--- title: "LLM-as-Scheduler: Agentic Workflow Dynamic Scheduling (2026)" description: "Multi-agent LLM pipelines, whether hand-built or found automatically by ADAS or AFlow, usually push every… 1.4 accuracy. 5 references." authors: ["Dawei Xiang", "Kexin Chu", "Wenyan Xu", "Wenhui Zhang", "Wei Zhang"] year: 2026 venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)" source: "https://aclanthology.org/2026.acl-long.581/" doi: "10.18653/v1/2026.acl-long.581" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/xiang-2026-llm-as-scheduler-agentic-workflow/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/xiang-2026-llm-as-scheduler-agentic-workflow/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/39/) / LLM-as-Scheduler: Agentic Workflow Dynamic Scheduling # LLM-as-Scheduler: Agentic Workflow Dynamic Scheduling **Authors:** [Dawei Xiang](https://md.research.elamur.ai/free/en/authors/dawei-xiang/), Kexin Chu, Wenyan Xu, Wenhui Zhang and [Wei Zhang](https://md.research.elamur.ai/free/en/authors/wei-zhang/) · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2026.acl-long.581/) · [PDF](https://aclanthology.org/2026.acl-long.581.pdf) · [DOI 10.18653/v1/2026.acl-long.581](https://doi.org/10.18653/v1/2026.acl-long.581) · [OpenAlex](https://openalex.org/W7166816873) **Citations:** 0 citations (OpenAlex, 2026-10-14) ## Summary Multi-agent LLM pipelines, whether hand-built or found automatically by ADAS or AFlow, usually push every query through the same long chain of generation, validation, refinement and repair steps. That chain costs a lot of tokens and time. The authors ran such a workflow on MBPP, HumanEval and GSM8K. Roughly half of the problems were already solved by the first agent, about a fifth needed the full chain, and the rest failed regardless. To exploit this skew, they built LLM-as-Scheduler (LAS), a policy layer placed over an existing workflow. It uses a two-level cascade: - **Gate:** a cheap check that runs after every agent output, combining scripted signals with a small DistilBERT-based judge. - **Scheduler:** a larger LLM, invoked only for borderline cases, that decides whether to stop early, test, refine or reroute. Averaged over benchmarks, LAS halves token use and cuts latency by more than a third, losing at most 1.4 accuracy points against a strong fixed workflow. Dynamic per-query scheduling therefore makes agentic systems much cheaper to deploy. ## Key points - On MBPP, LAS saves 63.4% of tokens and 41.9% of latency, with an accuracy drop of no more than 0.5 pp. - In the MBPP ablation against the AFLOW baseline: - AFLOW baseline: 94.2% accuracy, about 6643 tokens, 134.3 s. - Gate+LAS: 93.7%, about 2430 tokens, 78.0 s. - Gate alone: falls to 86.7% accuracy. - The gate adds no tokens and about 0.15 s per call. At its best threshold it reaches 70.64% accuracy, 98.60% recall and AUC 0.737, and its judge trains in under an hour. - The scheduler matches oracle routing labels 65.72% of the time. Only 2.7% of its decisions are harmful, meaning it skips a needed refinement step. - The authors list cross-task transfer and extension to RAG and tool-use benchmarks as future work. *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 - [Mohamed bin Zayed University of Artificial Intelligence](https://md.research.elamur.ai/free/en/universities/mohamed-bin-zayed-university-of-artificial-intelligence/) — University, Abu Dhabi, United Arab Emirates · 138 works · 6,590 citations - [University of Connecticut](https://md.research.elamur.ai/free/en/universities/university-of-connecticut/) — University, Storrs, United States · 13 works · 357 citations 📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works 🧭 Topics (1): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,894 works ## Cite Cite as: Dawei Xiang, Kexin Chu, Wenyan Xu, Wenhui Zhang and Wei Zhang. 2026. LLM-as-Scheduler: Agentic Workflow Dynamic Scheduling. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{xiang2026llm, title = {{LLM-as-Scheduler: Agentic Workflow Dynamic Scheduling}}, author = {Dawei Xiang, Kexin Chu, Wenyan Xu, Wenhui Zhang and Wei Zhang}, booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, year = {2026}, doi = {10.18653/v1/2026.acl-long.581}, url = {https://doi.org/10.18653/v1/2026.acl-long.581} } ``` - [← previous LLM-as-a-Jury for Machine Translation Publishability Assessment](https://md.research.elamur.ai/free/en/papers/yanishevsky-2026-llm-as-jury-machine-translation/) - [next → LLM-Assisted Spanish Dialect Corpus Construction](https://md.research.elamur.ai/free/en/papers/vidal-2026-llm-assisted-spanish-dialect-corpus/) - [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/39/) ## References 5 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Jacob Austin, Augustus Odena, Maxwell Nye, Maarten Bosma, Henryk Michalewski, David Dohan, Ellen Jiang, Carrie Cai, Michael Terry, Quoc Le, and 1 others. 2021. [Program synthesis with large language models](https://md.research.elamur.ai/free/en/papers/austin-2021-program-synthesis-large-language-models/). arXiv preprint arXiv:2108.07732. 2. Lingjiao Chen, Matei Zaharia, and James Zou. 2024. [Frugalgpt: How to use large language models while reducing cost and improving performance](https://md.research.elamur.ai/free/en/papers/chen-2023-frugalgpt-use-large-language-models/). Transactions on Machine Learning Research. 3. We highlight the inefficiency of fixed multi-agent workflows and propose LLM-as-Scheduler (LAS), a cascade controller that adapts execution per query via a lightweight gate and an LLM scheduler. Experiments show that LAS preserves nearly all accuracy while reducing token usage by 50.5% and latency b… [find](https://scholar.google.com/scholar?q=We+highlight+the+inefficiency+of+fixed+multi%2Dagent+workflows+and+propose+LLM%2Das%2DScheduler+%28LAS%29%2C+a+cascade+controller+that+adapts+execution+per+query+via+a+lightweight+gate+and+an+LLM+scheduler%2E+Exper) 4. Mark Chen. 2021. [Evaluating large language models trained on code](https://md.research.elamur.ai/free/en/papers/chen-2021-evaluating-large-language-models-trained/). arXiv preprint arXiv:2107.03374. 5. Jasper Dekoninck, Maximilian Baader, and Martin Vechev. 2025. A unified approach to routing and cascading for llms. In Proceedings of the 42nd International Conference on Machine Learning, volume 267 of Proceedings of Machine Learning Research, pages 12987–13010. PMLR. [find](https://scholar.google.com/scholar?q=Jasper+Dekoninck%2C+Maximilian+Baader%2C+and+Martin+Vechev%2E+2025%2E+A+unified+approach+to+routing+and+cascading+for+llms%2E+In+Proceedings+of+the+42nd+International+Conference+on+Machine+Learning%2C+volume+267+) *Updated 2 November 2026*