FlowBank
A bank of reusable workflow fragments enables query-adaptive optimization without rebuilding every agentic pipeline from scratch.
Agentic workflows
Compose specialized reasoning into systems. We study how agents select, reuse, route, and coordinate reasoning components so complex workflows become adaptive, efficient, and auditable.
Research question
Can an agent assemble the right workflow for each query instead of using one fixed pipeline?
We study how agents select, reuse, route, and coordinate reasoning components so complex workflows become adaptive, efficient, and auditable.
- Workflow optimization
- Precompute and reuse
- Model routing
- Multi-agent coordination
Representative projects
Compose specialized reasoning into systems.
Each project connects its central idea with papers, code, datasets, demonstrations, and public explanations.
Agentic Critical Training
Structured critical cycles teach agents to propose, inspect, and revise multi-stage solutions as a coherent workflow.
Selected publications
The papers behind the projects.
Browse the full publication database for the broader body of work in reasoning control.
FlowBank: Query-Adaptive Agentic Workflows Optimization through Precompute-and-Reuse
BibTeX
@misc{yuan2026flowbank663c,
title = {FlowBank: Query-Adaptive Agentic Workflows Optimization through Precompute-and-Reuse},
author = {Lingzhi Yuan and Chenghao Deng and Fangxu Yu and Souradip Chakraborty and Mohammad Rostami and Furong Huang},
year = {2026},
eprint = {2606.11290},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2606.11290},
}Agentic Critical Training
BibTeX
@misc{liu2026agenticb95b,
title = {Agentic Critical Training},
author = {Weize Liu and Minghui Liu and Sy-Tuyen Ho and Souradip Chakraborty and Xiyao Wang and Furong Huang},
year = {2026},
eprint = {2603.08706},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2603.08706},
}Token-Level LLM Collaboration via FusionRoute
Forty-third International Conference on Machine Learning (ICML), 2026
BibTeX
@inproceedings{xiong2026token015c,
title = {Token-Level LLM Collaboration via FusionRoute},
author = {Nuoya Xiong and Yuhang Zhou and Hanqing Zeng and Zhaorun Chen and Furong Huang and Shuchao Bi and Lizhu Zhang and Zhuokai Zhao},
booktitle = {Forty-third International Conference on Machine Learning (ICML), 2026},
year = {2026},
eprint = {2601.05106},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2601.05106},
}Collab: Controlled Decoding using Mixture of Agents for LLM Alignment
The Thirteenth International Conference on Learning Representations (ICLR), 2025
BibTeX
@inproceedings{chakraborty2025collabbdbe,
title = {Collab: Controlled Decoding using Mixture of Agents for LLM Alignment},
author = {Souradip Chakraborty and Sujay Bhatt and Udari Madhushani Sehwag and Soumya Suvra Ghosal and Jiahao Qiu and Mengdi Wang and Dinesh Manocha and Furong Huang and Alec Koppel and Sumitra Ganesh},
booktitle = {The Thirteenth International Conference on Learning Representations (ICLR), 2025},
year = {2025},
eprint = {2503.21720},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2503.21720},
}