Page 243 - 《软件学报》2026年第6期

2562 软件学报 2026 年第 37 卷第 6 期

[26] Jiang JC, Li Y, Nie J, Li JB, Wen BQ, Gadekallu TR. Integrating large language models with cross-modal data fusion for advanced
intelligent transportation systems in sustainable cities development. Applied Soft Computing, 2025, 177: 113278. [doi: 10.1016/j.asoc.
2025.113278]
[27] Chen C, Yin YC, Shang LF, Jiang X, Qin YJ, Wang FY, Wang Z, Chen X, Liu ZY, Liu Q. bert2BERT: Towards reusable pretrained
language models. In: Proc. of the 60th Annual Meeting of the Association for Computational Linguistics (Vol. 1: Long Papers). Dublin:
ACL, 2022. 2134–2148. [doi: 10.18653/v1/2022.acl-long.151]
[28] Xiao CJ, Zhang ZY, Song CY, et al. Configurable foundation models: Building LLMs from a modular perspective. arXiv:2409.02877,
2024.
[29] Wang S, Wang CH, Gao J, Qi Z, Zheng HY, Liao XX. Feature alignment-based knowledge distillation for efficient compression of large
language models. arXiv:2412.19449, 2024.
[30] Ainsworth SK, Hayase J, Srinivasa S. Git re-basin: Merging models modulo permutation symmetries. arXiv:2209.04836, 2023.
[31] Liu TL, Guo SM, Bianco L, Calandriello D, Berthet Q, Llinares F, Hoffmann J, Dixon L, Valko M, Blondel M. Decoding-time
realignment of language models. In: Proc. of the 41st Int’l Conf. on Machine Learning. Vienna: JMLR.org, 2024. 31015–31031.
[32] Lu P, Peng BL, Cheng H, Galley M, Chang KW, Wu YN, Zhu SC, Gao JF. Chameleon: Plug-and-play compositional reasoning with
large language models. In: Proc. of the 37th Int’l Conf. on Neural Information Processing Systems. New Orleans: Curran Associates Inc.,
2023. 43447–43478.
[33] Aggarwal P, Madaan A, Anand A, Potharaju SP, Mishra S, Zhou P, Gupta A, Rajagopal D, Kappaganthu K, Yang YM, Upadhyay S,
Faruqui M, Mausam. AutoMix: Automatically mixing language models. In: Proc. of the 38th Int’l Conf. on Neural Information
Processing Systems. Vancouver: Curran Associates Inc., 2025. 131000–131034.
[34] Zhang MJ, Shen XM, Cao JN, Cui ZY, Jiang S. EdgeShard: Efficient LLM inference via collaborative edge computing. IEEE Internet of
Things Journal, 2025, 12(10): 13119–13131. [doi: 10.1109/JIOT.2024.3524255]
[35] Jiang DF, Ren X, Lin BY. LLM-Blender: Ensembling large language models with pairwise ranking and generative fusion. In: Proc. of the
61st Annual Meeting of the Association for Computational Linguistics (Vol. 1: Long Papers). Toronto: ACL, 2023. 14165–14178. [doi:
10.18653/v1/2023.acl-long.792]
[36] Brown B, Juravsky J, Ehrlich R, Clark R, Le QV, Ré C, Mirhoseini A. Large language monkeys: Scaling inference compute with repeated
sampling. arXiv:2407.21787, 2024.
[37] Zhang YS, Sun RX, Chen YF, Pfister T, Zhang R, Arık SÖ. Chain of agents: Large language models collaborating on long-context tasks.
In: Proc. of the 38th Int’l Conf. on Neural Information Processing Systems. Vancouver: Curran Associates Inc., 2025. 132208–132237.
[38] Zhao J, Zu C, Hao X, Lu Y, He W, Ding YW, Gui T, Zhang Q, Huang XJ. LONGAGENT: Achieving question answering for 128k-
Token-Long documents through multi-agent collaboration. In: Proc. of the 2024 Conf. on Empirical Methods in Natural Language
Processing. Miami: ACL, 2024. 16310–16324. [doi: 10.18653/v1/2024.emnlp-main.912]
[39] Sun XF, Li XY, Zhang SY, Wang SH, Wu F, Li JW, Zhang TW, Wang GY. Sentiment analysis through LLM negotiations.
arXiv:2311.01876, 2023.
[40] Bo XH, Zhang ZY, Dai QY, Feng XY, Wang L, Li R, Chen X, Wen JR. Reflective multi-agent collaboration based on large language
models. In: Proc. of the 38th Int’l Conf. on Neural Information Processing Systems. Vancouver: Curran Associates Inc., 2025.
138595–138631.
[41] Wang LQ, Zhou YT, Zhuang HY, Li QS, Cui D, Zhao YT, Wang L. Unity is strength: Collaborative LLM-based agents for code reviewer
recommendation. In: Proc. of the 39th IEEE/ACM Int’l Conf. on Automated Software Engineering. Sacramento: ACM, 2024. 2235–2239.
[doi: 10.1145/3691620.3695291]
[42] Ishibashi Y, Nishimura Y. Self-organized agents: A LLM multi-agent framework toward ultra large-scale code generation and
optimization. arXiv:2404.02183, 2024.
[43] Wang XY, Chen YY, Yuan LF, Zhang YZ, Li YZ, Peng H, Ji H. Executable code actions elicit better LLM agents. In: Proc. of the 41st
Int’l Conf. on Machine Learning. Vienna: JMLR.org, 2024. 50208–50232.
[44] Hari SN, Thomson M. Tryage: Real-time, intelligent routing of user prompts to large language models. arXiv:2308.11601, 2023.
[45] Kim S, Suk J, Longpre S, Lin BY, Shin J, Welleck S, Neubig G, Lee M, Lee K, Seo M. Prometheus 2: An open source language model
specialized in evaluating other language models. In: Proc. of the 2024 Conf. on Empirical Methods in Natural Language Processing.
Miami: ACL, 2024. 4334–4353. [doi: 10.18653/v1/2024.emnlp-main.248]
[46] Ye S, Kim D, Kim S, Hwang H, Kim S, Jo Y, Thorne J, Kim J, Seo M. FLASK: Fine-grained language model evaluation based on
alignment skill sets. arXiv:2307.10928, 2024.
[47] Chen SH, Jiang WS, Lin BJ, Kwok JT, Zhang Y. RouterDC: Query-based router by dual contrastive learning for assembling large