Elamur Research⌕
☰
home / papers / 2026 / PExA: Parallel Exploration Agent for Complex Text-to-SQL

PExA: Parallel Exploration Agent for Complex Text-to-SQL

Paper · 2026 · Tanmay Parekh, Ella Hofmann-Coyle, Shuyi Wang et al.

Summary

LLM-based text-to-SQL agents usually trade speed for accuracy. Gains often come from long sequential reasoning, many tool calls and repeated self-correction, which slows interactive analytics. The authors borrow an idea from software testing. Instead of solving a complex question in one sequential pass, PExA builds a suite of small, self-contained SQL "test cases" that together cover the question's meaning. Some of these tests deliberately probe nearby database content beyond the literal query.

The system has three sub-agents:

  • a Planner, which designs tests and decides when there is enough evidence,
  • a Test Case Generator, which turns tests into SQL over a schema-linked, compressed database and runs them in parallel,
  • an SQL Proposer, which writes the final query from the test results alone.

Two tools support them: an SQL Executor and an LLM-based Semantic Verifier that back-translates SQL into natural language.

Because the tests run independently, latency depends on the slowest test rather than the sum of all of them. PExA reports a new state-of-the-art accuracy of 70.2% on Spider 2.0, with wall-time comparable to existing baselines.

Key points

  • Main result: 70.2% accuracy on Spider 2.0, reported as state of the art as of November 2025, achieved without any post-training of the base LLMs.
  • Three forms of parallelism:
    • diverse test planning in a single forward pass,
    • concurrent execution of test cases,
    • single-step multi-path search over candidate SQL.
  • Tool feedback: the SQL Executor reports compilation errors, NULL (empty-result) errors, or success with truncated results. Schema linking and database compression follow ReFoRCE.
  • Branching ablation: limiting search to a single branch drops execution accuracy by 4.5 points, from 42.9 unconstrained to 38.4. A modest limit costs only about 2–3% while reducing latency and cost.
  • Model comparisons and errors:
    • On 100-sample studies, GPT-o3 and GPT-5 work best; Claude Sonnet-4 handles planning well but is weaker at long-horizon SQL generation.
    • Most remaining errors come from semantic misreadings and flawed initial plans, not syntax mistakes.

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

🎓University of California, Los AngelesLos Angeles · United States87 works · 54,961 citations

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksComputer Networks and Communications · 64 works

🧭 Topics 2Research subjects and languages the work is about.Semantic parsing & meaning representation · 185 worksCode & programming languages · 129 works

Cite

Cite as Tanmay Parekh, Ella Hofmann-Coyle, Shuyi Wang, Sachith Sri Ram Kothur, Srivas Prasad and Yunmo Chen. 2026. PExA: Parallel Exploration Agent for Complex Text-to-SQL. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.acl-short.48

@inproceedings{parekh2026pexa,
  title = {{PExA: Parallel Exploration Agent for Complex Text-to-SQL}},
  author = {Tanmay Parekh, Ella Hofmann-Coyle, Shuyi Wang, Sachith Sri Ram Kothur, Srivas Prasad and Yunmo Chen},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-short.48},
  url = {https://doi.org/10.18653/v1/2026.acl-short.48}
}

References

71 references, 22 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Paul Ammann and Jeff Offutt. 2008. Introduction to Software Testing. Cambridge University Press. find
  2. Samuel David Arcadinho, David Aparicio, Hugo Veiga, and Antonio Alegria. 2022. T5QL: Taming language models for SQL generation. In Proceedings of the Second Workshop on Natural Language Generation, Evaluation, and Metrics (GEM), pages 276–286, Abu Dhabi, United Arab Emirates (Hybrid). Association fo… find
  3. Victor Barres, Honghua Dong, Soham Ray, Xujie Si, and Karthik Narasimhan. 2025. τ 2 -bench: Evaluating conversational agents in a dual-control environment. CoRR, abs/2506.07982. find
  4. Kent Beck. 2003. Test-driven development: by example. Addison-Wesley Professional. find
  5. Maciej Besta, Nils Blach, Ales Kubicek, Robert Gerstenberger, Michal Podstawski, Lukas Gianinazzi, Joanna Gajda, Tomasz Lehmann, Hubert Niewiadomski, Piotr Nyczyk, and Torsten Hoefler. 2024. find
  6. Graph Yanxi Chen, Xuchen Pan, Yaliang Li, Bolin Ding, and Jingren Zhou. 2024. A simple and provable scaling law for the test-time compute of large language models. CoRR, abs/2411.19477. — [arXiv:2411.19477](https://arxiv.org/abs/2411.19477) find
  7. Minghang Deng, Ashwin Ramachandran, Canwen Xu, Lanxiang Hu, Zhewei Yao, Anupam Datta, and Hao Zhang. 2025. Reforce: A text-to-sql agent with self-refinement, format restriction, and column exploration. CoRR, abs/2502.00675. — [arXiv:2502.00675](https://arxiv.org/abs/2502.00675) find
  8. Xiang Deng, Ahmed Hassan Awadallah, Christopher Meek, Oleksandr Polozov, Huan Sun, and Matthew Richardson. 2021. Structure-grounded pretraining for text-to-SQL. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Techno…
  9. Shaoming Duan, Youxuan Wu, Chuanyi Liu, Yuhao Zhang, Zirui Wang, Peiyi Han, Shengyuan Yu, Liang Yan, and Yingwei Liang. 2025. DSQG-syn: Synthesizing high-quality data for text-to-SQL parsing by domain specific question generation. In Findings of the Association for Computational Linguistics: NAACL 2… find
  10. Martin Fowler. 2002. Refactoring: Improving the design of existing code. In Extreme Programming and Agile Methods - XP/Agile Universe 2002, Second XP Universe and First Agile Universe Conference Chicago, IL, USA, August 4-7, 2002, Proceedings, volume 2418 of Lecture Notes in Computer Science, page 2… find
  11. Yujian Gan, Xinyun Chen, Qiuping Huang, and Matthew Purver. 2022. Measuring and improving 569 6 compositional generalization in text-to-SQL via component alignment. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 831– 843, Seattle, United States. Association for Compu… find
  12. Sida Wang, and Tao Yu. 2025. Spider 2.0: Evaluating language models on real-world enterprise text-to-sql workflows. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net. find
  13. Yujian Gan, Xinyun Chen, and Matthew Purver. 2021. Exploring underexplored limitations of cross-domain text-to-SQL generalization. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 8926–8931, Online and Punta Cana, Dominican Republic. Association for Co…
  14. Chunhui Li, Yifan Wang, Zhen Wu, Zhen Yu, Fei Zhao, Shujian Huang, and Xinyu Dai. 2024a. MultiSQL: A schema-integrated context-dependent Text2SQL dataset with diverse SQL operations. In Findings of the Association for Computational Linguistics: ACL 2024, pages 13857–13867, Bangkok, Thailand. Associa… find
  15. Chunxi Guo, Zhiliang Tian, Jintao Tang, Shasha Li, Zhihua Wen, Kaixuan Wang, and Ting Wang. 2023. Retrieval-augmented gpt-3.5-based text-to-sql framework with sample-aware prompting and dynamic revision chain. CoRR, abs/2307.05074. — [arXiv:2307.05074](https://arxiv.org/abs/2307.05074) find
  16. Haoyang Li, Jing Zhang, Hanbing Liu, Ju Fan, Xiaokang Zhang, Jun Zhu, Renjie Wei, Hongyan Pan, Cuiping Li, and Hong Chen. 2024b. Codes: Towards building open-source language models for text-to-sql. CoRR, abs/2402.16347. find
  17. Mingqian He, Yongliang Shen, Wenqi Zhang, Qiuying Peng, Jun Wang, and Weiming Lu. 2025. STaR-SQL: Self-taught reasoner for text-to-SQL. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 24365–24375, Vienna, Austria. Association…
  18. Jinyang Li, Binyuan Hui, Ge Qu, Binhua Li, Jiaxi Yang, Bowen Li, Bailin Wang, Bowen Qin, Rongyu Cao, Ruiying Geng, Nan Huo, Xuanhe Zhou, Chenhao Ma, Guoliang Li, Kevin Chen-Chuan Chang, Fei Huang, Reynold Cheng, and Yongbin Li. 2023. Can LLM already serve as A database interface? A big bench for lar…
  19. Tushar Khot, Harsh Trivedi, Matthew Finlayson, Yao Fu, Kyle Richardson, Peter Clark, and Ashish Sabharwal. 2023. Decomposed prompting: A modular approach for solving complex tasks. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenRev… find
  20. Mathew J. Koretsky, Maya Willey, Adi Asija, Owen Bianchi, Chelsea X. Alvarado, Tanay Nayak, Nicole Kuznetsov, Sungwon Kim, Mike A. Nalls, Daniel Khashabi, and Faraz Faghri. 2025. Biomedsql: Text-to-sql for scientific reasoning on biomedical knowledge bases. CoRR, abs/2505.20321. — [arXiv:2505.20321](https://arxiv.org/abs/2505.20321) find
  21. Rahul Kumar, Amar Raja Dibbu, Shrutendra Harsola, Vignesh Subrahmaniam, and Ashutosh Modi. 2024. BookSQL: A large scale text-to-SQL dataset for accounting domain. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Tech… find
  22. Dongjun Lee, Choongwon Park, Jaehyuk Kim, and Heesoo Park. 2025. MCS-SQL: Leveraging multiple prompts and multiple-choice selection for text-to-SQL generation. In Proceedings of the 31st International Conference on Computational Linguistics, pages 337–353, Abu Dhabi, UAE. Association for Computation…
  23. Fangyu Lei, Jixuan Chen, Yuxiao Ye, Ruisheng Cao, Dongchan Shin, Hongjin Su, Zhaoqing Suo, Hongcheng Gao, Wenjing Hu, Pengcheng Yin, Victor Zhong, Caiming Xiong, Ruoxi Sun, Qian Liu, Hunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ily… — Let's Verify Step by Step
  24. Xi Victoria Lin, Richard Socher, and Caiming Xiong. 2020. Bridging textual and tabular data for cross-domain text-to-SQL semantic parsing. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 4870–4888, Online. Association for Computational Linguistics.
  25. Aiwei Liu, Xuming Hu, Lijie Wen, and Philip S. Yu. 2023. A comprehensive evaluation of chatgpt’s zero-shot text-to-sql capability. CoRR, abs/2303.13547.
  26. Tao Liu, Hongying Zan, Yifan Li, Dixuan Zhang, Lulu Kong, Haixin Liu, Jiaming Hou, Aoze Zheng, Rui Li, Yiming Qiao, Zewei Luo, Qi Wang, Zhiqiang Zhang, Jiaxi Li, Supeng Liu, Kunli Zhang, and Min Peng. 2025. Logiccat: A chain-of-thought text-to-sql benchmark for multi-domain reasoning challenges. CoR… — [arXiv:2505.18744](https://arxiv.org/abs/2505.18744) find
  27. Zhengdong Lu, Weikai Lu, Yiling Tao, Yun Dai, Zixuan Chen, Huiping Zhuang, Cen Chen, Hao Peng, and Ziqian Zeng. 2025. Decompose, plan in parallel, and merge: A novel paradigm for large language models based planning with multiple constraints. CoRR, abs/2506.02683. — [arXiv:2506.02683](https://arxiv.org/abs/2506.02683) find
  28. Reiichiro Nakano, Jacob Hilton, Suchir Balaji, Jeff Wu, Long Ouyang, Christina Kim, Christopher Hesse, Shantanu Jain, Vineet Kosaraju, William Saunders, 570 7 find
  29. Xu Jiang, Karl Cobbe, Tyna Eloundou, Gretchen Krueger, Kevin Button, Matthew Knight, Benjamin Chess, and John Schulman. 2021. Webgpt: Browser-assisted question-answering with human feedback. CoRR, abs/2112.09332.
  30. Linyong Nan, Yilun Zhao, Weijin Zou, Narutatsu Ri, Jaesung Tae, Ellen Zhang, Arman Cohan, and Dragomir Radev. 2023. Enhancing text-to-SQL capabilities of large language models: A study on prompt design strategies. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 14935–… find
  31. Zhihong Pan, Kai Zhang, Yuze Zhao, and Yupeng Han. 2025. Route to reason: Adaptive routing for LLM and reasoning strategy selection. CoRR, abs/2505.19435. — [arXiv:2505.19435](https://arxiv.org/abs/2505.19435) find
  32. Mohammadreza Pourreza and Davood Rafiei. 2023. DIN-SQL: decomposed in-context learning of text-to-sql with self-correction. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16,…
  33. Mohammadreza Pourreza and Davood Rafiei. 2024. DTS-SQL: Decomposed text-to-SQL with small large language models. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 8212–8220, Miami, Florida, USA. Association for Computational Linguistics. find
  34. Roger S Pressman. 2005. Software engineering: a practitioner’s approach. Palgrave macmillan. find
  35. Tanmay Parekh, Yuxuan Dong, Lucas Bandarkar, Artin Kim, I-Hung Hsu, Kai-Wei Chang, and Nanyun Peng. 2025a. SNaRe: Domain-aware data generation for low-resource event detection. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 20583–20604, Suzhou, China… find
  36. Tanmay Parekh, Jeffrey Kwan, Jiarui Yu, Sparsh Johri, Hyosang Ahn, Sreya Muppalla, Kai-Wei Chang, Wei Wang, and Nanyun Peng. 2024. SPEED++: A multilingual event extraction framework for epidemic prediction and preparedness. In Proceedings of the 2024 Conference on Empirical Methods in Natural Langua… find
  37. Tanmay Parekh, Kartik Mehta, Ninareh Mehrabi, Kai-Wei Chang, and Nanyun Peng. 2025b. DiCoRe: Enhancing zero-shot event detection via divergent-convergent LLM reasoning. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 20560–20582, Suzhou, China. Associ… find
  38. Tanmay Parekh, Pradyot Prakash, Alexander Radovic, Akshay Shekher, and Denis Savenkov. 2025c. Dynamic strategy planning for efficient question answering with large language models. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 6038–6059, Albuquerque, New Mexico. Ass… find
  39. David Lorge Parnas. 1972. On the criteria to be used in decomposing systems into modules. Commun. ACM, 15(12):1053–1058. find
  40. Mohammadreza Pourreza, Hailong Li, Ruoxi Sun, Yeounoh Chung, Shayan Talaei, Gaurav Tarlok Kakkar, Yu Gan, Amin Saberi, Fatma Ozcan, and Sercan Ö. Arik. 2025. CHASE-SQL: multi-path reasoning and preference optimized candidate selection in text-to-sql. In The Thirteenth International Conference on Lea… find
  41. Sandra Rapps and Elaine J. Weyuker. 1985. Selecting software test data using data flow information. IEEE Trans. Software Eng., 11(4):367–375. find
  42. Stuart Reid. 2005. The art of software testing, second edition. glenford j. myers. revised and updated by tom badgett and todd m. thomas, with corey sandler. john wiley and sons, new jersey, usa, 2004, ISBN 0-471-46912-2. Softw. Test. Verification Reliab., 15(2):136– 137. find
  43. Swarnadeep Saha, Omer Levy, Asli Celikyilmaz, Mohit Bansal, Jason Weston, and Xian Li. 2024. Branch-solve-merge improves large language model evaluation and generation. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Languag… find
  44. Riya Sawhney, Samrat Yadav, Indrajit Bhattacharya, and Mausam. 2025. Iterative repair with weak verifiers for few-shot transfer in KBQA with unanswerability. In Findings of the Association for Computational Linguistics: ACL 2025, pages 24578–24596, Vienna, Austria. Association for Computational Ling… find
  45. Timo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu, Maria Lomeli, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. 2023. Toolformer: Language models can teach themselves to use tools. CoRR, abs/2302.04761.
  46. Torsten Scholak, Nathan Schucher, and Dzmitry Bahdanau. 2021. PICARD: Parsing incrementally for constrained auto-regressive decoding from language models. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9895–9901, Online and Punta Cana, Dominican Repu… find
  47. Zhili Shen, Pavlos Vougiouklis, Chenxin Diao, Kaustubh Vyas, Yuanyi Ji, and Jeff Z. Pan. 2024. Improving retrieval-augmented text-to-SQL with AST-based ranking and schema pruning. In Proceedings of the 2024 Conference on Empirical Methods in 571 8 find
  48. Natural Language Processing, pages 7865–7879, Miami, Florida, USA. Association for Computational Linguistics. find
  49. Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. 2023. Reflexion: language agents with verbal reinforcement learning. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans,…
  50. Charlie Snell, Jaehoon Lee, Kelvin Xu, and Aviral Kumar. 2024. Scaling LLM test-time compute optimally can be more effective than scaling model parameters. CoRR, abs/2408.03314.
  51. Ji Sun, Guoliang Li, Peiyao Zhou, Yihui Ma, Jingzhe Xu, and Yuan Li. 2025. Agenticdata: An agentic data analytics system for heterogeneous data. CoRR, abs/2508.05002. models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 260… — [arXiv:2508.05002](https://arxiv.org/abs/2508.05002) find
  52. Lilin Wang, Lucas Ramalho, Alan Celestino, Phuc Anthony Pham, Yu Liu, Umang Kumar Sinha, Andres Portillo, Onassis Osunwa, and Gabriel Maduekwe. 2025b. Swe-bench++: A framework for the scalable generation of software engineering benchmarks from open-source repositories. arXiv preprint arXiv:2512.1741… — [arXiv:2512.17419](https://arxiv.org/abs/2512.17419) find
  53. Ping Wang, Tian Shi, and Chandan K. Reddy. 2020b. Text-to-sql generation for question answering on electronic medical records. In WWW ’20: The Web Conference 2020, Taipei, Taiwan, April 20-24, 2020, pages 350–361. ACM / IW3C2. find
  54. Shayan Talaei, Mohammadreza Pourreza, Yu-Chen Chang, Azalia Mirhoseini, and Amin Saberi. 2024. CHESS: contextual harnessing for efficient SQL synthesis. CoRR, abs/2405.16755. — [arXiv:2405.16755](https://arxiv.org/abs/2405.16755) find
  55. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2023b. Self-consistency improves chain of thought reasoning in language models. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5…
  56. Dayton G. Thorpe, Andrew J. Duberstein, and Ian A. Kinsey. 2024. Dubo-sql: Diverse retrieval-augmented generation and fine tuning for text-to-sql. CoRR, abs/2404.12560. — [arXiv:2404.12560](https://arxiv.org/abs/2404.12560) find
  57. Zhongyuan Wang, Richong Zhang, Zhijie Nie, and Jaein Kim. 2024b. Tool-assisted agent on SQL inspection and refinement in real-world scenarios. CoRR, abs/2408.16991. — [arXiv:2408.16991](https://arxiv.org/abs/2408.16991) find
  58. Immanuel Trummer. 2022. Codexdb: Generating code for processing SQL queries using GPT-3 codex. CoRR, abs/2204.08941. — [arXiv:2204.08941](https://arxiv.org/abs/2204.08941) find
  59. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Ed H. Chi, Quoc Le, and Denny Zhou. 2022. Chain of thought prompting elicits reasoning in large language models. CoRR, abs/2201.11903.
  60. Bailin Wang, Richard Shin, Xiaodong Liu, Oleksandr Polozov, and Matthew Richardson. 2020a. RAT-SQL: Relation-aware schema encoding and linking for text-to-SQL parsers. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7567–7578, Online. Association for…
  61. Bing Wang, Changyu Ren, Jian Yang, Xinnian Liang, Jiaqi Bai, LinZheng Chai, Zhao Yan, Qian-Wen Zhang, Di Yin, Xing Sun, and Zhoujun Li. 2025a. MAC-SQL: A multi-agent collaborative framework for text-to-SQL. In Proceedings of the 31st International Conference on Computational Linguistics, pages 540–…
  62. Dingzirui Wang, Longxu Dou, Xuanliang Zhang, Qingfu Zhu, and Wanxiang Che. 2024a. Improving demonstration diversity by human-free fusing for text-to-SQL. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 1193– 1207, Miami, Florida, USA. Association for Computational Lin… find
  63. Lei Wang, Wanyu Xu, Yihuai Lan, Zhiqiang Hu, Yunshi Lan, Roy Ka-Wei Lee, and Ee-Peng Lim. 2023a. Plan-and-solve prompting: Improving zero-shot chain-of-thought reasoning by large language Wenxuan Xie, Gaochen Wu, and Bowen Zhou. 2024. MAG-SQL: multi-agent generative approach with soft schema linking… — [arXiv:2408.07930](https://arxiv.org/abs/2408.07930) find
  64. Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. 2023a. Tree of thoughts: Deliberate problem solving with large language models. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023,… find
  65. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R. Narasimhan, and Yuan Cao. 2023b. React: Synergizing reasoning and acting in language models. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net.
  66. Zhewei Yao, Guoheng Sun, Lukasz Borchmann, Zheyu Shen, Minghang Deng, Bohan Zhai, Hao Zhang, Ang Li, and Yuxiong He. 2025. Arctic-text2sql-r1: Simple rewards, strong reasoning in text-to-sql. CoRR, abs/2505.20315.
  67. Pengcheng Yin, Graham Neubig, Wen-tau Yih, and Sebastian Riedel. 2020. TaBERT: Pretraining for joint 572 9 understanding of textual and tabular data. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 8413–8426, Online. Association for Computational Lin… find
  68. Tao Yu, Rui Zhang, Kai Yang, Michihiro Yasunaga, Dongxu Wang, Zifan Li, James Ma, Irene Li, Qingning Yao, Shanelle Roman, Zilin Zhang, and Dragomir Radev. 2018. Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-SQL task. In Proceedings of the 2018…
  69. John M. Zelle and Raymond J. Mooney. 1996. Learning to parse database queries using inductive logic programming. In Proceedings of the Thirteenth National Conference on Artificial Intelligence and Eighth Innovative Applications of Artificial Intelligence Conference, AAAI 96, IAAI 96, Portland, Orego…
  70. Andy Zhou, Kai Yan, Michal Shlapentokh-Rothman, Haohan Wang, and Yu-Xiong Wang. 2023a. Language agent tree search unifies reasoning acting and planning in language models. CoRR, abs/2310.04406. find
  71. Denny Zhou, Nathanael Schärli, Le Hou, Jason Wei, Nathan Scales, Xuezhi Wang, Dale Schuurmans, Claire Cui, Olivier Bousquet, Quoc V. Le, and Ed H. Chi. 2023b. Least-to-most prompting enables complex reasoning in large language models. In The Eleventh International Conference on Learning Representati…

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/parekh-2026-pexa-parallel-exploration-agent-complex/