REFERENCES

1. OpenAI. OpenAI Agents SDK. https://github.com/openai/openai-agents-python (accessed 2026-10-28).

2. Kumayama, K. D.; Chiruvolu, P.; Weiss, D. AI agents: greater capabilities and enhanced risks. Reuters Legal News, 2025. 22 April 2025. https://www.reuters.com/legal/legalindustry/ai-agents-greater-capabilities-enhanced-risks-2025-04-22/ (accessed 2026-10-28).

3. Wang, L.; Ma, C.; Feng, X.; et al. A survey on large language model based autonomous agents. Front Comput Sci 2024, 18, 186345.

4. Xu, D.; Cao, J.; Mo, G.; et al. LiveFMBench: unveiling the power and limits of agentic workflows in specification generation. arXiv 2026;arXiv:2605.01394. Available online: https://doi.org/10.48550/arXiv.2605.01394 [accessed 28 October 2026].

5. Lu, X.; Sun, W.; Zhang, Y.; et al. Requirements development and formalization for reliable code generation: a multi-agent vision. In: 2025 40th IEEE/ACM International Conference on Automated Software Engineering (ASE); 2025 Nov 16-20; Seoul, Korea. IEEE; 2025. pp. 3932-7.

6. Yao, S.; Zhao, J.; Yu, D.; et al. ReAct: synergizing reasoning and acting in language models. arXiv 2023;arXiv:2210.03629. Available online: https://doi.org/10.48550/arXiv.2210.03629 [accessed 28 October 2026].

7. Hu, M.; Chen, T.; Chen, Q.; Mu, Y.; Shao, W.; Luo, P. HiAgent: hierarchical working memory management for solving long-horizon agent tasks with large language model. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers); 2025 Jun; Vienna, Austria. Stroudsburg, PA, USA: Association for Computational Linguistics; 2025. pp. 32779-98.

8. Zhou, S.; Xu, F. F.; Zhu, H.; et al. WebArena: a realistic web environment for building autonomous agents. In: Proceeding of Twelfth International Conference on Learning Representations; 2024 May 7-11; Vienna, Austria. Curran Associates, Inc.; 2024. pp. 1-22. Available from: https://proceedings.iclr.cc/paper_files/paper/2024/file/4410c0711e9154a7a2d26f9b3816d1ef-Paper-Conference.pdf (accessed 2026-10-28).

9. Cemri, M.; Pan, M. Z.; Yang, S.; et al. Why Do Multi-Agent LLM Systems Fail? In: Belgrave D, Zhang C, Lin H, Pascanu R, Koniusz P, Ghassemi M, Chen N, Editors. Advances in Neural Information Processing Systems 38; 2025 Nov 30-Dec 7; San Diego, California, USA and Mexico City, Mexico. San Diego, California, USA: Neural Information Processing Systems Foundation, Inc. (NeurIPS); 2025. pp. 135676-729.

10. Xie, Y.; Zhu, C.; Zhang, X.; et al. From spark to fire: modeling and mitigating error cascades in LLM-based multi-agent collaboration. arXiv 2026;arXiv:2603.04474. Available online: https://doi.org/10.48550/arXiv.2603.04474 [accessed 28 October 2026].

11. Zhou, J.; Chen, J.; Lu, Q.; Zhao, D.; Zhu, L. SHIELDA: structured handling of exceptions in LLM-driven agentic workflows. arXiv 2025;arXiv:2508.07935. Available online: https://doi.org/10.48550/arXiv.2508.07935 [accessed 28 October 2026].

12. Arike, R.; Donoway, E.; Bartsch, H.; Hobbhahn, M. Technical report: evaluating goal drift in language model agents. arXiv 2025;arXiv:2505.02709. Available online: https://doi.org/10.48550/arXiv.2505.02709 [accessed 28 October 2026].

13. Huang, D.; Malwe, G.; Wang, Z. When agents fail to act: a diagnostic framework for tool invocation reliability in multi-agent LLM systems. In: 2026 9th International Conference on Artificial Intelligence and Big Data (ICAIBD); 2026 May 29-31; Chengdu, China. IEEE; 2026. pp. 492-7.

14. Huang, S.; Fang, Z.; Chen, Z.; et al. CRITICTOOL: evaluating self-critique capabilities of large language models in tool-calling error scenarios. In: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing; 2025 Oct; Suzhou, China. Stroudsburg, PA, USA: Association for Computational Linguistics; 2025. pp. 26683-92.

15. Zhu, X.; Wu, J.; Zhang, X.; et al. An empirical study of bugs in modern LLM agent frameworks. arXiv 2026;arXiv:2602.21806v1. Available online: https://doi.org/10.48550/arXiv.2602.21806 [accessed 28 October 2026].

16. Shi, J.; Yuan, Z.; Tie, G.; Zhou, P.; Gong, N.; Sun, L. Prompt injection attack to tool selection in LLM agents. In: Network and Distributed System Security Symposium; San Diego, CA, USA. Reston, VA: Internet Society; 2026.

17. Qu, C.; Dai, S.; Wei, X.; et al. Tool learning with large language models: a survey. Front. Comput. Sci. 2025, 19, 198343.

18. Yehudai, A.; Eden, L.; Li, A.; et al. A survey on evaluation of LLM-based agents. In: Findings of the Association for Computational Linguistics: ACL 2026; 2026 Jun; San Diego, California, United States. Stroudsburg, PA, USA: Association for Computational Linguistics; 2026. pp. 26690-714.

19. Mohammadi, M.; Li, Y.; Lo, J.; Yip, W. Evaluation and benchmarking of LLM agents: a survey. In: KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining; Toronto ON Canada. New York, NY, USA: ACM; 2025. pp. 6129-39.

20. Durante, Z.; Huang, Q.; Wake, N.; et al. Agent AI: surveying the horizons of multimodal interaction, arXiv 2024;arXiv:2401.03568v2. Available online: https://doi.org/10.48550/arXiv.2401.03568 [accessed 28 October 2026].

21. Significant Gravitas. AutoGPT. https://github.com/Significant-Gravitas/AutoGPT (accessed 2026-10-28).

22. Nakajima, Y. BabyAGI, 2023. Original 2023 project, archived September 2024. https://github.com/yoheinakajima/babyagi_archive (accessed 2026-10-28).

23. LangChain contributors. LangChain. https://github.com/langchain-ai/langchain (accessed 2026-10-28).

24. Pathak, D.; George, F.; Kumar, H.; et al. Detecting silent failures in multi-agentic AI trajectories (Work In Progress Paper). In: ICPE '26: 17th ACM/SPEC International Conference on Performance Engineering; Florence Italy. New York, NY, USA: ACM; 2026. pp. 33-9.

25. Rabanser, S.; Kapoor, S.; Kirgis, P.; Liu, K.; Utpala, S.; Narayanan, A. Towards a science of AI agent reliability. In: Proceedings of the 43rd International Conference on Machine Learning (Volume 306); 2026 July 6-11; Seoul, Korea. PMLR; 2026. pp. 102769-820. https://raw.githubusercontent.com/mlresearch/v306/main/assets/rabanser26a/rabanser26a.pdf.

26. Winston, C.; Just, R. A Taxonomy of failures in tool-augmented LLMs. In: 2025 IEEE/ACM International Conference on Automation of Software Test (AST); 2025 Apr 28-29; Ottawa, ON, Canada. IEEE; 2025. pp. 125-35.

27. Sapkota, R.; Roumeliotis, K. I.; Karkee, M. AI agents vs. agentic AI: a conceptual taxonomy, applications and challenges. Inform Fusion. 2026, 126, 103599.

28. Bullwinkel, B.; Minnich, A.; Chawla, S.; et al. Lessons from red teaming 100 generative AI products. arXiv 2025;arXiv:2501.07238. Available online: https://doi.org/10.48550/arXiv.2501.07238 [accessed 28 October 2026].

29. Wang, H.; Poskitt, C. M.; Sun, J. AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents. In: ICSE '26: 2026 IEEE/ACM 48th International Conference on Software Engineering; Rio de Janeiro Brazil. New York, NY, USA: ACM; 2026. pp. 2938-50.

30. Syros, G.; Suri, A.; Ginesin, J.; Nita-rotaru, C.; Oprea, A. SAGA: a security architecture for governing AI agentic systems. In: Network and Distributed System Security Symposium 2026; 2026 Feb 23-27; San Diego, CA, USA. Reston, VA: Internet Society; 2026.

31. Khan, R.; Joyce, D.; Habiba, M. AGENTSAFE: a unified framework for ethical assurance and governance in agentic. arXiv 2025;arXiv:2512.03180. Available online: https://doi.org/10.48550/arXiv.2512.03180 [accessed 28 October 2026].

32. Zheng, L.; Chen, J.; Yin, Q.; Zhang, J.; Zeng, X.; Tian, Y. Rethinking the reliability of multi-agent system: a perspective from byzantine fault tolerance. AAAI. 2026, 40, 35012-20.

33. Doshi, A.; Hong, Y.; Xu, C.; Kang, E.; Kapravelos, A.; Kästner, C. Towards verifiably safe tool use for LLM agents. In: ICSE-NIER '26: 2026 IEEE/ACM 48th International Conference on Software Engineering; 2026 Apr 12-18; Rio de Janeiro, Brazil. New York, NY, USA: ACM; 2026. pp. 201-5.

34. Li, P.; Zou, X.; Wu, Z.; et al. SAFEFLOW: a principled protocol for trustworthy and transactional autonomous agent systems. arXiv 2025;arXiv:2506.07564v3. Available online: https://doi.org/10.48550/arXiv.2506.07564 [accessed 28 October 2026].

35. Zhan, Q.; Liang, Z.; Ying, Z.; Kang, D. InjecAgent: benchmarking indirect prompt injections in tool-integrated large language model agents. In: Findings of the Association for Computational Linguistics ACL 2024; 2024 Aug 11-16; Bangkok, Thailand and virtual meeting. Stroudsburg, PA, USA: Association for Computational Linguistics; 2024. pp. 10471-506.

36. Ma, T.; Chen, Y.; Anand, V.; et al. MAESTRO: multi-agent evaluation suite for testing, reliability, and observability. arXiv 2026;arXiv:2601.00481. Available online: https://doi.org/10.48550/arXiv.2601.00481 [accessed 28 October 2026].

37. Andriushchenko, M.; Souly, A.; Dziemian, M.; et al. AgentHarm: a benchmark for measuring harmfulness of LLM agents. In: Proceedings of the Thirteenth International Conference on Learning Representations; 2025 Apr 24-28; Singapore. International Conference on Learning Representations. 2025. pp. 1-36. https://proceedings.iclr.cc/paper_files/paper/2025/file/c493d23af93118975cdbc32cbe7323f5-Paper-Conference.pdf.

38. Shen, Z.; Dai, J.; Zhang, Y.; Yang, M. Security debt in LLM agent applications: a measurement study of vulnerabilities and mitigation trade-offs. In: 2025 40th IEEE/ACM International Conference on Automated Software Engineering (ASE); 2025 Nov 16-20; Seoul, Korea. IEEE; 2025. pp. 559-70.

39. Gajjar, J.; Subramaniakuppusamy, K.; Puthal, R.; Ranaware, K. SecureFixAgent: a hybrid LLM agent for automated python static vulnerability repair. In: 2025 International Conference on Machine Learning and Applications (ICMLA); 2025 Dec 3-5; Boca Raton, FL, USA. IEEE; 2025. pp. 1390-5.

40. Luo, H.; Dai, S.; Ni, C.; et al. AgentAuditor: human-level safety and security evaluation for LLM agents. In: Belgrave D, Zhang C, Lin H, Pascanu R, Koniusz P, Ghassemi M, Chen N, Editors. Advances in Neural Information Processing Systems 38; 2025 Nov 30-Dec 7; San Diego, California, USA and Mexico City, Mexico. San Diego, California, USA: Neural Information Processing Systems Foundation, Inc. (NeurIPS); 2025. pp. 48268-325.

41. Qin, Y.; Liang, S.; Ye, Y.; et al. ToolLLM: facilitating large language models to master 16000+ real-world APIs. In: Proceedings of the Twelfth International Conference on Learning Representations; 2024 May 7-11; Vienna, Austria. International Conference on Learning Representations. 2024. pp. 1-23. Available from: https://proceedings.iclr.cc/paper_files/paper/2024/file/28e50ee5b72e90b50e7196fde8ea260e-Paper-Conference.pdf.

42. Patil, S. G.; Mao, H.; Yan, F.; et al. The Berkeley function calling leaderboard (BFCL): from tool use to agentic evaluation of large language models. In: Proceedings of the 42nd International Conference on Machine Learning (Volume 267); 2025 Jul 13-19. PMLR, 2025; pp. 48371-92. https://proceedings.mlr.press/v267/patil25a.html.

43. He, H.; Yao, W.; Ma, K.; et al. WebVoyager: building an end-to-end web agent with large multimodal models. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers); 2024 Aug 11-16; Bangkok, Thailand. Stroudsburg, PA, USA: Association for Computational Linguistics; 2024. pp. 6864-90.

44. Xie, T.; Zhang, D.; Chen, J.; et al. OSWorld: benchmarking multimodal agents for open-ended tasks in real computer environments. In: Globerson A, Mackey L, Belgrave D, Fan A, Paquet U, Tomczak J, Zhang C, Editors. Advances in Neural Information Processing Systems 37; 2024 Dec 10-15; Vancouver, BC, Canada. San Diego, California, USA: Neural Information Processing Systems Foundation, Inc. (NeurIPS); 2024. pp. 52040-94.

45. Jimenez, C. E.; Yang, J.; Wettig, A.; et al. SWE-bench: can language models resolve real-world GitHub issues? In: Proceeding of Twelfth International Conference on Learning Representations; 2024 May 7-11; Vienna, Austria. Curran Associates, Inc.; 2024. https://proceedings.iclr.cc/paper_files/paper/2024/file/edac78c3e300629acfe6cbe9ca88fb84-Paper-Conference.pdf.

46. Liu, X.; Yu, H.; Zhang, H.; et al. AgentBench: evaluating LLMs as agents. In: Proceeding of Twelfth International Conference on Learning Representations; 2024 May 7-11; Vienna, Austria. Curran Associates, Inc.; 2024. https://proceedings.iclr.cc/paper_files/paper/2024/file/e9df36b21ff4ee211a8b71ee8b7e9f57-Paper-Conference.pdf.

47. Mialon, G.; Fourrier, C.; Swift, C.; Wolf, T.; LeCun, Y.; Scialom, T. GAIA: a benchmark for general AI assistants. In: Proceeding of Twelfth International Conference on Learning Representations; 2024 May 7-11; Vienna, Austria. Curran Associates, Inc.; 2024. Available from: https://proceedings.iclr.cc/paper_files/paper/2024/file/25ae35b5b1738d80f1f03a8713e405ec-Paper-Conference.pdf.

48. Ma, C.; Zhang, J.; Zhu, Z.; et al. AgentBoard: an analytical evaluation board of multi-turn LLM agents. In: Globerson A, Mackey L, Belgrave D, Fan A, Paquet U, Tomczak J, Zhang C, Editors. Advances in Neural Information Processing Systems 37; 2024 Dec 10-15; Vancouver, BC, Canada. San Diego, California, USA: Neural Information Processing Systems Foundation, Inc. (NeurIPS); 2024. pp. 74325-62.

49. Debenedetti, E.; Zhang, J.; Balunovic, M.; Beurer-kellner, L.; Fischer, M.; Tramèr, F. AgentDojo: a dynamic environment to evaluate prompt injection attacks and defenses for LLM agents. In: Globerson A, Mackey L, Belgrave D, Fan A, Paquet U, Tomczak J, Zhang C, Editors. Advances in Neural Information Processing Systems 37; 2024 Dec 10-15; Vancouver, BC, Canada. San Diego, California, USA: Neural Information Processing Systems Foundation, Inc. (NeurIPS); 2024. pp. 82895-920.

50. Wu, D.; Wang, H.; Yu, W.; Zhang, Y.; Chang, K. W.; Yu, D. LongMemEval: benchmarking chat assistants on long-term interactive memory. In: Proceedings of the Thirteenth International Conference on Learning Representations; 2025 Apr 24-28; Singapore. International Conference on Learning Representations. 2025. https://proceedings.iclr.cc/paper_files/paper/2025/file/d813d324dbf0598bbdc9c8e79740ed01-Paper-Conference.pdf.

51. Yao, S.; Shinn, N.; Razavi, P.; Narasimhan, K. τ-bench: a benchmark for tool-agent-user interaction in real-world domains. In: Proceedings of the Thirteenth International Conference on Learning Representations; 2025 Apr 24-28; Singapore. International Conference on Learning Representations. 2025. https://proceedings.iclr.cc/paper_files/paper/2025/file/1b126cc38b8638e07bef37e7b2bb72bf-Paper-Conference.pdf.

52. Barres, V.; Dong, H.; Ray, S.; Si, X.; Narasimhan, K. τ²-bench: evaluating conversational agents in a dual-control environment. arXiv 2025;arXiv:2506.07982v1. Available online: https://doi.org/10.48550/arXiv.2506.07982 [accessed 28 October 2026].

53. Liang, P.; Bommasani, R.; Lee, T.; et al. Holistic evaluation of language models. Trans Mach Learn Res 2023. https://openreview.net/forum?id=iO4LZibEqW.

54. Zheng, L.; Chiang, W.; Sheng, Y.; et al. Judging LLM-as-a-judge with MT-bench and chatbot arena. In: Oh A, Naumann T, Globerson A, Saenko K, Hardt M, Levine S, Editors. Advances in Neural Information Processing Systems 36; 2023 Dec 10-16; New Orleans, Louisiana, USA. San Diego, California, USA: Neural Information Processing Systems Foundation, Inc. (NeurIPS); 2023. pp. 46595-623.

55. Hu, H.; Chen, P.; Zhao, Y.; Chen, Y. AgentSentinel: an end-to-end and real-time security defense framework for computer-use agents. In: CCS '25: ACM SIGSAC Conference on Computer and Communications Security; Taipei Taiwan. New York, NY, USA: ACM; 2025. pp. 3535-49.

56. He, X.; Wu, D.; Zhai, Y.; Sun, K. SentinelAgent: graph-based anomaly detection in multi-agent systems. arXiv 2025;arXiv:2505.24201. Available online: https://doi.org/10.48550/arXiv.2505.24201 [accessed 28 October 2026].

57. Ro, Y.; Qiu, H.; Goiri, Í.; et al. Sherlock: reliable and efficient agentic workflow execution. arXiv 2025; arXiv:2511.00330. Available online: https://doi.org/10.48550/arXiv.2511.00330 [accessed 28 October 2026].

58. Liu, F.; Zhang, Y.; Luo, J.; et al. Make agent defeat agent: automatic detection of taint-style vulnerabilities in LLM-based agents. In: 34th USENIX Security Symposium (USENIX Security 25); 2025 Aug 13-15; Seattle, WA, USA: USENIX Association, 2025; pp. 3767-86. https://www.usenix.org/conference/usenixsecurity25/presentation/liu-fengyu.

59. Costa, M.; Köpf, B.; Kolluri, A.; et al. Securing AI agents with information-flow control. arXiv 2025; arXiv:2505.23643. Available online: https://doi.org/10.48550/arXiv.2505.23643 [accessed 28 October 2026].

60. Debenedetti, E.; Shumailov, I.; Fan, T.; et al. Defeating prompt injections by design. arXiv 2025; arXiv:2503.18813. Available online: https://doi.org/10.48550/arXiv.2503.18813 [accessed 28 October 2026].

61. Chen, S.; Piet, J.; Sitawarin, C.; Wagner, D. StruQ: defending against prompt injection with structured queries. 34th USENIX Security Symposium (USENIX Security 25) ; 2025 Aug 13-15; Seattle, WA, USA: USENIX Association, 2025; pp. 2383-400. Available from: https://www.usenix.org/conference/usenixsecurity25/presentation/chen-sizhe.

62. Chen, S.; Zharmagambetov, A.; Mahloujifar, S.; Chaudhuri, K.; Wagner, D.; Guo, C. SecAlign: defending against prompt injection with preference optimization. In: CCS '25: ACM SIGSAC Conference on Computer and Communications Security; Taipei Taiwan. New York, NY, USA: ACM; 2025. pp. 2833-47.

63. Shi, S.; Wang, X.; Zhang, C.; et al. Think twice before you act: protecting LLM agents against tool description poisoning via isolated planning. In: Proceedings of the 43rd International Conference on Machine Learning (Volume 306); 2026 July 6-11; Seoul, Korea. PMLR; 2026. pp. 112320-37. https://openreview.net/forum?id=jiNw5AgBbw.

64. Li, K.; Zhao, T.; Zhou, W.; Hu, S. DORA: Dynamic optimization prompt for continuous reflection of LLM-based agent. In: Proceedings of the 31st International Conference on Computational Linguistics; 2025 Jan 19-24; Abu Dhabi, UAE: Association for Computational Linguistics, 2025; pp. 7546-57. https://aclanthology.org/2025.coling-main.504/.

65. Gou, Z.; Shao, Z.; Gong, Y.; et al. CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing. In: Proceedings of the Twelfth International Conference on Learning Representations; 2024 May 7-11; Vienna, Austria. International Conference on Learning Representations. 2024. https://proceedings.iclr.cc/paper_files/paper/2024/file/fef126561bbf9d4467dbb8d27334b8fe-Paper-Conference.pdf.

66. Zhao, A.; Huang, D.; Xu, Q.; Lin, M.; Liu, Y.; Huang, G. ExpeL: LLM agents are experiential learners. AAAI. 2024, 38, 19632-42.

67. Patel, K.; Surendira, S.; George, J.; Kapale, S. The six sigma agent: achieving enterprise-grade reliability in LLM systems through consensus-driven decomposed execution. arXiv 2026; arXiv:2601.22290. Available online: https://doi.org/10.48550/arXiv.2601.22290 [accessed 28 October 2026].

68. Liu, B.; Jiang, Y.; Zhang, X.; et al. LLM+P: empowering large language models with optimal planning proficiency. arXiv 2023; arXiv:2304.11477v3. Available online: https://doi.org/10.48550/arXiv.2304.11477 [accessed 28 October 2026].

69. Zhou, A.; Yan, K.; Shlapentokh-Rothman, M.; Wang, H.; Wang, Y. X. Language agent tree search unifies reasoning, acting, and planning in language models. In: Proceedings of the 41st International Conference on Machine Learning (Volume 235); 2024 Jul 21-27; Vienna, Austria. PMLR, 2024; pp. 62138-60. https://proceedings.mlr.press/v235/zhou24r.html.

70. Packer, C.; Wooders, S.; Lin, K.; et al. MemGPT: towards LLMs as operating systems. arXiv 2024; arXiv:2310.08560v2. Available online: https://doi.org/10.48550/arXiv.2310.08560 [accessed 28 October 2026].

71. Zhong, W.; Guo, L.; Gao, Q.; Ye, H.; Wang, Y. MemoryBank: enhancing large language models with long-term memory. AAAI. 2024, 38, 19724-31.

72. Xu, W.; Liang, Z.; Mei, K.; Gao, H.; Tan, J.; Zhang, Y. A-Mem: agentic memory for LLM agents. In: Belgrave D, Zhang C, Lin H, Pascanu R, Koniusz P, Ghassemi M, Chen N, Editors. Advances in Neural Information Processing Systems 38; 2025 Nov 30-Dec 7; San Diego, California, USA and Mexico City, Mexico. San Diego, California, USA: Neural Information Processing Systems Foundation, Inc. (NeurIPS); 2025. pp. 20004-31.

73. Wang, Z. Z.; Mao, J.; Fried, D.; Neubig, G. Agent workflow memory. In: Proceedings of the 42nd International Conference on Machine Learning (Volume 267); 2025 Jul 13-19. PMLR, 2025; pp. 63897-911. Available from: https://proceedings.mlr.press/v267/wang25bx.html.

74. Schick, T.; Dwivedi-Yu, J.; Dessi, R.; et al. Toolformer: language models can teach themselves to use tools. In: Oh A, Naumann T, Globerson A, Saenko K, Hardt M, Levine S, Editors. Advances in Neural Information Processing Systems 36; 2023 Dec 10-16; New Orleans, Louisiana, USA. San Diego, California, USA: Neural Information Processing Systems Foundation, Inc. (NeurIPS); 2023. pp. 68539-51.

75. Shinn, N.; Cassano, F.; Gopinath, A.; Narasimhan, K.; Yao, S. Reflexion: language agents with verbal reinforcement learning. In: Oh A, Naumann T, Globerson A, Saenko K, Hardt M, Levine S, Editors. Advances in Neural Information Processing Systems 36; 2023 Dec 10-16; New Orleans, Louisiana, USA. San Diego, California, USA: Neural Information Processing Systems Foundation, Inc. (NeurIPS); 2023. pp. 8634-52.

76. Ma, X. Towards Trustworthy AIoT systems: an interaction-centric perspective. In: MobiSys Companion '26: 24th Annual International Conference on Mobile Systems, Applications and Services Companion; University of Cambridge Cambridge United Kingdom. New York, NY, USA: ACM; 2026. pp. 148-9.

77. Zhou, C.; Hu, S.; Gao, J.; Huang, X.; Zhuang, W.; Shen, X. User-centric immersive communications in 6G: a data-oriented framework via digital twin. IEEE Wireless Commun. 2025, 32, 122-9.

78. Ma, X.; Lu, H.; Dai, X.; Zhang, Y. TrustTwin: world-model-enhanced twins for trustworthy AIoT decision making. In: 2026 IEEE/CIC International Conference on Communications in China (ICCC); 2026 Aug 7-9; Wuhan, China. IEEE; 2026. pp. 271-6.

79. Betzer, J. S.; Boudjadar, J.; Frasheri, M.; Talasila, P. Digital twin enabled runtime verification for autonomous mobile robots under uncertainty. In: 2024 28th International Symposium on Distributed Simulation and Real Time Applications (DS-RT); 2024 Oct 7-9; Urbino, Italy. IEEE; 2024. pp. 10-7.

80. Zhuang, Y.; Chen, K.; Duan, Y.; et al. AgentRewind: recoverable execution for long-horizon LLM agents. arXiv 2026; arXiv:2608.14380. Available online: https://doi.org/10.48550/arXiv.2608.14380 [accessed 28 October 2026].

81. Zheng, Y.; Yang, Y.; Zhang, W.; Quinn, A. ACRFence: preventing semantic rollback attacks in agent checkpoint-restore. arXiv 2026; arXiv:2603.20625. Available online: https://doi.org/10.48550/arXiv.2603.20625 [accessed 28 October 2026].