{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T04:08:14Z","timestamp":1779422894619,"version":"3.53.1"},"publisher-location":"New York, NY, USA","reference-count":61,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T00:00:00Z","timestamp":1779753600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,5,26]]},"DOI":"10.1145\/3786335.3813143","type":"proceedings-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T03:16:22Z","timestamp":1779419782000},"page":"46-60","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Tressoir: Unifying Online, Offline, and HIL Design and Evolution of Multi-Agent Systems via Interpretable Blueprints"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8422-5212","authenticated-orcid":false,"given":"Amadou","family":"Latyr Ngom","sequence":"first","affiliation":[{"name":"EECS, Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5487-952X","authenticated-orcid":false,"given":"Ziniu","family":"Wu","sequence":"additional","affiliation":[{"name":"EECS, Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5497-0481","authenticated-orcid":false,"given":"Jason","family":"Mohoney","sequence":"additional","affiliation":[{"name":"EECS, Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3311-9800","authenticated-orcid":false,"given":"James","family":"Moore","sequence":"additional","affiliation":[{"name":"EECS, Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0081-7991","authenticated-orcid":false,"given":"Alex","family":"Zhang","sequence":"additional","affiliation":[{"name":"EECS, Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7470-3265","authenticated-orcid":false,"given":"Samuel","family":"Madden","sequence":"additional","affiliation":[{"name":"EECS, Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2414-2759","authenticated-orcid":false,"given":"Tim","family":"Kraska","sequence":"additional","affiliation":[{"name":"EECS, Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,5,26]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Agent Skills. 2026. Agent Skills Specification. https:\/\/agentskills.io\/specification."},{"key":"e_1_3_3_2_3_2","unstructured":"Anthropic. 2025. Claude Code: An Agentic Coding Tool. https:\/\/docs.anthropic.com\/en\/docs\/claude-code. Released February 2025; generally available May 2025."},{"key":"e_1_3_3_2_4_2","unstructured":"Anthropic. 2026. Claude Code Agent Teams: Multi-Session Orchestration. https:\/\/code.claude.com\/docs\/en\/agent-teams. Accessed: 2026-02-15."},{"key":"e_1_3_3_2_5_2","unstructured":"Ibragim Badertdinov Alexander Golubev Maksim Nekrashevich Anton Shevtsov Simon Karasik Andrei Andriushchenko Maria Trofimova Daria Litvintseva and Boris Yangel. 2025. SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.20411 (2025)."},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.5555\/993954"},{"key":"e_1_3_3_2_7_2","unstructured":"Birgitta B\u00f6ckeler. 2025. Understanding Spec-Driven-Development: Kiro spec-kit and Tessl. https:\/\/martinfowler.com\/articles\/exploring-gen-ai\/sdd-3-tools.html martinfowler.com."},{"key":"e_1_3_3_2_8_2","volume-title":"Proceedings of the Twelfth International Conference on Learning Representations (ICLR)","author":"Cai Tianle","year":"2024","unstructured":"Tianle Cai, Xuezhi Wang, Tengyu Ma, Xinyun Chen, and Denny Zhou. 2024. Large Language Models as Tool Makers. In Proceedings of the Twelfth International Conference on Learning Representations (ICLR). arXiv:https:\/\/arXiv.org\/abs\/2305.17126."},{"key":"e_1_3_3_2_9_2","volume-title":"Proceedings of the Twelfth International Conference on Learning Representations (ICLR)","author":"Chen Weize","year":"2024","unstructured":"Weize Chen, Yusheng Su, Jingwei Zuo, Cheng Yang, Chenfei Yuan, Chi-Min Chan, Heyang Yu, Yaxi Lu, Yi-Hsin Hung, Chen Qian, Yujia Qin, Xin Cong, Ruobing Xie, Zhiyuan Liu, Maosong Sun, and Jie Zhou. 2024. AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors. In Proceedings of the Twelfth International Conference on Learning Representations (ICLR). arXiv:https:\/\/arXiv.org\/abs\/2308.10848."},{"key":"e_1_3_3_2_10_2","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Cheng Ching-An","year":"2024","unstructured":"Ching-An Cheng, Allen Nie, and Adith Swaminathan. 2024. Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs. In Advances in Neural Information Processing Systems (NeurIPS). arXiv:https:\/\/arXiv.org\/abs\/2406.16218."},{"key":"e_1_3_3_2_11_2","unstructured":"Xiang Deng Jeff Da Edwin Pan Yannis\u00a0Yiming He Charles Ide Kanak Garg Niklas Lauffer Andrew Park Nitin Pasari Chetan Rane Karmini Sampath Maya Krishnan Srivatsa Kundurthy Sean Hendryx Zifan Wang Vijay Bharadwaj Jeff Holm Raja Aluri Chen Bo\u00a0Calvin Zhang Noah Jacobson Bing Liu and Brad Kenstler. 2025. SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks? arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2509.16941 (2025)."},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3106237.3121282"},{"key":"e_1_3_3_2_13_2","unstructured":"G5 Labs. 2026. G5: Generation 5 Programming. https:\/\/g5labs.ai\/."},{"key":"e_1_3_3_2_14_2","unstructured":"Huan-ang Gao Jiayi Geng Wenyue Hua Mengkang Hu Xinzhe Juan Hongzhang Liu Shilong Liu Jiahao Qiu Xuan Qi Yiran Wu Hongru Wang Han Xiao Yuhang Zhou Shaokun Zhang Jiayi Zhang Jinyu Xiang Yixiong Fang Qiwen Zhao Dongrui Liu Qihan Ren Cheng Qian Zhenghailong Wang Minda Hu Huazheng Wang Qingyun Wu Heng Ji and Mengdi Wang. 2025. A Survey of Self-Evolving Agents: What When How and Where to Evolve on the Path to Artificial Super Intelligence. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2507.21046 (2025)."},{"key":"e_1_3_3_2_15_2","unstructured":"GitHub. 2025. GitHub Copilot. https:\/\/github.com\/copilot."},{"key":"e_1_3_3_2_16_2","unstructured":"GitHub. 2025. GitHub Copilot: Agents on GitHub. https:\/\/github.com\/features\/copilot\/agents. Accessed: 2026-02-15."},{"key":"e_1_3_3_2_17_2","unstructured":"GitHub. 2025. A Unified Experience for All Coding Agents. https:\/\/code.visualstudio.com\/blogs\/2025\/11\/03\/unified-agent-experience. Accessed: 2026-02-15."},{"key":"e_1_3_3_2_18_2","unstructured":"Alex Gu Naman Jain Wen-Ding Li Manish Shetty Yijia Shao Ziyang Li Diyi Yang Kevin Ellis Koushik Sen and Armando Solar-Lezama. 2025. Challenges and Paths Towards AI for Software Engineering. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.22625 (2025)."},{"key":"e_1_3_3_2_19_2","volume-title":"Proceedings of the Twelfth International Conference on Learning Representations (ICLR)","author":"Guo Qingyan","year":"2024","unstructured":"Qingyan Guo, Rui Wang, Junliang Guo, Bei Li, Kaitao Song, Xu Tan, Guoqing Liu, Jiang Bian, and Yujiu Yang. 2024. Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers. In Proceedings of the Twelfth International Conference on Learning Representations (ICLR). arXiv:https:\/\/arXiv.org\/abs\/2309.08532."},{"key":"e_1_3_3_2_20_2","unstructured":"H Company. 2025. Holo2: Open Foundation Models for Navigation and Computer Use Agents. https:\/\/huggingface.co\/collections\/Hcompany\/holo2 Model release."},{"key":"e_1_3_3_2_21_2","unstructured":"Zishun He Mengqi Li Dongyuan Chen and Xinyu Liu. 2025. Enabling Self-Improving Agents to Learn at Test Time With Human-In-The-Loop Guidance. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2507.17131 (2025)."},{"key":"e_1_3_3_2_22_2","volume-title":"Proceedings of the Twelfth International Conference on Learning Representations (ICLR)","author":"Hong Sirui","year":"2024","unstructured":"Sirui Hong, Mingchen Zhuge, Jiaqi Chen, Xiawu Zheng, Yuheng Cheng, Ceyao Zhang, Jinlin Wang, Zili Wang, Steven Ka\u00a0Shing Yau, Zijuan Lin, Liyang Zhou, Chenyu Ran, Lingfeng Xiao, Chenglin Wu, and J\u00fcrgen Schmidhuber. 2024. MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework. In Proceedings of the Twelfth International Conference on Learning Representations (ICLR). arXiv:https:\/\/arXiv.org\/abs\/2308.00352."},{"key":"e_1_3_3_2_23_2","volume-title":"Proceedings of the Thirteenth International Conference on Learning Representations (ICLR)","author":"Hu Shengran","year":"2025","unstructured":"Shengran Hu, Cong Lu, and Jeff Clune. 2025. Automated Design of Agentic Systems. In Proceedings of the Thirteenth International Conference on Learning Representations (ICLR). arXiv:https:\/\/arXiv.org\/abs\/2408.08435."},{"key":"e_1_3_3_2_24_2","volume-title":"Proceedings of the Thirteenth International Conference on Learning Representations (ICLR)","author":"Hu Yue","year":"2025","unstructured":"Yue Hu, Yuzhu Cai, Yaxin Du, Xinyu Zhu, Xiangrui Liu, Zijie Yu, Yuchen Hou, Shuo Tang, and Siheng Chen. 2025. EvoMAC: Self-Evolving Multi-Agent Collaboration Networks for Software Development. In Proceedings of the Thirteenth International Conference on Learning Representations (ICLR). arXiv:https:\/\/arXiv.org\/abs\/2410.16946."},{"key":"e_1_3_3_2_25_2","unstructured":"Zhiyuan Jiang Shenghao Xie Wenyi Li Wenqiang Zu Peihang Li Jiahao Qiu Siqi Pei Lei Ma Tiejun Huang Mengdi Wang and Shilong Liu. 2025. Zoom in Click out: Unlocking and Evaluating the Potential of Zooming for GUI Grounding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2512.05941 (2025)."},{"key":"e_1_3_3_2_26_2","volume-title":"Proceedings of the Twelfth International Conference on Learning Representations (ICLR)","author":"Jimenez Carlos\u00a0E.","year":"2024","unstructured":"Carlos\u00a0E. Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik\u00a0R. Narasimhan. 2024. SWE-bench: Can Language Models Resolve Real-World GitHub Issues?. In Proceedings of the Twelfth International Conference on Learning Representations (ICLR). Oral presentation. arXiv:https:\/\/arXiv.org\/abs\/2310.06770."},{"key":"e_1_3_3_2_27_2","volume-title":"Proceedings of the Twelfth International Conference on Learning Representations (ICLR)","author":"Khattab Omar","year":"2024","unstructured":"Omar Khattab, Arnav Singhvi, Paridhi Maheshwari, Zhiyuan Zhang, Keshav Santhanam, Sri Vardhamanan, Saiful Haq, Ashutosh Sharma, Thomas\u00a0T. Joshi, Hanna Moazam, Heather Miller, Matei Zaharia, and Christopher Potts. 2024. DSPy: Compiling Declarative Language Model Calls into State-of-the-Art Pipelines. In Proceedings of the Twelfth International Conference on Learning Representations (ICLR). Oral presentation. arXiv:https:\/\/arXiv.org\/abs\/2310.03714."},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-17511-4_20"},{"key":"e_1_3_3_2_29_2","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Li Jinyang","year":"2025","unstructured":"Jinyang Li, Xiaolong Li, Ge Qu, Per Jacobsson, Bowen Qin, Binyuan Hui, Shuzheng Si, Nan Huo, Xiaohan Xu, Yue Zhang, Ziwei Tang, Yuanshuai Li, Florensia Widjaja, Xintong Zhu, Feige Zhou, Yongfeng Huang, Yannis Papakonstantinou, Fatma Ozcan, Chenhao Ma, and Reynold Cheng. 2025. SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications. In Advances in Neural Information Processing Systems (NeurIPS). Introduces the BIRD-CRITIC benchmark. arXiv:https:\/\/arXiv.org\/abs\/2506.18951."},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755688"},{"key":"e_1_3_3_2_31_2","volume-title":"Proceedings of the Conference on Language Modeling (COLM)","author":"Liu Zijun","year":"2024","unstructured":"Zijun Liu, Yanzhe Zhang, Peng Li, Yang Liu, and Diyi Yang. 2024. DyLAN: A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration. In Proceedings of the Conference on Language Modeling (COLM). arXiv:https:\/\/arXiv.org\/abs\/2310.02170."},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3759429.3762628"},{"key":"e_1_3_3_2_33_2","unstructured":"Moonshot AI. 2026. Kimi K2.5 Agent Swarm. https:\/\/www.kimi.com\/ai-models\/kimi-k2-5."},{"key":"e_1_3_3_2_34_2","unstructured":"Hussein Mozannar Gagan Bansal Cheng Tan Adam Fourney Victor Dibia Jingya Chen Jack Gerrits Tyler Payne Matheus\u00a0Kunzler Maldaner Madeleine Grunde-McLaughlin Eric Zhu Griffin Bassman Jacob Alber Peter Chang Ricky Loynd Friederike Niedtner Ece Kamar Maya Murad Rafah Hosn and Saleema Amershi. 2025. Magentic-UI: Towards Human-in-the-Loop Agentic Systems. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2507.22358 (2025)."},{"key":"e_1_3_3_2_35_2","unstructured":"Alexander Novikov Ng\u00e2n V\u0169 Marvin Eisenberger Emilien Dupont Po-Sen Huang Adam\u00a0Zsolt Wagner Sergey Shirobokov Borislav Kozlovskii Francisco J.\u00a0R. Ruiz Abbas Mehrabian M.\u00a0Pawan Kumar Abigail See Swarat Chaudhuri George Holland Alex Davies Sebastian Nowozin Pushmeet Kohli and Matej Balog. 2025. AlphaEvolve: A coding agent for scientific and algorithmic discovery. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.13131 (2025)."},{"key":"e_1_3_3_2_36_2","unstructured":"OpenAI. 2026. Why SWE-bench Verified no longer measures frontier coding capabilities. https:\/\/openai.com\/index\/why-we-no-longer-evaluate-swe-bench-verified\/. OpenAI Research publication. Accessed 2026-02-23."},{"key":"e_1_3_3_2_37_2","unstructured":"Deepak\u00a0Babu Piskala. 2026. Spec-Driven Development: From Code to Contract in the Age of AI Coding Assistants. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2602.00180 (2026)."},{"key":"e_1_3_3_2_38_2","volume-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Qian Chen","year":"2024","unstructured":"Chen Qian, Wei Liu, Hongzhang Liu, Nuo Chen, Yufan Dang, Jiahao Li, Cheng Yang, Weize Chen, Yusheng Su, Xin Cong, Juyuan Xu, Dahai Li, Zhiyuan Liu, and Maosong Sun. 2024. ChatDev: Communicative Agents for Software Development. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL). arXiv:https:\/\/arXiv.org\/abs\/2307.07924."},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","unstructured":"Maxime Robeyns Martin Szummer and Laurence Aitchison. 2025. A Self-Improving Coding Agent. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.15228 (2025). 10.48550\/arXiv.2504.15228","DOI":"10.48550\/arXiv.2504.15228"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"crossref","unstructured":"Bernardino Romera-Paredes Mohammadamin Barekatain Alexander Novikov Matej Balog M.\u00a0Pawan Kumar Emilien Dupont Francisco J.\u00a0R. Ruiz Jordan\u00a0S. Ellenberg Pengming Wang Omar Fawzi Pushmeet Kohli and Alhussein Fawzi. 2024. Mathematical discoveries from program search with large language models. Nature 625 7995 (2024) 468\u2013475.","DOI":"10.1038\/s41586-023-06924-6"},{"key":"e_1_3_3_2_41_2","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Shinn Noah","year":"2023","unstructured":"Noah Shinn, Federico Cassano, Edward Berman, Ashutosh Gopinath, Karthik Narasimhan, and Shunyu Yao. 2023. Reflexion: Language Agents with Verbal Reinforcement Learning. In Advances in Neural Information Processing Systems (NeurIPS). arXiv:https:\/\/arXiv.org\/abs\/2303.11366."},{"key":"e_1_3_3_2_42_2","volume-title":"Proceedings of the 47th International Conference on Software Engineering, Software Engineering in Practice (ICSE-SEIP)","author":"Takerngsaksiri Wannita","year":"2025","unstructured":"Wannita Takerngsaksiri, Jirat Pasuksmit, Patanamon Thongtanunam, Chakkrit Tantithamthavorn, Ruixiong Zhang, Fan Jiang, Jing Li, Evan Cook, Kun Chen, and Ming Wu. 2025. Human-In-the-Loop Software Development Agents. In Proceedings of the 47th International Conference on Software Engineering, Software Engineering in Practice (ICSE-SEIP). arXiv:https:\/\/arXiv.org\/abs\/2411.12924."},{"key":"e_1_3_3_2_43_2","unstructured":"Guanzhi Wang Yuqi Xie Yunfan Jiang Ajay Mandlekar Chaowei Xiao Yuke Zhu Linxi Fan and Anima Anandkumar. 2024. Voyager: An Open-Ended Embodied Agent with Large Language Models. Transactions on Machine Learning Research (TMLR) (2024). Originally arXiv:https:\/\/arXiv.org\/abs\/2305.16291 May 2023."},{"key":"e_1_3_3_2_44_2","volume-title":"Proceedings of the Thirteenth International Conference on Learning Representations (ICLR)","author":"Wang Junlin","year":"2025","unstructured":"Junlin Wang, Jue Wang, Ben Athiwaratkun, Ce Zhang, and James Zou. 2025. Mixture-of-Agents Enhances Large Language Model Capabilities. In Proceedings of the Thirteenth International Conference on Learning Representations (ICLR). arXiv:https:\/\/arXiv.org\/abs\/2406.04692."},{"key":"e_1_3_3_2_45_2","unstructured":"Kun Wang Guibin Zhang ManKit Ye Xinyu Deng Dongxia Wang Xiaobin Hu Jinyang Guo Yang Liu and Yufei Guo. 2025. MAS2: Self-Generative Self-Configuring Self-Rectifying Multi-Agent Systems. arxiv:https:\/\/arXiv.org\/abs\/2509.24323\u00a0[cs.MA] https:\/\/arxiv.org\/abs\/2509.24323"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"crossref","unstructured":"Lei Wang Chen Ma Xueyang Feng Zeyu Zhang Hao Yang Jingsen Zhang Zhiyuan Chen Jiakai Tang Xu Chen Yankai Lin Wayne\u00a0Xin Zhao Zhewei Wei and Ji-Rong Wen. 2024. A Survey on Large Language Model based Autonomous Agents. Frontiers of Computer Science (2024). arXiv:https:\/\/arXiv.org\/abs\/2308.11432.","DOI":"10.1007\/s11704-024-40231-1"},{"key":"e_1_3_3_2_47_2","unstructured":"Wenyi Wang Piotr Pi\u0119kos Li Nanbo Firas Laakom Yimeng Chen Mateusz Ostaszewski Mingchen Zhuge and J\u00fcrgen Schmidhuber. 2025. Huxley-G\u00f6del Machine: Human-Level Coding Agent Development by an Approximation of the Optimal Self-Improving Machine. arxiv:https:\/\/arXiv.org\/abs\/2510.21614\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2510.21614"},{"key":"e_1_3_3_2_48_2","unstructured":"Xingyao Wang Boxuan Li Yufan Song Frank\u00a0F. Xu Xiangru Tang Mingchen Zhuge Jiayi Pan Yueqi Song Bowen Li Jaskirat Singh Hoang\u00a0H. Tran Fuqiang Li Ren Ma Mingzhang Zheng Bill Qian Yanjun Shao Niklas Muennighoff Yizhe Zhang Binyuan Hui Junyang Lin Robert Brennan Hao Peng Heng Ji and Graham Neubig. 2024. OpenHands: An Open Platform for AI Software Developers as Generalist Agents. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.16741 (2024)."},{"key":"e_1_3_3_2_49_2","volume-title":"Proceedings of the Conference on Language Modeling (COLM)","author":"Wu Qingyun","year":"2024","unstructured":"Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Jiale Liu, Ahmed\u00a0Hassan Awadallah, Ryen\u00a0W. White, Doug Burger, and Chi Wang. 2024. AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework. In Proceedings of the Conference on Language Modeling (COLM). arXiv:https:\/\/arXiv.org\/abs\/2308.08155."},{"key":"e_1_3_3_2_50_2","volume-title":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Xi Zhiheng","year":"2025","unstructured":"Zhiheng Xi, Yiwen Ding, Wenxiang Chen, Boyang Hong, Honglin Guo, Junzhe Wang, Dingwen Yang, Chenyang Liao, Xin Guo, Wei He, Songyang Gao, Lu Chen, Rui Zheng, Yicheng Zou, Tao Gui, Qi Zhang, Xipeng Qiu, Xuanjing Huang, Zuxuan Wu, and Yu-Gang Jiang. 2025. AgentGym: Evolving Large Language Model-based Agents across Diverse Environments. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL). arXiv:https:\/\/arXiv.org\/abs\/2406.04151."},{"key":"e_1_3_3_2_51_2","unstructured":"Chunqiu\u00a0Steven Xia Zhe Wang Yan Yang Yuxiang Wei and Lingming Zhang. 2025. Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly? arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2511.13646 (2025)."},{"key":"e_1_3_3_2_52_2","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Yang John","year":"2024","unstructured":"John Yang, Carlos\u00a0E. Jimenez, Alexander Wettig, Kilian Lieret, Shunyu Yao, Karthik Narasimhan, and Ofir Press. 2024. SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering. In Advances in Neural Information Processing Systems (NeurIPS), Vol.\u00a037. arXiv:https:\/\/arXiv.org\/abs\/2405.15793."},{"key":"e_1_3_3_2_53_2","volume-title":"Proceedings of the Eleventh International Conference on Learning Representations (ICLR)","author":"Yao Shunyu","year":"2023","unstructured":"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 Proceedings of the Eleventh International Conference on Learning Representations (ICLR). arXiv:https:\/\/arXiv.org\/abs\/2210.03629."},{"key":"e_1_3_3_2_54_2","volume-title":"Proceedings of the Twelfth International Conference on Learning Representations (ICLR)","author":"Yuan Lifan","year":"2024","unstructured":"Lifan Yuan, Yangyi Chen, Xingyao Wang, Yi\u00a0R. Fung, Hao Peng, and Heng Ji. 2024. CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets. In Proceedings of the Twelfth International Conference on Learning Representations (ICLR). arXiv:https:\/\/arXiv.org\/abs\/2309.17428."},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"publisher","unstructured":"Mert Yuksekgonul Federico Bianchi Joseph Boen Sheng Liu Pan Lu Zhi Huang Carlos Guestrin and James Zou. 2025. Optimizing Generative AI by Backpropagating Language Model Feedback. Nature 639 (2025) 609\u2013616. 10.1038\/s41586-025-08661-4arXiv:https:\/\/arXiv.org\/abs\/2406.07496 (\u201cTextGrad\u201d).","DOI":"10.1038\/s41586-025-08661-4"},{"key":"e_1_3_3_2_56_2","unstructured":"Guibin Zhang Luyang Niu Junfeng Fang Kun Wang Lei Bai and Xiang Wang. 2025. MaAS: Multi-agent Architecture Search via Agentic Supernet. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.04180 (2025)."},{"key":"e_1_3_3_2_57_2","volume-title":"Proceedings of the Thirteenth International Conference on Learning Representations (ICLR)","author":"Zhang Guibin","year":"2025","unstructured":"Guibin Zhang, Yanwei Yue, Xiangguo Sun, Guancheng Wan, Miao Yu, Junfeng Fang, Kun Wang, Tianlong Chen, and Dawei Cheng. 2025. G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks. In Proceedings of the Thirteenth International Conference on Learning Representations (ICLR). arXiv:https:\/\/arXiv.org\/abs\/2410.11782."},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"crossref","unstructured":"Jenny Zhang Shengran Hu Cong Lu Robert Lange and Jeff Clune. 2025. Darwin G\u00f6del Machine: Open-Ended Evolution of Self-Improving Agents. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.22954 (2025).","DOI":"10.70777\/si.v2i3.15063"},{"key":"e_1_3_3_2_59_2","volume-title":"Proceedings of the Thirteenth International Conference on Learning Representations (ICLR)","author":"Zhang Jiayi","year":"2025","unstructured":"Jiayi Zhang, Jinyu Xiang, Zhaoyang Yu, Fengwei Teng, Xiong-Hui Chen, Jiaqi Chen, Mingchen Zhuge, Xin Cheng, Sirui Hong, Jinlin Wang, Bingnan Zheng, Bang Liu, Yuyu Luo, and Chenglin Wu. 2025. AFlow: Automating Agentic Workflow Generation. In Proceedings of the Thirteenth International Conference on Learning Representations (ICLR). Oral presentation. arXiv:https:\/\/arXiv.org\/abs\/2410.10762."},{"key":"e_1_3_3_2_60_2","unstructured":"Linghao Zhang Shilin He Chaoyun Zhang Yu Kang Bowen Li Chengxing Xie Junhao Wang Maoquan Wang Yufan Huang Shengyu Fu Elsie Nallipogu Qingwei Lin Yingnong Dang Saravan Rajmohan and Dongmei Zhang. 2025. SWE-bench Goes Live! arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.23419 (2025)."},{"key":"e_1_3_3_2_61_2","volume-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Zhang Wenqi","year":"2024","unstructured":"Wenqi Zhang, Ke Tang, Hai Wu, Mengna Wang, Yongliang Shen, Guiyang Hou, Zeqi Tan, Peng Li, Yueting Zhuang, and Weiming Lu. 2024. Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL). arXiv:https:\/\/arXiv.org\/abs\/2402.17574."},{"key":"e_1_3_3_2_62_2","volume-title":"Proceedings of the Forty-First International Conference on Machine Learning (ICML)","author":"Zhuge Mingchen","year":"2024","unstructured":"Mingchen Zhuge, Wenyi Wang, Louis Kirsch, Francesco Faccio, Dmitrii Khizbullin, and J\u00fcrgen Schmidhuber. 2024. GPTSwarm: Language Agents as Optimizable Graphs. In Proceedings of the Forty-First International Conference on Machine Learning (ICML). Oral presentation. arXiv:https:\/\/arXiv.org\/abs\/2402.16823."}],"event":{"name":"CAIS '26: ACM Conference on AI and Agentic Systems","location":"San Jose CA USA","acronym":"CAIS '26"},"container-title":["Proceedings of the ACM Conference on AI and Agentic Systems"],"original-title":[],"deposited":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T03:32:21Z","timestamp":1779420741000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3786335.3813143"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,26]]},"references-count":61,"alternative-id":["10.1145\/3786335.3813143","10.1145\/3786335"],"URL":"https:\/\/doi.org\/10.1145\/3786335.3813143","relation":{},"subject":[],"published":{"date-parts":[[2026,5,26]]},"assertion":[{"value":"2026-05-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}