CoChat
Sign Up
Cited by 4

The DOI matches its Crossref record.

EVOTOOL: Self-Evolving Tool-Use Policy Optimization in LLM Agents via Blame-Aware Mutation and Diversity-Aware Selection

Yang, Shuo, Han, Caren, Ma, Xueqi, Li, Yan, Ghasemi Madani, Mohammad Reza, Hovy, Eduard·2026·Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
DOI 10.18653/v1/2026.acl-long.2016
Open this paper in CoChat — free account

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.18653/v1/2026.acl-long.2016

Cites

Statistics

Figures

Figure 1 Limitations of monolithic and single-aspect tool-use policy optimization, and how EVOTOOL enables targeted, blame-aware policy updates.
Figure 1 Limitations of monolithic and single-aspect tool-use policy optimization, and how EVOTOOL enables targeted, blame-aware policy updates.CC-BY · From the PDF
Figure 2 Overall architecture of EVOTOOL. EVOTOOL optimizes a modular tool-use policy through a self-evolving loop consisting of (1) trajectory collection from the tool environment, (2) trajectory-grounded blame attribution to identify the responsible module, (3) feedback-guided targeted mutation to update that module using natural language feedback, and (4) diversity-aware population selection over candidate policies to retain complementary candidates.
Figure 2 Overall architecture of EVOTOOL. EVOTOOL optimizes a modular tool-use policy through a self-evolving loop consisting of (1) trajectory collection from the tool environment, (2) trajectory-grounded blame attribution to identify the responsible module, (3) feedback-guided targeted mutation to update that module using natural language feedback, and (4) diversity-aware population selection over candidate policies to retain complementary candidates.CC-BY · From the PDF
Figure 3 Learning dynamics and efficiency comparison. (a) Learning curves across evolution iterations on four benchmarks. (b) Performance versus log token cost under GPT-4.1.
Figure 3 Learning dynamics and efficiency comparison. (a) Learning curves across evolution iterations on four benchmarks. (b) Performance versus log token cost under GPT-4.1.CC-BY · From the PDF
Figure 4 Module-level error progression across evolution iterations diagnosed by the Blamer LLM.
Figure 4 Module-level error progression across evolution iterations diagnosed by the Blamer LLM.CC-BY · From the PDF
Figure 5 Transferability across datasets and backbone models. (a) Cross-dataset transfer between ToolBench and RestBench. (b) Cross-model transfer between Qwen3-8B and GPT-4.1.
Figure 5 Transferability across datasets and backbone models. (a) Cross-dataset transfer between ToolBench and RestBench. (b) Cross-model transfer between Qwen3-8B and GPT-4.1.CC-BY · From the PDF

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

No references could be resolved yet.

Research works printed but not linked: 36

  1. Lakshya A Agrawal, Shangyin Tan, Dilara Soylu, Noah Ziems, Rishi Khare, Krista Opsahl-Ong, Ar- nav Singhvi, Herumb Shandilya, Michael J Ryan, Meng Jiang, and 1 others. 2025. Gepa: Reflec- tive prompt evolution can outperform reinforcement learning. arXiv preprint arXiv:2507.19457. · arXiv
  2. Andres M Bran, Sam Cox, Oliver Schilter, Carlo Baldas- sari, Andrew D White, and Philippe Schwaller. 2023. Chemcrow: Augmenting large-language models with chemistry tools. arXiv preprint arXiv:2304.05376. · arXiv
  3. Yu Du, Fangyun Wei, and Hongyang Zhang. 2024. Any- tool: Self-reflective, hierarchical agents for large- scale api calls. arXiv preprint arXiv:2402.04253. · arXiv
  4. Jinyuan Fang, Yanwen Peng, Xi Zhang, Yingxu Wang, Xinhao Yi, Guibin Zhang, Yi Xu, Bin Wu, Siwei Liu, Zihao Li, and 1 others. 2025. A comprehensive survey of self-evolving ai agents: A new paradigm bridging foundation models and lifelong agentic sys- tems. arXiv preprint arXiv:2508.07407. · arXiv
  5. Jiazhan Feng, Shijue Huang, Xingwei Qu, Ge Zhang, Yujia Qin, Baoquan Zhong, Chengquan Jiang, Jinxin Chi, and Wanjun Zhong. 2025. Retool: Reinforce- ment learning for strategic tool use in llms. arXiv preprint arXiv:2504.11536. · arXiv
  6. Chrisantha Fernando, Dylan Banarse, Henryk Michalewski, Simon Osindero, and Tim Rock- täschel. 2023. Promptbreeder: Self-referential self-improvement via prompt evolution. arXiv preprint arXiv:2309.16797. · arXiv
  7. Huan-ang Gao, Jiayi Geng, Wenyue Hua, Mengkang Hu, Xinzhe Juan, Hongzhang Liu, Shilong Liu, Jiahao Qiu, Xuan Qi, Yiran Wu, and 1 others. 2025. A survey of self-evolving agents: On path to artificial super intelligence. arXiv preprint arXiv:2507.21046. · arXiv
  8. Qingyan Guo, Rui Wang, Junliang Guo, Bei Li, Kaitao Song, Xu Tan, Guoqing Liu, Jiang Bian, and Yu- jiu Yang. 2023. Connecting large language models with evolutionary algorithms yields powerful prompt optimizers. arXiv preprint arXiv:2309.08532. · arXiv
  9. Shengran Hu, Cong Lu, and Jeff Clune. 2024. Au- tomated design of agentic systems. arXiv preprint arXiv:2408.08435. · arXiv
  10. Pengcheng Jiang, Jiacheng Lin, Zhiyi Shi, Zifeng Wang, Luxi He, Yichen Wu, Ming Zhong, Peiyang Song, Qizheng Zhang, Heng Wang, and 1 others. 2025. Adaptation of agentic ai. arXiv preprint arXiv:2512.16301. · arXiv
  11. Omar Khattab, Arnav Singhvi, Paridhi Maheshwari, Zhiyuan Zhang, Keshav Santhanam, Sri Vard- hamanan, Saiful Haq, Ashutosh Sharma, Thomas T Joshi, Hanna Moazam, and 1 others. 2023. Dspy: Compiling declarative language model calls into self-improving pipelines. arXiv preprint arXiv:2310.03714. · arXiv
  12. Xiao Liu, Hao Yu, Hanchen Zhang, Yifan Xu, Xuanyu Lei, Hanyu Lai, Yu Gu, Hangliang Ding, Kaiwen Men, Kejuan Yang, and 1 others. 2023. Agent- bench: Evaluating llms as agents. arXiv preprint arXiv:2308.03688. · arXiv
  13. Pan Lu, Bowen Chen, Sheng Liu, Rahul Thapa, Joseph Boen, and James Zou. 2025. Octotools: An agentic framework with extensible tools for complex reason- ing. arXiv preprint arXiv:2502.11271. · arXiv
  14. Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, and 1 others. 2023. Self-refine: Iterative refinement with self-feedback. Advances in Neural Information Processing Systems, 36:46534-46594.
  15. Shishir G. Patil, Huanzhi Mao, Charlie Cheng-Jie Ji, Fanjia Yan, Vishnu Suresh, Ion Stoica, and Joseph E. Gonzalez. 2025. The berkeley function calling leaderboard (bfcl): From tool use to agentic eval- uation of large language models. In Forty-second International Conference on Machine Learning.
  16. Shishir G Patil, Tianjun Zhang, Xin Wang, and Joseph E Gonzalez. 2024. Gorilla: Large language model connected with massive apis. Advances in Neural Information Processing Systems, 37:126544-126565.
  17. Cheng Qian, Emre Can Acikgoz, Qi He, Hongru Wang, Xiusi Chen, Dilek Hakkani-Tür, Gokhan Tur, and Heng Ji. 2025. Toolrl: Reward is all tool learning needs. arXiv preprint arXiv:2504.13958. · arXiv
  18. Yujia Qin, Shihao Liang, Yining Ye, Kunlun Zhu, Lan Yan, Yaxi Lu, Yankai Lin, Xin Cong, Xiangru Tang, Bill Qian, and 1 others. 2023. Toolllm: Facilitating large language models to master 16000+ real-world apis. arXiv preprint arXiv:2307.16789. · arXiv
  19. Changle Qu, Sunhao Dai, Xiaochi Wei, Hengyi Cai, Shuaiqiang Wang, Dawei Yin, Jun Xu, and Ji-Rong Wen. 2024. From exploration to mastery: En- abling llms to master tools via self-driven interac- tions. arXiv preprint arXiv:2410.08197. · arXiv
  20. Changle Qu, Sunhao Dai, Xiaochi Wei, Hengyi Cai, Shuaiqiang Wang, Dawei Yin, Jun Xu, and Ji-Rong Wen. 2025. Tool learning with large language mod- els: A survey. Frontiers of Computer Science, 19(8):198343.
  21. Kiran Ramnath, Kang Zhou, Sheng Guan, Soumya Sm- ruti Mishra, Xuan Qi, Zhengyuan Shen, Shuai Wang, Sangmin Woo, Sullam Jeoung, Yawei Wang, Haozhu Wang, Han Ding, Yuzhe Lu, Zhichao Xu, Yun Zhou, Balasubramaniam Srinivasan, Qiaojing Yan, Yueyan Chen, Haibo Ding, and 2 others. 2025. A systematic survey of automatic prompt optimization techniques. In Proceedings of the 2025 Conference on Empiri- cal Methods in Natural Language Processing, pages 33066-33098, Suzhou, China. Association for Com- putational Linguistics. · DOI
  22. Timo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu, Maria Lomeli, Eric Hambro, Luke Zettle- moyer, Nicola Cancedda, and Thomas Scialom. 2023. Toolformer: Language models can teach themselves to use tools. Advances in Neural Information Pro- cessing Systems, 36:68539-68551.
  23. Yongliang Shen, Kaitao Song, Xu Tan, Dongsheng Li, Weiming Lu, and Yueting Zhuang. 2023. Hugging- gpt: Solving ai tasks with chatgpt and its friends in hugging face. Advances in Neural Information Processing Systems, 36:38154-38180.
  24. Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. 2023. Re- flexion: Language agents with verbal reinforcement learning. Advances in Neural Information Process- ing Systems, 36:8634-8652.
  25. Yifan Song, Weimin Xiong, Dawei Zhu, Wenhao Wu, Han Qian, Mingbo Song, Hailiang Huang, Cheng Li, Ke Wang, Rong Yao, and 1 others. 2023. Restgpt: Connecting large language models with real-world restful apis. arXiv preprint arXiv:2306.06624. · arXiv
  26. Haotian Sun, Yuchen Zhuang, Lingkai Kong, Bo Dai, and Chao Zhang. 2023. Adaplanner: Adaptive plan- ning from feedback with language models. Advances in neural information processing systems, 36:58202- 58245.
  27. Lei Wang, Wanyu Xu, Yihuai Lan, Zhiqiang Hu, Yunshi Lan, Roy Ka-Wei Lee, and Ee-Peng Lim. 2023. Plan- and-solve prompting: Improving zero-shot chain-of- thought reasoning by large language models. In Pro- ceedings of the 61st Annual Meeting of the Associa- tion for Computational Linguistics (Volume 1: Long Papers), pages 2609-2634, Toronto, Canada. Associ- ation for Computational Linguistics. · DOI · Paper page
  28. 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 elic- its reasoning in large language models. Advances in neural information processing systems, 35:24824- 24837.
  29. Tianbao Xie, Danyang Zhang, Jixuan Chen, Xiaochuan Li, Siheng Zhao, Ruisheng Cao, Toh J Hua, Zhoujun Cheng, Dongchan Shin, Fangyu Lei, and 1 others. 2024. Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments. Advances in Neural Information Processing Systems, 37:52040-52094.
  30. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, and 1 others. 2025. Qwen3 technical report. arXiv preprint arXiv:2505.09388. · arXiv
  31. Chengrun Yang, Xuezhi Wang, Yifeng Lu, Hanxiao Liu, Quoc V Le, Denny Zhou, and Xinyun Chen. 2023. Large language models as optimizers. In The Twelfth International Conference on Learning Representations.
  32. John Yang, Carlos E Jimenez, Alexander Wettig, Kilian Lieret, Shunyu Yao, Karthik Narasimhan, and Ofir Press. 2024. Swe-agent: Agent-computer interfaces enable automated software engineering. Advances in Neural Information Processing Systems, 37:50528- 50652.
  33. Shunyu Yao, Noah Shinn, Pedram Razavi, and Karthik Narasimhan. 2024. τ -bench: A benchmark for tool- agent-user interaction in real-world domains. arXiv preprint arXiv:2406.12045. · arXiv
  34. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R Narasimhan, and Yuan Cao. 2022. React: Synergizing reasoning and acting in language models. In The eleventh international conference on learning representations.
  35. Siyu Yuan, Kaitao Song, Jiangjie Chen, Xu Tan, Yongliang Shen, Kan Ren, Dongsheng Li, and De- qing Yang. 2025. Easytool: Enhancing llm-based agents with concise tool instruction. In Proceedings of the 2025 Conference of the Nations of the Amer- icas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 951-972.
  36. Mert Yuksekgonul, Federico Bianchi, Joseph Boen, Sheng Liu, Zhi Huang, Carlos Guestrin, and James Zou. 2024. Textgrad: Automatic" differentiation" via text. arXiv preprint arXiv:2406.07496. · arXiv

Cited by

Sorted by citations

See all 4

Metadata

Authors
Yang, S., Han, C., Ma, X., Li, Y., Ghasemi Madani, M. R., & Hovy, E.
Venue
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Publisher
Association for Computational Linguistics
Published
2026
Pages
43553-43572
DOI
10.18653/v1/2026.acl-long.2016
Cited by
1
References
0

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: EVOTOOL: Self-Evolving Tool-Use Policy Optimization in LLM Agents via Blame-Aware Mutation and Diversity-Aware Selection. https://app.cochat.ai/papers/10.18653/v1/2026.acl-long.2016
The paper
Yang, S., Han, C., Ma, X., Li, Y., Ghasemi Madani, M. R., & Hovy, E. (2026). EVOTOOL: Self-Evolving Tool-Use Policy Optimization in LLM Agents via Blame-Aware Mutation and Diversity-Aware Selection. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). https://doi.org/10.18653/v1/2026.acl-long.2016