Elamur Research⌕
☰
home / papers / 2026 / FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments

FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments

Paper · 2026 · Amir Saeidi, Venkatesh Mishra, Souradeep Mukhopadhyay et al.

Summary

LLM-driven agents in multi-turn customer-service tool-use settings often fail because early wrong decisions compound over the conversation. Smaller open-source models are especially vulnerable, given their short context windows and tight inference budgets. The authors propose FAMA (Failure-Aware Meta-Agentic), a training-free framework built in two phases. First, a baseline agent's failed trajectories are examined, and errors are grouped into a few recurring categories, such as domain policy violations and misreading of complex tool outputs. Second, an orchestrator agent identifies the main cause of each failure. A mitigation agent then switches on only the minimal subset of helper agents needed to address it. These helpers add focused context before the tool-use agent makes its next decision, instead of injecting every possible aid. FAMA was tested on τ-bench, τ-trait and ACEBench with four open-source backbones ranging from 4B to 72B parameters. It beat standard baselines by up to 27% while using fewer tokens than an all-agents approach. This suggests that selective, failure-driven context curation is a practical route to more reliable small-model agents.

Key points

  • Reported gains over baselines reach up to 25% on τ-bench, 27% on ACEBench and 24% on τ-trait.
  • The helper pool includes a Planner, Tool Suggestion, Verifier, Tool Output Reformation and Domain Extractor agent, plus a Memory module. The mitigation agent most often selects the Memory module and the domain-constraint agent, which points to memory as a key weakness of open-source models.
  • The best memory size depends on the domain rather than the model: k = 6 works best for Retail and k = 2 for Airline.
  • With Qwen3-32B, FAMA adds about 30% token overhead. The all-agents baseline IRMA adds 50–58% and has higher latency (149.8 s on retail and 111.6 s on airline, on average).
  • One limitation is that FAMA only draws on a fixed, predefined set of helper agents and cannot create new ones automatically.

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

🎓Arizona State UniversityTempe · United States50 works · 2,032 citations

 Fields, topics and concepts

📚 Shelves 4The 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 works

🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 3,320 works

Cite

Cite as Amir Saeidi, Venkatesh Mishra, Souradeep Mukhopadhyay, Gaowen Liu, Ali Payani, Jayanth Srinivasa and Chitta Baral. 2026. FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.1716

@inproceedings{saeidi2026fama,
  title = {{FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments}},
  author = {Amir Saeidi, Venkatesh Mishra, Souradeep Mukhopadhyay, Gaowen Liu, Ali Payani, Jayanth Srinivasa and Chitta Baral},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1716},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1716}
}

References

78 references, 19 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Marah Abdin, Jyoti Aneja, Harkirat Behl, Sébastien Bubeck, Ronen Eldan, Suriya Gunasekar, Michael Harrison, Russell J Hewett, Mojan Javaheripi, Piero Kauffmann, and 1 others. 2024. Phi-4 technical report. arXiv preprint arXiv:2412.08905.
  2. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, and 1 others. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774.
  3. Emre Can Acikgoz, Jinoh Oh, Jie Hao, Joo Hyuk Jeon, Heng Ji, Dilek Hakkani-Tür, Gokhan Tur, Xiang Li, Chengyuan Ma, and Xing Fan. 2025. Speakrl: Synergizing reasoning, speaking, and acting in language models with reinforcement learning. arXiv preprint arXiv:2512.13159. find
  4. Mariana Almeida. 2025. Building realistic multi-turn tests for ai agents. Accessed: 2026-01-02. find
  5. Anthropic. 2025. Introducing claude opus 4.5. Accessed: 2026-01-02. find
  6. Neveen Awad, Mahmood Serry, and Joe Vasquez. 2025. How agentic ai is transforming enterprise platforms. Accessed: 2026-01-03. find
  7. Adi Banerjee, Anirudh Nair, and Tarik Borogovac. 2025. Where did it all go wrong? a hierarchical look into multi-agent error attribution. arXiv preprint arXiv:2510.04886. — [arXiv:2510.04886](https://arxiv.org/abs/2510.04886) find
  8. Victor Barres, Honghua Dong, Soham Ray, Xujie Si, and Karthik Narasimhan. 2025. τ 2-bench: Evaluating conversational agents in a dual-control environment. ArXiv, abs/2506.07982. find
  9. Peter Belcak, Greg Heinrich, Shizhe Diao, Yonggan Fu, Xin Dong, Saurav Muralidharan, Yingyan Celine Lin, and Pavlo Molchanov. 2025. Small language models are the future of agentic ai. arXiv preprint arXiv:2506.02153. find
  10. Mert Cemri, Melissa Z Pan, Shuyi Yang, Lakshya A Agrawal, Bhavya Chopra, Rishabh Tiwari, Kurt Keutzer, Aditya Parameswaran, Dan Klein, Kannan Ramchandran, and 1 others. 2025. Why do multi-agent llm systems fail? arXiv preprint arXiv:2503.13657. find
  11. Baian Chen, Chang Shu, Ehsan Shareghi, Nigel Collier, Karthik Narasimhan, and Shunyu Yao. 2023. Fireact: Toward language agent fine-tuning. arXiv preprint arXiv:2310.05915.
  12. Chen Chen, Xinlong Hao, Weiwen Liu, Xu Huang, Xingshan Zeng, Shuai Yu, Dexun Li, Shuai Wang, Weinan Gan, Yuefeng Huang, and 1 others. 2025a. Acebench: Who wins the match point in tool usage? arXiv preprint arXiv:2501.12851. — [arXiv:2501.12851](https://arxiv.org/abs/2501.12851) find
  13. Zhaorun Chen, Zhuokai Zhao, Kai Zhang, Bo Liu, Qi Qi, Yifan Wu, Tarun Kalluri, Sara Cao, Yuanhao Xiong, Haibo Tong, and 1 others. 2025b. Scaling agent learning via experience synthesis. arXiv preprint arXiv:2511.03773. find
  14. Sadia Sultana Chowa, Riasad Alvi, Subhey Sadi Rahman, Md Abdur Rahman, Mohaimenul Azam Khan Raiaan, Md Rafiqul Islam, Mukhtar Hussain, and Sami Azam. 2025. From language to action: A review of large language models as autonomous agents and tool users. arXiv preprint arXiv:2508.17281. — [arXiv:2508.17281](https://arxiv.org/abs/2508.17281) find
  15. Yihong Dong, Xue Jiang, Jiaru Qian, Tian Wang, Kechi Zhang, Zhi Jin, and Ge Li. 2025. A survey on code generation with llm-based agents. arXiv preprint arXiv:2508.00083. — [arXiv:2508.00083](https://arxiv.org/abs/2508.00083) find
  16. Nicholas Farn and Richard Shin. 2023. Tooltalk: Evaluating tool-usage in a conversational setting. arXiv preprint arXiv:2311.10775. — [arXiv:2311.10775](https://arxiv.org/abs/2311.10775) find
  17. Yao Fu, Dong-Ki Kim, Jaekyeom Kim, Sungryull Sohn, Lajanugen Logeswaran, Kyunghoon Bae, and Honglak Lee. 2024. Autoguide: Automated generation and selection of context-aware guidelines for large language model agents. Advances in Neural Information Processing Systems, 37:119919–119948. find
  18. Yu Ge, Linna Xie, Zhong Li, Yu Pei, and Tian Zhang. 2025. Who is introducing the failure? automatically attributing failures of multi-agent systems via spectrum analysis. arXiv preprint arXiv:2509.13782. — [arXiv:2509.13782](https://arxiv.org/abs/2509.13782) find
  19. Alexander Golubev, Maria Trofimova, Sergei Polezhaev, Ibragim Badertdinov, Maksim Nekrashevich, Anton Shevtsov, Simon Karasik, Sergey Abramov, Andrei Andriushchenko, Filipp Fisin, and 1 others. 2025. Training long-context, multi-turn software engineering agents with reinforcement learning. arXiv pre… — [arXiv:2508.03501](https://arxiv.org/abs/2508.03501) find
  20. Google DeepMind. 2025. Gemini 3 pro. Accessed: 2026-01-02. find
  21. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, and 1 others. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783.
  22. Divij Handa, David Blincoe, Orson Adams, and Yinlin Fu. 2025a. Optagent: Optimizing query rewriting for e-commerce via multi-agent simulation. arXiv preprint arXiv:2510.03771. — [arXiv:2510.03771](https://arxiv.org/abs/2510.03771) find
  23. Divij Handa, Mihir Parmar, Aswin RRV, Md Nayem Uddin, Hamid Palangi, and Chitta Baral. 2025b. Guidedsampling: Steering llms towards diverse candidate solutions at inference-time. arXiv preprint arXiv:2510.03777. — [arXiv:2510.03777](https://arxiv.org/abs/2510.03777) find
  24. Muyu He, Anand Kumar, Tsach Mackey, Meghana Rajeev, James Zou, and Nazneen Rajani. 2025. Impatient users confuse ai agents: High-fidelity simulations of human traits for testing agents. arXiv preprint arXiv:2510.04491. find
  25. Yuchen Huang, Sijia Li, Minghao Liu, Wei Liu, Shijue Huang, Zhiyuan Fan, Hou Pong Chan, and Yi R Fung. 2025. Environment scaling for interactive agentic experience collection: A survey. arXiv preprint arXiv:2511.09586. — [arXiv:2511.09586](https://arxiv.org/abs/2511.09586) find
  26. Polaris Jhandi, Owais Kazi, Shreyas Subramanian, and Neel Sendas. 2025. Small language models for efficient agentic tool calling: Outperforming large models with targeted fine-tuning. arXiv preprint arXiv:2512.15943. find
  27. Dongfu Jiang, Yi Lu, Zhuofeng Li, Zhiheng Lyu, Ping Nie, Haozhe Wang, Alex Su, Hui Chen, Kai Zou, Chao Du, and 1 others. 2025. Verltool: Towards holistic agentic reinforcement learning with tool use. arXiv preprint arXiv:2509.01055. — [arXiv:2509.01055](https://arxiv.org/abs/2509.01055) find
  28. Kiran Kate, Tejaswini Pedapati, Kinjal Basu, Yara Rizk, Vijil Chenthamarakshan, Subhajit Chaudhury, Mayank Agarwal, and Ibrahim Abdelaziz. 2025. Longfunceval: Measuring the effectiveness of long context models for function calling. arXiv preprint arXiv:2505.10570. — [arXiv:2505.10570](https://arxiv.org/abs/2505.10570) find
  29. Kai-Kristian Kemell, Matti Saarikallio, Anh Nguyen-Duc, and Pekka Abrahamsson. 2025. Still just personal assistants? – a multiple case study of generative ai adoption in software organizations. Information and Software Technology, 186:107805. find
  30. Shirley Kokane, Ming Zhu, Tulika Awalgaonkar, Jianguo Zhang, Thai Hoang, Akshara Prabhakar, Zuxin Liu, Tian Lan, Liangwei Yang, Juntao Tan, and 1 others. 2024. Spectool: A benchmark for characterizing errors in tool-use llms. arXiv preprint arXiv:2411.13547. — [arXiv:2411.13547](https://arxiv.org/abs/2411.13547) find
  31. Shrinidhi Kumbhar, Venkatesh Mishra, Kevin Coutinho, Divij Handa, Ashif Iquebal, and Chitta Baral. 2025. Hypothesis generation for materials discovery and design using goal-driven and constraint-guided LLM agents. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 7539–7… find
  32. Minghao Li, Yingxiu Zhao, Bowen Yu, Feifan Song, Hangyu Li, Haiyang Yu, Zhoujun Li, Fei Huang, and Yongbin Li. 2023. API-bank: A comprehensive benchmark for tool-augmented LLMs. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 3102–3116, Singapore. Ass…
  33. Guannan Liang and Qianqian Tong. 2025. Llm-powered ai agent systems and their applications in industry. In 2025 IEEE World AI IoT Congress (AIIoT), pages 0463–0471. find
  34. Ilija Lichkovski, Alexander Müller, Mariam Ibrahim, and Tiwai Mhundwa. 2025. Eu-agent-bench: Measuring illegal behavior of llm agents under eu law. arXiv preprint arXiv:2510.21524. find
  35. Aixin Liu, Aoxue Mei, Bangcai Lin, Bing Xue, Bingxuan Wang, Bingzheng Xu, Bochao Wu, Bowei Zhang, Chaofan Lin, Chen Dong, and 1 others. 2025a. Deepseek-v3. 2: Pushing the frontier of open large language models. arXiv preprint arXiv:2512.02556.
  36. Shuo Liu, Kaining Ying, Hao Zhang, Yue Yang, Yuqi Lin, Tianle Zhang, Chuanhao Li, Yu Qiao, Ping Luo, Wenqi Shao, and 1 others. 2024. Convbench: A multi-turn conversation evaluation benchmark with hierarchical capability for large vision-language models. arXiv preprint arXiv:2403.20194. — [arXiv:2403.20194](https://arxiv.org/abs/2403.20194) find
  37. Zihan Liu, Yang Chen, Mohammad Shoeybi, Bryan Catanzaro, and Wei Ping. 2025b. Acemath: Advancing frontier math reasoning with post-training and reward modeling. In Findings of the Association for Computational Linguistics: ACL 2025, pages 3993– 4015. find
  38. Jiarui Lu, Thomas Holleis, Yizhe Zhang, Bernhard Aumayer, Feng Nan, Haoping Bai, Shuang Ma, Shen Ma, Mengyu Li, Guoli Yin, and 1 others. 2025a. Toolsandbox: A stateful, conversational, interactive evaluation benchmark for llm tool use capabilities. In Findings of the Association for Computational Li…
  39. Ruofan Lu, Yichen Li, and Yintong Huo. 2025b. Exploring autonomous agents: A closer look at why they fail when completing tasks. arXiv preprint arXiv:2508.13143. — [arXiv:2508.13143](https://arxiv.org/abs/2508.13143) find
  40. Zhiyuan Ma, Jiayu Liu, Xianzhen Luo, Zhenya Huang, Qingfu Zhu, and Wanxiang Che. 2025. Advancing tool-augmented large language models via meta-verification and reflection learning. In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2, KDD ’25, page 2078–2089, N… find
  41. 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. find
  42. Venkatesh Mishra, Amir Saeidi, Satyam Raj, Mutsumi Nakamura, Jayanth Srinivasa, Gaowen Liu, Ali Payani, and Chitta Baral. 2025. How can input reformulation improve tool usage accuracy in a complex dynamic environment? a study on τ -bench. ArXiv, abs/2508.20931. — [arXiv:2508.20931](https://arxiv.org/abs/2508.20931) find
  43. Hadi Nekoei, Aman Jaiswal, Patrice Bechard, Oleh Shliazhko, Orlando Marquez Ayala, Mathieu Reymond, Massimo Caccia, Alexandre Drouin, Sarath Chandar, and Alexandre Lacoste. 2025. Just-intime episodic feedback hinter: Leveraging offline knowledge to improve llm agents adaptation. arXiv preprint arXiv… — [arXiv:2510.04373](https://arxiv.org/abs/2510.04373) find
  44. OpenAI. 2025. Introducing gpt-5.2. Accessed: 2026-01-02. find
  45. 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.
  46. Zehan Qi, Xiao Liu, Iat Long Iong, Hanyu Lai, Xueqiao Sun, Jiadai Sun, Xinyue Yang, Yu Yang, Shuntian Yao, Wei Xu, and 1 others. 2025. Webrl: Training llm web agents via self-evolving online curriculum reinforcement learning. In The Thirteenth International Conference on Learning Representations. find
  47. 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.
  48. Changle Qu, Sunhao Dai, Xiaochi Wei, Hengyi Cai, Shuaiqiang Wang, Dawei Yin, Jun Xu, and Ji-Rong Wen. 2025. Tool learning with large language models: A survey. Frontiers of Computer Science, 19(8):198343.
  49. Mizanur Rahman, Amran Bhuiyan, Mohammed Saidul Islam, Md Tahmid Rahman Laskar, Ridwan Mahbub, Ahmed Masry, Shafiq Joty, and Enamul Hoque. 2025. Llm-based data science agents: A survey of capabilities, challenges, and future directions. arXiv preprint arXiv:2510.04023. — [arXiv:2510.04023](https://arxiv.org/abs/2510.04023) find
  50. Paulius Rauba, Nabeel Seedat, Max Ruiz Luyten, and Mihaela van der Schaar. 2024. Context-aware testing: A new paradigm for model testing with large language models. In Advances in Neural Information Processing Systems, volume 37, pages 112505– 112553. Curran Associates, Inc. find
  51. Aswin Rrv, Jacob Dineen, Divij Handa, Md Nayem Uddin, Mihir Parmar, Chitta Baral, and Ben Zhou. 2025. ThinkTuning: Instilling cognitive reflections without distillation. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 31236–31250, Suzhou, China. Assoc… find
  52. Amir Saeidi, Chitta Baral, Ahmed Hassan Awadallah, and Harkirat Behl. 2026. Vulcan: Where agents learn by living in simulated tool environments. In ICLR 2026 Workshop on Data-FM. Last modified: April 1, 2026. find
  53. Sarath Shekkizhar, Romain Cosentino, Adam Earle, and Silvio Savarese. 2025. Echoing: Identity failures when llm agents talk to each other. arXiv preprint arXiv:2511.09710. — [arXiv:2511.09710](https://arxiv.org/abs/2511.09710) find
  54. Weizhou Shen, Chenliang Li, Hongzhan Chen, Ming Yan, Xiaojun Quan, Hehong Chen, Ji Zhang, and Fei Huang. 2024. Small LLMs are weak tool learners: A multi-LLM agent. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 16658–16680, Miami, Florida, USA. Asso…
  55. Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. 2023. Reflexion: Language agents with verbal reinforcement learning. Advances in Neural Information Processing Systems, 36:8634–8652.
  56. Akshit Sinha, Arvindh Arun, Shashwat Goel, Steffen Staab, and Jonas Geiping. 2025. The illusion of diminishing returns: Measuring long horizon execution in llms. In First Workshop on Multi-Turn Interactions in Large Language Models. find
  57. Peter Stone and Manuela Veloso. 2000. Multiagent systems: A survey from a machine learning perspective. Autonomous Robots, 8(3):345–383. find
  58. Hongru Wang, Wenyu Huang, Yufei Wang, Yuanhao Xi, Jianqiao Lu, Huan Zhang, Nan Hu, Zeming Liu, Jeff Z. Pan, and Kam-Fai Wong. 2025a. Rethinking stateful tool use in multi-turn dialogues: Benchmarks and challenges. In Findings of the Association for Computational Linguistics: ACL 2025, pages 5433–545… find
  59. Hongru Wang, Wenyu Huang, Yufei Wang, Yuanhao Xi, Jianqiao Lu, Huan Zhang, Nan Hu, Zeming Liu, Jeff Z Pan, and Kam-Fai Wong. 2025b. Rethinking stateful tool use in multi-turn dialogues: Benchmarks and challenges. arXiv preprint arXiv:2505.13328. find
  60. Xingyao Wang, Zihan Wang, Jiateng Liu, Yangyi Chen, Lifan Yuan, Hao Peng, and Heng Ji. 2023. Mint: Evaluating llms in multi-turn interaction with tools and language feedback. arXiv preprint arXiv:2309.10691.
  61. Yutong Wang, Pengliang Ji, Kaixin Li, Baolong Bi, Tao Feng, and Guillaume Sartoretti. 2025c. Beyond policy optimization: A data curation flywheel for sparse-reward long-horizon planning. arXiv preprint arXiv:2508.03018. — [arXiv:2508.03018](https://arxiv.org/abs/2508.03018) find
  62. Zora Zhiruo Wang, Jiayuan Mao, Daniel Fried, and Graham Neubig. 2025d. Agent workflow memory. In Forty-second International Conference on Machine Learning.
  63. 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. Advances in neural information processing systems, 35:24824– 24837.
  64. 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.
  65. Shunyu Yao, Noah Shinn, Pedram Razavi, and Karthik Narasimhan. 2024. τ -bench: A benchmark for tool-agent-user interaction in real-world domains. Preprint, arXiv:2406.12045.
  66. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2023. React: Synergizing reasoning and acting in language models. In International Conference on Learning Representations (ICLR).
  67. Aohan Zeng, Mingdao Liu, Rui Lu, Bowen Wang, Xiao Liu, Yuxiao Dong, and Jie Tang. 2024. AgentTuning: Enabling generalized agent abilities for LLMs. In Findings of the Association for Computational Linguistics: ACL 2024, pages 3053–3077, Bangkok, Thailand. Association for Computational Linguistics.
  68. Yirong Zeng, Xiao Ding, Yutai Hou, Yuxian Wang, Li Du, Juyi Dai, Qiuyang Ding, Duyu Tang, Dandan Tu, Weiwen Liu, Bing Qin, and Ting Liu. 2025. Tool zero: Training tool-augmented LLMs via pure RL from scratch. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 9135– 9147,… find
  69. Chen Zhang, Xinyi Dai, Yaxiong Wu, Qu Yang, Yasheng Wang, Ruiming Tang, and Yong Liu. 2025a. A survey on multi-turn interaction capabilities of large language models. arXiv preprint arXiv:2501.09959. — [arXiv:2501.09959](https://arxiv.org/abs/2501.09959) find
  70. Guibin Zhang, Hejia Geng, Xiaohang Yu, Zhenfei Yin, Zaibin Zhang, Zelin Tan, Heng Zhou, Zhongzhi Li, Xiangyuan Xue, Yijiang Li, and 1 others. 2025b. The landscape of agentic reinforcement learning for llms: A survey. arXiv preprint arXiv:2509.02547. — [arXiv:2509.02547](https://arxiv.org/abs/2509.02547) find
  71. Guibin Zhang, Junhao Wang, Junjie Chen, Wangchunshu Zhou, Kun Wang, and Shuicheng Yan. 2025c. Agentracer: Who is inducing failure in the llm agentic systems? arXiv preprint arXiv:2509.03312. — [arXiv:2509.03312](https://arxiv.org/abs/2509.03312) find
  72. Kai Zhang, Xiangchao Chen, Bo Liu, Tianci Xue, Zeyi Liao, Zhihan Liu, Xiyao Wang, Yuting Ning, Zhaorun Chen, Xiaohan Fu, and 1 others. 2025d. Agent learning via early experience. arXiv preprint arXiv:2510.08558. find
  73. Wentao Zhang, Ce Cui, Yilei Zhao, Yang Liu, and Bo An. 2025e. Agentorchestra: A hierarchical multi-agent framework for general-purpose task solving. arXiv preprint arXiv:2506.12508. — [arXiv:2506.12508](https://arxiv.org/abs/2506.12508) find
  74. Bingxi Zhao, Lin Geng Foo, Ping Hu, Christian Theobalt, Hossein Rahmani, and Jun Liu. 2025a. Llm-based agentic reasoning frameworks: A survey from methods to scenarios. arXiv preprint arXiv:2508.17692. — [arXiv:2508.17692](https://arxiv.org/abs/2508.17692) find
  75. Weikang Zhao, Xili Wang, Chengdi Ma, Lingbin Kong, Zhaohua Yang, Mingxiang Tuo, Xiaowei Shi, Yitao Zhai, and Xunliang Cai. 2025b. Mua-rl: Multi-turn user-interacting agent reinforcement learning for agentic tool use. ArXiv, abs/2508.18669. — [arXiv:2508.18669](https://arxiv.org/abs/2508.18669) find
  76. Lianhao Zhou, Hongyi Ling, Cong Fu, Yepeng Huang, Michael Sun, Wendi Yu, Xiaoxuan Wang, Xiner Li, Xingyu Su, Junkai Zhang, and 1 others. 2025. Autonomous agents for scientific discovery: Orchestrating scientists, language, code, and physics. arXiv preprint arXiv:2510.09901. — [arXiv:2510.09901](https://arxiv.org/abs/2510.09901) find
  77. Kunlun Zhu, Zijia Liu, Bingxuan Li, Muxin Tian, Yingxuan Yang, Jiaxun Zhang, Pengrui Han, Qipeng Xie, Fuyang Cui, Weijia Zhang, and 1 others. 2025. Where llm agents fail and how they can learn from failures. arXiv preprint arXiv:2509.25370. — [arXiv:2509.25370](https://arxiv.org/abs/2509.25370) find
  78. K.J Åström. 1965. Optimal control of markov processes with incomplete state information. Journal of Mathematical Analysis and Applications, 10(1):174–205. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/saeidi-2026-fama-failure-aware-meta-agentic/