to the architectural complexity of blockchains and the semantic gap between knob-specific logic and the numerical optimization requirements of tuning tools. In addition, configuration changes are often coupled across different stages of the transaction pipeline, making their performance impact difficult to isolate and predict. Since each trial requires deployment and distributed benchmarking, ineffective exploration incurs substantial cost. These challenges motivate BCTuner, a Large Language Model (LLM)-guided framework that combines knowledge-guided reasoning with structured search. BCTuner organizes multi-source tuning knowledge to support LLM-based reasoning over knob semantics, constraints, and deployment context. It formulates tuning as a Monte Carlo Tree Search (MCTS) process over structured action trajectories, where configurations are incrementally constructed, validated, evaluated, and refined rather than generated in one step. BCTuner further applies adaptive pruning to discard infeasible or low-potential branches before system evaluation. We evaluate BCTuner on Hyperledger Fabric and ChainMaker under diverse workloads and network settings. Experimental results show that BCTuner achieves up to 211.38% throughput improvement over default configurations and outperforms the state-of-the-art blockchain tuning method by up to 20% in performance, while requiring up to 8x fewer interactions with the blockchain system.

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

2 major / 0 minor

Summary. The paper introduces BCTuner, an LLM-guided Monte Carlo Tree Search framework for tuning configuration knobs in permissioned blockchains. It organizes multi-source tuning knowledge to enable LLM reasoning over knob semantics, constraints, and deployment context; formulates the tuning task as an MCTS process that incrementally constructs, validates, evaluates, and refines configurations via structured action trajectories; applies adaptive pruning of infeasible or low-potential branches; and evaluates the approach on Hyperledger Fabric and ChainMaker under diverse workloads and network settings. The central empirical claims are up to 211.38% throughput improvement over default configurations, up to 20% better performance than the state-of-the-art blockchain tuning method, and up to 8x fewer interactions with the blockchain system.

Significance. If the reported gains hold under rigorous validation, the work would be significant for practical blockchain systems engineering. It targets a genuine pain point—the high cost of each configuration trial due to deployment and distributed benchmarking—by combining semantic knowledge from LLMs with structured search and pruning, potentially making knob tuning more scalable than purely numerical or exhaustive methods.

major comments (2)
  1. [Abstract] Abstract: The headline efficiency claim (up to 8x fewer interactions) and performance gains (211.38% over default, 20% over SOTA) are load-bearing for the contribution, yet the text provides no ablation isolating the LLM component's effect on pruning accuracy, error rate, or evaluation count reduction; without such isolation it is impossible to confirm that LLM guidance produces net savings rather than requiring compensatory real evaluations.
  2. [Abstract] Abstract: The performance claims are presented without reference to any table, figure, workload definition, baseline implementation details, statistical tests, or variance measures, so it cannot be determined whether the reported numbers are supported by the data or generalize beyond the tested settings.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback on the presentation of our empirical results. We address each major comment below and outline targeted revisions to strengthen the manuscript.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The headline efficiency claim (up to 8x fewer interactions) and performance gains (211.38% over default, 20% over SOTA) are load-bearing for the contribution, yet the text provides no ablation isolating the LLM component's effect on pruning accuracy, error rate, or evaluation count reduction; without such isolation it is impossible to confirm that LLM guidance produces net savings rather than requiring compensatory real evaluations.

    Authors: We agree that an explicit ablation isolating the LLM guidance component is necessary to substantiate the efficiency claims. The current manuscript reports aggregate results of the full BCTuner framework but does not include a dedicated ablation comparing LLM-guided pruning against a non-LLM MCTS baseline on metrics such as pruning accuracy or interaction count. We will add this ablation study in the revised version, including quantitative results on error rates and evaluation savings attributable to the LLM. revision: yes

  2. Referee: [Abstract] Abstract: The performance claims are presented without reference to any table, figure, workload definition, baseline implementation details, statistical tests, or variance measures, so it cannot be determined whether the reported numbers are supported by the data or generalize beyond the tested settings.

    Authors: The abstract is a concise summary and therefore omits detailed references. The full manuscript details the experimental methodology in Section 5 (workloads: YCSB and Smallbank at varying rates; network settings; baseline implementations including defaults and the prior SOTA method), with supporting data in Tables 3–5 and Figures 4–7 that report means, standard deviations over 5 runs, and direct comparisons. We will revise the abstract to include brief pointers to these sections and add a note on statistical testing in the results discussion; due to abstract length limits, exhaustive details remain in the body. revision: partial

Circularity Check

0 steps flagged

No circularity: empirical performance claims rest on direct measurements

full rationale

The paper describes an LLM-guided MCTS framework for blockchain knob tuning and reports throughput gains from experiments on Hyperledger Fabric and ChainMaker. No equations, first-principles derivations, fitted parameters renamed as predictions, or self-citation load-bearing uniqueness theorems appear in the provided text. All central claims (211% improvement, 20% over SOTA, 8x fewer interactions) are presented as outcomes of system evaluations rather than quantities constructed by definition from the method's own inputs or prior self-citations. The derivation chain is therefore self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Only the abstract is available, so no explicit free parameters, axioms, or invented entities can be extracted; the central claims rest on unstated assumptions about LLM reliability and experimental validity that are not detailed.

pith-pipeline@v0.9.0 · 5794 in / 1163 out tokens · 23812 ms · 2026-05-25T02:40:26.443902+00:00 · methodology

discussion (0)

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

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

57 extracted references · 57 canonical work pages · 2 internal anchors

  1. [1]

    ChainMaker: A Next-Generation Permissioned Blockchain Platform

    2024. ChainMaker: A Next-Generation Permissioned Blockchain Platform. https: //chainmaker.org.cn/home. Accessed: 2026-04-22

    work page 2024

  2. [2]

    Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Floren- cia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report.arXiv preprint arXiv:2303.08774 (2023)

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  3. [3]

    Elli Androulaki, Artem Barger, Vita Bortnikov, Christian Cachin, Konstantinos Christidis, Angelo De Caro, David Enyeart, Christopher Ferris, Gennady Lavent- man, Yacov Manevich, et al. 2018. Hyperledger fabric: a distributed operating system for permissioned blockchains. InProceedings of the thirteenth EuroSys conference. 1–15

    work page 2018

  4. [4]

    Jason Ansel, Shoaib Kamil, Kalyan Veeramachaneni, Jonathan Ragan-Kelley, Jeffrey Bosboom, Una-May O’Reilly, and Saman Amarasinghe. 2014. Opentuner: An extensible framework for program autotuning. InProceedings of the 23rd international conference on Parallel architectures and compilation. 303–316

    work page 2014

  5. [5]

    Jiayuan Bai, Xuan-guang Pan, Chongyang Tao, and Shuai Ma. 2025. JudgeSQL: Reasoning over SQL Candidates with Weighted Consensus Tournament.arXiv preprint arXiv:2510.15560(2025)

    work page arXiv 2025

  6. [6]

    Yushi Bai, Xin Lv, Jiajie Zhang, Hongchang Lyu, Jiankai Tang, Zhidian Huang, Zhengxiao Du, Xiao Liu, Aohan Zeng, Lei Hou, et al . 2024. Longbench: A bilingual, multitask benchmark for long context understanding. InProceedings of the 62nd annual meeting of the association for computational linguistics (volume 1: Long papers). 3119–3137

    work page 2024

  7. [7]

    Bank for International Settlements. 2024. Project mBridge: Multi-CBDC Plat- form for Cross-Border Payments. https://www.bis.org/about/bisih/topics/cbdc/ mcbdc_bridge.htm. Accessed: 2026-04

    work page 2024

  8. [8]

    Alexander Bianchi, Rafael Dolores, Andrew Chai, Vincent Corvinelli, Parke Godfrey, Jarek Szlichta, and Calisto Zuzarte. 2025. Db2une: Tuning ibm db2 with deep learning. In2025 IEEE 41st International Conference on Data Engineering (ICDE). IEEE, 4540–4543

    work page 2025

  9. [9]

    Baoqing Cai, Yu Liu, Ce Zhang, Guangyu Zhang, Ke Zhou, Li Liu, Chunhua Li, Bin Cheng, Jie Yang, and Jiashu Xing. 2022. HUNTER: an online cloud database hybrid tuning system for personalized requirements. InProceedings of the 2022 International Conference on Management of Data. 646–659

    work page 2022

  10. [10]

    Stefano Cereda, Stefano Valladares, Paolo Cremonesi, Stefano Doni, et al. 2021. Cgptuner: a contextual gaussian process bandit approach for the automatic tuning of it configurations under varying workload conditions.Proceedings of the VLDB Endowment14, 8 (2021), 1401–1413

    work page 2021

  11. [11]

    Sibei Chen, Ju Fan, Bin Wu, Nan Tang, Chao Deng, Pengyi Wang, Ye Li, Jian Tan, Feifei Li, Jingren Zhou, and Xiaoyong Du. 2025. Automatic Database Configura- tion Debugging using Retrieval-Augmented Language Models.Proc. ACM Manag. Data3, 1, Article 13 (Feb. 2025), 27 pages. https://doi.org/10.1145/3709663

    work page doi:10.1145/3709663 2025

  12. [12]

    Coinbase. 2024. Coinbase: Institutional Digital Asset Custody and Exchange. https://www.coinbase.com/institutional. Accessed: 2026-04

    work page 2024

  13. [13]

    Tien Tuan Anh Dinh, Rui Liu, Meihui Zhang, Gang Chen, Beng Chin Ooi, and Ji Wang. 2018. Untangling Blockchain: A Data Processing View of Blockchain Systems.IEEE Transactions on Knowledge and Data Engineering30, 7 (2018), 1366–1385. https://doi.org/10.1109/TKDE.2017.2781227

    work page doi:10.1109/tkde.2017.2781227 2018

  14. [14]

    Songyun Duan, Vamsidhar Thummala, and Shivnath Babu. 2009. Tuning database configuration parameters with ituned.Proceedings of the VLDB Endowment2, 1 (2009), 1246–1257

    work page 2009

  15. [15]

    Jia-Ke Ge, Yan-Feng Chai, and Yun-Peng Chai. 2021. WATuning: a workload- aware tuning system with attention-based deep reinforcement learning.Journal of Computer Science and Technology36, 4 (2021), 741–761

    work page 2021

  16. [16]

    Victor Giannakouris and Immanuel Trummer. 2025. 𝜆-tune: Harnessing large language models for automated database system tuning.Proceedings of the ACM on Management of Data3, 1 (2025), 1–26

    work page 2025

  17. [17]

    Global Shipping Business Network. 2023. GSBN: Blockchain-Based Data In- frastructure for Global Supply Chains. https://www.gsbn.trade/. Accessed: 2026-04

    work page 2023

  18. [18]

    Christian Gorenflo, Stephen Lee, Lukasz Golab, and Srinivasan Keshav. 2020. Fast- Fabric: Scaling hyperledger fabric to 20 000 transactions per second.International Journal of Network Management30, 5 (2020), e2099

    work page 2020

  19. [19]

    Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Peiyi Wang, Qihao Zhu, Runxin Xu, Ruoyu Zhang, Shirong Ma, Xiao Bi, et al. 2025. DeepSeek-R1 incen- tivizes reasoning in LLMs through reinforcement learning.Nature645, 8081 (2025), 633–638

    work page 2025

  20. [20]

    Xinmei Huang, Haoyang Li, Jing Zhang, Xinxin Zhao, Zhiming Yao, Yiyan Li, Tieying Zhang, Jianjun Chen, Hong Chen, and Cuiping Li. 2025. E2ETune: End- to-End Knob Tuning via Fine-Tuned Generative Language Model.Proc. VLDB Endow.18, 13 (Sept. 2025), 5540–5554. https://doi.org/10.14778/3773731.3773732

    work page doi:10.14778/3773731.3773732 2025

  21. [21]

    Frank Hutter, Holger H Hoos, and Kevin Leyton-Brown. 2011. Sequential model- based optimization for general algorithm configuration. InInternational confer- ence on learning and intelligent optimization. Springer, 507–523

    work page 2011

  22. [22]

    Hyperledger. 2026. Hyperledger Caliper Documentation (v0.7.1). https:// hyperledger-caliper.github.io/caliper/0.7.1/. Accessed: 2026-04-28

    work page 2026

  23. [23]

    JPMorgan Chase. 2024. Tokenized Assets on Blockchain via Onyx Platform. https://www.jpmorgan.com/kinexys. Accessed: 2026-04

    work page 2024

  24. [24]

    Konstantinos Kanellis, Cong Ding, Brian Kroth, Andreas Müller, Carlo Curino, and Shivaram Venkataraman. 2022. LlamaTune: sample-efficient DBMS con- figuration tuning.Proc. VLDB Endow.15, 11 (July 2022), 2953–2965. https: //doi.org/10.14778/3551793.3551844

    work page doi:10.14778/3551793.3551844 2022

  25. [25]

    Levente Kocsis and Csaba Szepesvári. 2006. Bandit based monte-carlo planning. InEuropean conference on machine learning. Springer, 282–293

    work page 2006

  26. [26]

    Jiale Lao, Yibo Wang, Yufei Li, Jianping Wang, Yunjia Zhang, Zhiyuan Cheng, Wanghu Chen, Mingjie Tang, and Jianguo Wang. 2025. GPTuner: An LLM-Based Database Tuning System.ACM SIGMOD Record54, 1 (2025), 101–110

    work page 2025

  27. [27]

    Guoliang Li, Xuanhe Zhou, Shifu Li, and Bo Gao. 2019. Qtune: A query-aware database tuning system with deep reinforcement learning.Proceedings of the VLDB Endowment12, 12 (2019), 2118–2130

    work page 2019

  28. [28]

    Mingxuan Li, Yazhe Wang, Shuai Ma, Chao Liu, Dongdong Huo, Yu Wang, and Zhen Xu. 2023. Auto-Tuning with Reinforcement Learning for Permissioned Blockchain Systems.Proc. VLDB Endow.16, 5 (Jan. 2023), 1000–1012. https: //doi.org/10.14778/3579075.3579076

    work page doi:10.14778/3579075.3579076 2023

  29. [29]

    Yiyan Li, Haoyang Li, Jing Zhang, Renata Borovica-Gajic, Shuai Wang, Tieying Zhang, Jianjun Chen, Rui Shi, Cuiping Li, and Hong Chen. 2025. AgentTune: An Agent-Based Large Language Model Framework for Database Knob Tuning. Proceedings of the ACM on Management of Data3, 6 (2025), 1–29

    work page 2025

  30. [30]

    Zhaodonghui Li, Haitao Yuan, Huiming Wang, Gao Cong, and Lidong Bing

    work page

  31. [31]

    LLM-R2: A large language model enhanced rule-based rewrite system for boosting query efficiency.arXiv preprint arXiv:2404.12872(2024)

    work page arXiv 2024

  32. [32]

    Jie Liu and Barzan Mozafari. 2026. GenRewrite: Query Rewriting via Large Language Models.Proc. ACM Manag. Data4, 1, Article 70 (April 2026), 26 pages. https://doi.org/10.1145/3786684

    work page doi:10.1145/3786684 2026

  33. [33]

    Nelson F Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, and Percy Liang. 2024. Lost in the middle: How language models use long contexts.Transactions of the association for computational linguistics12 (2024), 157–173

    work page 2024

  34. [34]

    PGTune. 2014. PGTune: PostgreSQL Configuration Tuning Tool. https://pgtune. leopard.in.ua. Accessed: 2026-04-20

    work page 2014

  35. [35]

    Ripple. 2026. Ripple: Financial Infrastructure and Blockchain Solutions. https: //ripple.com/. Accessed: 2026-04

    work page 2026

  36. [36]

    Pingcheng Ruan, Tien Tuan Anh Dinh, Dumitrel Loghin, Meihui Zhang, Gang Chen, Qian Lin, and Beng Chin Ooi. 2021. Blockchains vs. distributed databases: Dichotomy and fusion. InProceedings of the 2021 International Conference on Management of Data. 1504–1517

    work page 2021

  37. [37]

    Ankur Sharma, Felix Martin Schuhknecht, Divya Agrawal, and Jens Dittrich

    work page

  38. [38]

    InProceedings of the 2019 International Conference on Management of Data

    Blurring the lines between blockchains and database systems: the case of hyperledger fabric. InProceedings of the 2019 International Conference on Management of Data. 105–122

    work page 2019

  39. [39]

    David G Sullivan, Margo I Seltzer, and Avi Pfeffer. 2004. Using probabilistic rea- soning to automate software tuning.ACM SIGMETRICS Performance Evaluation Review32, 1 (2004), 404–405

    work page 2004

  40. [40]

    Jian Tan, Tieying Zhang, Feifei Li, Jie Chen, Qixing Zheng, Ping Zhang, Honglin Qiao, Yue Shi, Wei Cao, and Rui Zhang. 2019. Ibtune: Individualized buffer tuning for large-scale cloud databases.Proc. VLDB Endow.12, 10 (2019), 1221–1234

    work page 2019

  41. [41]

    Reads the Manual

    Immanuel Trummer. 2022. DB-BERT: a Database Tuning Tool that" Reads the Manual". InProceedings of the 2022 international conference on management of data. 190–203

    work page 2022

  42. [42]

    Dana Van Aken, Andrew Pavlo, Geoffrey J Gordon, and Bohan Zhang. 2017. Automatic database management system tuning through large-scale machine learning. InProceedings of the 2017 ACM international conference on management of data. 1009–1024

    work page 2017

  43. [43]

    Dana Van Aken, Dongsheng Yang, Sebastien Brillard, Ari Fiorino, Bohan Zhang, Christian Bilien, and Andrew Pavlo. 2021. An inquiry into machine learning- based automatic configuration tuning services on real-world database manage- ment systems.Proceedings of the VLDB Endowment14, 7 (2021), 1241–1253

    work page 2021

  44. [44]

    Bing Wang, Changyu Ren, Jian Yang, Xinnian Liang, Jiaqi Bai, Linzheng Chai, Zhao Yan, Qian-Wen Zhang, Di Yin, Xing Sun, et al. 2025. MAC-SQL: A Multi- Agent Collaborative Framework for Text-to-SQL. InCOLING. 540–557

    work page 2025

  45. [45]

    Junxiong Wang, Immanuel Trummer, and Debabrota Basu. 2021. UDO: universal database optimization using reinforcement learning.Proc. VLDB Endow.14, 13 (Sept. 2021), 3402–3414. https://doi.org/10.14778/3484224.3484236

    work page doi:10.14778/3484224.3484236 2021

  46. [46]

    we.trade. 2023. we.trade: Blockchain-Based Trade Finance Platform. https://we- trade.com/. Accessed: 2026-04

    work page 2023

  47. [47]

    Xiwei Xu, Ingo Weber, Mark Staples, Liming Zhu, Jan Bosch, Len Bass, Cesare Pautasso, and Paul Rimba. 2017. A Taxonomy of Blockchain-Based Systems for Architecture Design. In2017 IEEE International Conference on Software Architec- ture (ICSA). 243–252. https://doi.org/10.1109/ICSA.2017.33

    work page doi:10.1109/icsa.2017.33 2017

  48. [48]

    Zihan Yan, Rui Xi, and Mengshu Hou. 2025. MCTuner: Spatial Decomposition- Enhanced Database Tuning via LLM-Guided Exploration.Proceedings of the ACM on Management of Data3, 6 (2025), 1–25

    work page 2025

  49. [49]

    An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, et al. 2025. Qwen3 technical 13 report.arXiv preprint arXiv:2505.09388(2025)

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  50. [50]

    Ji Zhang, Ke Zhou, Guoliang Li, Yu Liu, Ming Xie, Bin Cheng, and Jiashu Xing

    work page

  51. [51]

    CDBTune+: An efficient deep reinforcement learning-based automatic cloud database tuning system.The VLDB Journal30, 6 (2021), 959–987

    work page 2021

  52. [52]

    Xinyi Zhang, Hong Wu, Zhuo Chang, Shuowei Jin, Jian Tan, Feifei Li, Tieying Zhang, and Bin Cui. 2021. Restune: Resource oriented tuning boosted by meta- learning for cloud databases. InProceedings of the 2021 international conference on management of data. 2102–2114

    work page 2021

  53. [53]

    Xinyi Zhang, Hong Wu, Yang Li, Jian Tan, Feifei Li, and Bin Cui. 2022. Towards dynamic and safe configuration tuning for cloud databases. InProceedings of the 2022 International Conference on Management of Data. 631–645

    work page 2022

  54. [54]

    Xinyi Zhang, Hong Wu, Yang Li, Zhengju Tang, Jian Tan, Feifei Li, and Bin Cui

    work page

  55. [55]

    An efficient transfer learning based configuration adviser for database tuning.Proceedings of the VLDB Endowment17, 3 (2023), 539–552

    work page 2023

  56. [56]

    Xuanhe Zhou, Guoliang Li, Zhaoyan Sun, Zhiyuan Liu, Weize Chen, Jianming Wu, Jiesi Liu, Ruohang Feng, and Guoyang Zeng. 2024. D-Bot: Database Diagnosis System using Large Language Models.Proc. VLDB Endow.17, 10 (June 2024), 2514–2527. https://doi.org/10.14778/3675034.3675043

    work page doi:10.14778/3675034.3675043 2024

  57. [57]

    Yuqing Zhu, Jianxun Liu, Mengying Guo, Yungang Bao, Wenlong Ma, Zhuoyue Liu, Kunpeng Song, and Yingchun Yang. 2017. Bestconfig: tapping the perfor- mance potential of systems via automatic configuration tuning. InProceedings of the 2017 symposium on cloud computing. 338–350. 14

    work page 2017