{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T04:07:50Z","timestamp":1779422870004,"version":"3.53.1"},"publisher-location":"New York, NY, USA","reference-count":22,"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\/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\/3786335.3813170","type":"proceedings-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T03:16:22Z","timestamp":1779419782000},"page":"224-238","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Expansion-Contraction: A Multi-Agent Graph Traversal Pattern for Compound AI Systems"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3743-1299","authenticated-orcid":false,"given":"Aiham","family":"Taleb","sequence":"first","affiliation":[{"name":"Amazon Web Services Inc., Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6968-4460","authenticated-orcid":false,"given":"Zainab","family":"Afolabi","sequence":"additional","affiliation":[{"name":"Amazon Web Services Inc., London, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5600-9707","authenticated-orcid":false,"given":"Joao","family":"Sousa","sequence":"additional","affiliation":[{"name":"Amazon Web Services Inc., Lisbon, Portugal"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1054-0985","authenticated-orcid":false,"given":"Mathias","family":"Seidel","sequence":"additional","affiliation":[{"name":"Continental AG, Hannover, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,5,26]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Markus\u00a0J. Buehler. 2025. Agentic Deep Graph Reasoning. CoRR abs\/2502.13025 (2025) 1\u201318.","DOI":"10.1002\/aidi.202500006"},{"key":"e_1_3_3_1_3_2","first-page":"1","volume-title":"NeurIPS Workshop on Efficient Reasoning","author":"Butler Jack","year":"2025","unstructured":"Jack Butler, Nikita Kozodoi, Zainab Afolabi, Brian Tyacke, and Gaiar Baimuratov. 2025. Finding the Sweet Spot: Trading Quality, Cost, and Speed During Inference-Time LLM Reflection. In NeurIPS Workshop on Efficient Reasoning. Neural Information Processing Systems Foundation, Vancouver, Canada, 1\u20139."},{"key":"e_1_3_3_1_4_2","unstructured":"Dongjie Chen et\u00a0al. 2023. Hierarchical Graph Neural Networks for Causal Discovery and Root Cause Localization. CoRR abs\/2302.01987 (2023) 1\u201310."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","unstructured":"Fabian Constante Fernando Silva and Ant\u00f3nio Pereira. 2019. DataCo SMART Supply Chain for Big Data Analysis. 10.17632\/8gx2fvg2k6.5Version 5.","DOI":"10.17632\/8gx2fvg2k6.5"},{"key":"e_1_3_3_1_6_2","unstructured":"Taicheng Guo et\u00a0al. 2025. A Survey on LLM-based Multi-Agent Systems: Workflow Infrastructure and Challenges. Scientific Reports 15 1 (2025) 4741."},{"key":"e_1_3_3_1_7_2","volume-title":"2nd Workshop on LLMs and Generative AI in Finance, International Conference on AI in Finance (ICAIF)","author":"Heus Evan","year":"2025","unstructured":"Evan Heus, Rick Bookstaber, and Dhruv Sharma. 2025. Exploring Network-Knowledge Graph Duality: A Case Study in Agentic Supply Chain Risk Analysis. In 2nd Workshop on LLMs and Generative AI in Finance, International Conference on AI in Finance (ICAIF). arXiv, New York, NY, USA."},{"key":"e_1_3_3_1_8_2","unstructured":"Omar Khattab Keshav Santhanam Xiang Li et\u00a0al. 2023. DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines. CoRR abs\/2310.03714 (2023) 1\u201325."},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"crossref","unstructured":"Edward\u00a0Elson Kosasih and Alexandra Brintrup. 2022. A machine learning approach for predicting hidden links in supply chain with graph neural networks. International Journal of Production Research 60 17 (2022) 5380\u20135393.","DOI":"10.1080\/00207543.2021.1956697"},{"key":"e_1_3_3_1_10_2","unstructured":"LangChain. 2024. LangGraph: Build Stateful Multi-Actor Applications with LLMs. https:\/\/github.com\/langchain-ai\/langgraph."},{"key":"e_1_3_3_1_11_2","first-page":"9459","volume-title":"Advances in Neural Information Processing Systems","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-tau Yih, Tim Rockt\u00e4schel, Sebastian Riedel, and Douwe Kiela. 2020. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. In Advances in Neural Information Processing Systems, Vol.\u00a033. Curran Associates, Inc., Red Hook, NY, USA, 9459\u20139474."},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Nelson\u00a0F. Liu Kevin Lin John Hewitt Ashwin Paranjape Michele Bevilacqua Fabio Petroni and Percy Liang. 2024. Lost in the Middle: How Language Models Use Long Contexts. Transactions of the Association for Computational Linguistics 12 1 (2024) 157\u2013173.","DOI":"10.1162\/tacl_a_00638"},{"key":"e_1_3_3_1_13_2","unstructured":"Jo\u00e3o Moura. 2024. CrewAI: Framework for Orchestrating Role-Playing Autonomous AI Agents. https:\/\/github.com\/crewAIInc\/crewAI."},{"key":"e_1_3_3_1_14_2","first-page":"68539","volume-title":"Advances in Neural Information Processing Systems","author":"Schick Timo","year":"2023","unstructured":"Timo Schick, Jane Dwivedi-Yu, Roberto Dess\u00ec, et\u00a0al. 2023. Toolformer: Language Models Can Teach Themselves to Use Tools. In Advances in Neural Information Processing Systems, Vol.\u00a036. Curran Associates, Inc., Red Hook, NY, USA, 68539\u201368551."},{"key":"e_1_3_3_1_15_2","unstructured":"Yifan Wang et\u00a0al. 2025. Parallelized Planning-Acting for Efficient LLM-based Multi-Agent Systems. CoRR abs\/2503.03505 (2025) 1\u20139."},{"key":"e_1_3_3_1_16_2","first-page":"1","volume-title":"4th Workshop on Graphs and more Complex Structures for Learning and Reasoning (GCLR), AAAI","author":"Wasi Azmine\u00a0Toushik","year":"2024","unstructured":"Azmine\u00a0Toushik Wasi, MD\u00a0Shafikul Islam, and Adipto\u00a0Raihan Akib. 2024. SupplyGraph: A Benchmark Dataset for Supply Chain Planning using Graph Neural Networks. In 4th Workshop on Graphs and more Complex Structures for Learning and Reasoning (GCLR), AAAI. AAAI Press, Vancouver, Canada, 1\u201313."},{"key":"e_1_3_3_1_17_2","unstructured":"Qingyun Wu Gagan Bansal Jieyu Zhang et\u00a0al. 2023. AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation. CoRR abs\/2308.08155 (2023) 1\u201322."},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.563"},{"key":"e_1_3_3_1_19_2","first-page":"1","volume-title":"Proceedings of the Eleventh International Conference on Learning Representations (ICLR)","author":"Yao Shunyu","year":"2023","unstructured":"Shunyu Yao, Jeffrey Zhao, Dian Yu, et\u00a0al. 2023. ReAct: Synergizing Reasoning and Acting in Language Models. In Proceedings of the Eleventh International Conference on Learning Representations (ICLR). OpenReview.net, Kigali, Rwanda, 1\u201334."},{"key":"e_1_3_3_1_20_2","unstructured":"Matei Zaharia Omar Khattab Lingjiao Chen et\u00a0al. 2024. The Shift from Models to Compound AI Systems. Berkeley AI Research Blog. https:\/\/bair.berkeley.edu\/blog\/2024\/02\/18\/compound-ai-systems\/ Accessed: 2025-01-15."},{"key":"e_1_3_3_1_21_2","unstructured":"Jing Zhang et\u00a0al. 2024. Root Cause Attribution of Delivery Risks via Causal Discovery with Reinforcement Learning. CoRR abs\/2408.05860 (2024) 1\u201312."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"Zhiyu Zhang et\u00a0al. 2025. DynTaskMAS: A Dynamic Task Graph-driven Framework for Asynchronous and Parallel LLM-based Multi-Agent Systems. CoRR abs\/2503.07675 (2025) 1\u201311.","DOI":"10.1609\/icaps.v35i1.36130"},{"key":"e_1_3_3_1_23_2","first-page":"62743","volume-title":"Proceedings of the 41st International Conference on Machine Learning (ICML)","volume":"235","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 41st International Conference on Machine Learning (ICML), Vol.\u00a0235. PMLR, Vienna, Austria, 62743\u201362767."}],"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":"2026-05-22T03:27:41Z","timestamp":1779420461000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3786335.3813170"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,26]]},"references-count":22,"alternative-id":["10.1145\/3786335.3813170","10.1145\/3786335"],"URL":"https:\/\/doi.org\/10.1145\/3786335.3813170","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"}}]}}