papers/enso/references.bib

% =====================================================================
% Enso paper bibliography.
% Hanzo internal artifacts + real external literature. No fabricated
% author lists: where a paper's individual authors are not known to us
% (e.g. Sakana's ICLR foundations), the institutional author is used.
% =====================================================================

% ---- Hanzo internal ----
@misc{ensoengine,
  author       = {{Hanzo Industries}},
  title        = {{enso: Learned SLO-Constrained Routing Policy for hanzo-router}},
  howpublished = {\url{https://github.com/hanzoai/engine}},
  year         = {2026}
}

@misc{hanzorouterpaper,
  author       = {Hanzo AI Research},
  title        = {{Hanzo Router: Memory-Aware, Local-First LLM Routing with a
                   Learned SLO-Constrained Policy}},
  howpublished = {Hanzo Research},
  year         = {2026}
}

@misc{hanzoengine,
  author       = {{Hanzo Industries}},
  title        = {{hanzo-engine: An OpenAI-Compatible LLM Inference Engine in Rust}},
  howpublished = {\url{https://github.com/hanzoai/engine}},
  year         = {2026}
}

@misc{hanzogateway,
  author       = {{Hanzo Industries}},
  title        = {{Hanzo AI Gateway: One \texttt{/v1} API over a Discovered Model Fleet}},
  howpublished = {\url{https://api.hanzo.ai}},
  year         = {2026}
}

@misc{zenrouter,
  author       = {{Zen LM}},
  title        = {{zen-router: A 0.6B Trainable Routing Model}},
  howpublished = {\url{https://github.com/zenlm/zen-router}},
  year         = {2026}
}

% ---- The foil: Sakana AI Fugu and its ICLR foundations ----
@misc{priororchestrator,
  author       = {{Sakana AI}},
  title        = {{Fugu: A Learned Orchestrator over Frontier Language Models}},
  howpublished = {arXiv preprint arXiv:2606.21228, \url{https://sakana.ai/fugu-release}},
  year         = {2026}
}

@inproceedings{trinity,
  author       = {{Sakana AI}},
  title        = {{Trinity: Evolutionary Composition of Language Model Experts}},
  booktitle    = {International Conference on Learning Representations (ICLR)},
  year         = {2026}
}

@inproceedings{conductor,
  author       = {{Sakana AI}},
  title        = {{Conductor: Reinforcement-Learned Orchestration of Model Ensembles}},
  booktitle    = {International Conference on Learning Representations (ICLR)},
  year         = {2026}
}

% ---- LLM routing and cascading ----
@misc{routellm,
  author       = {Isaac Ong and Amjad Almahairi and Vincent Wu and Wei-Lin Chiang and
                  Tianhao Wu and Joseph E. Gonzalez and M. Waleed Kadous and Ion Stoica},
  title        = {{RouteLLM: Learning to Route LLMs with Preference Data}},
  howpublished = {arXiv preprint arXiv:2406.18665},
  year         = {2024}
}

@article{frugalgpt,
  author       = {Lingjiao Chen and Matei Zaharia and James Zou},
  title        = {{FrugalGPT: How to Use Large Language Models While Reducing Cost
                   and Improving Performance}},
  journal      = {arXiv preprint arXiv:2305.05176},
  year         = {2023}
}

@inproceedings{hybridllm,
  author       = {Dujian Ding and Ankur Mallick and Chi Wang and Robert Sim and
                  Subhabrata Mukherjee and Victor R{\"u}hle and
                  Laks V. S. Lakshmanan and Ahmed Hassan Awadallah},
  title        = {{Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing}},
  booktitle    = {International Conference on Learning Representations (ICLR)},
  year         = {2024}
}

@article{automix,
  author       = {Aman Madaan and Pranjal Aggarwal and Ankit Anand and
                  Srividya Pranavi Potharaju and Swaroop Mishra and Pei Zhou and
                  Aditya Gupta and Dheeraj Rajagopal and Karthik Kappaganthu and
                  Yiming Yang and Shyam Upadhyay and Mausam and Manaal Faruqui},
  title        = {{AutoMix: Automatically Mixing Language Models}},
  journal      = {arXiv preprint arXiv:2310.12963},
  year         = {2023}
}

@inproceedings{tabi,
  author       = {Yiding Wang and Kai Chen and Haisheng Tan and Kun Guo},
  title        = {{Tabi: An Efficient Multi-Level Inference System for Large
                   Language Models}},
  booktitle    = {Proceedings of the 18th European Conference on Computer Systems
                   (EuroSys)},
  year         = {2023},
  pages        = {233--248},
  publisher    = {ACM}
}

% ---- Multi-agent / ensemble synthesis (Enso Ultra) ----
@inproceedings{moa,
  author       = {Junlin Wang and Jue Wang and Ben Athiwaratkun and Ce Zhang and
                  James Zou},
  title        = {{Mixture-of-Agents Enhances Large Language Model Capabilities}},
  booktitle    = {International Conference on Learning Representations (ICLR)},
  year         = {2025}
}

@inproceedings{llmblender,
  author       = {Dongfu Jiang and Xiang Ren and Bill Yuchen Lin},
  title        = {{LLM-Blender: Ensembling Large Language Models with Pairwise
                   Ranking and Generative Fusion}},
  booktitle    = {Proceedings of the 61st Annual Meeting of the Association for
                   Computational Linguistics (ACL)},
  year         = {2023}
}

@inproceedings{selfconsistency,
  author       = {Xuezhi Wang and Jason Wei and Dale Schuurmans and Quoc Le and
                  Ed H. Chi and Sharan Narang and Aakanksha Chowdhery and Denny Zhou},
  title        = {{Self-Consistency Improves Chain of Thought Reasoning in
                   Language Models}},
  booktitle    = {International Conference on Learning Representations (ICLR)},
  year         = {2023}
}

% ---- Learning machinery ----
@inproceedings{linucb,
  author       = {Lihong Li and Wei Chu and John Langford and Robert E. Schapire},
  title        = {{A Contextual-Bandit Approach to Personalized News Article
                   Recommendation}},
  booktitle    = {Proceedings of the 19th International Conference on World Wide Web
                   (WWW)},
  year         = {2010},
  pages        = {661--670},
  publisher    = {ACM}
}

@article{ridge,
  author       = {Arthur E. Hoerl and Robert W. Kennard},
  title        = {{Ridge Regression: Biased Estimation for Nonorthogonal Problems}},
  journal      = {Technometrics},
  volume       = {12},
  number       = {1},
  pages        = {55--67},
  year         = {1970},
  publisher    = {Taylor \& Francis}
}

@article{grpo,
  author       = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and
                  Junxiao Song and Xiao Bi and Haowei Zhang and Mingchuan Zhang and
                  Y. K. Li and Y. Wu and Daya Guo},
  title        = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in
                   Open Language Models}},
  journal      = {arXiv preprint arXiv:2402.03300},
  year         = {2024}
}

@article{sepcmaes,
  author       = {Raymond Ros and Nikolaus Hansen},
  title        = {{A Simple Modification in CMA-ES Achieving Linear Time and Space
                   Complexity}},
  journal      = {Parallel Problem Solving from Nature (PPSN X), LNCS 5199},
  pages        = {296--305},
  year         = {2008},
  publisher    = {Springer}
}

% ---- Benchmarks ----
@inproceedings{swebench,
  author       = {Carlos E. Jimenez and John Yang and Alexander Wettig and
                  Shunyu Yao and Kexin Pei and Ofir Press and Karthik Narasimhan},
  title        = {{SWE-bench: Can Language Models Resolve Real-World GitHub Issues?}},
  booktitle    = {International Conference on Learning Representations (ICLR)},
  year         = {2024}
}

@article{livecodebench,
  author       = {Naman Jain and King Han and Alex Gu and Wen-Ding Li and
                  Fanjia Yan and Tianjun Zhang and Sida Wang and Armando Solar-Lezama and
                  Koushik Sen and Ion Stoica},
  title        = {{LiveCodeBench: Holistic and Contamination Free Evaluation of
                   Large Language Models for Code}},
  journal      = {arXiv preprint arXiv:2403.07974},
  year         = {2024}
}

@article{gpqa,
  author       = {David Rein and Betty Li Hou and Asa Cooper Stickland and
                  Jackson Petty and Richard Yuanzhe Pang and Julien Dirani and
                  Julian Michael and Samuel R. Bowman},
  title        = {{GPQA: A Graduate-Level Google-Proof Q\&A Benchmark}},
  journal      = {arXiv preprint arXiv:2311.12022},
  year         = {2023}
}

@article{hle,
  author       = {Long Phan and others},
  title        = {{Humanity's Last Exam}},
  journal      = {arXiv preprint arXiv:2501.14249},
  year         = {2025}
}

@article{charxiv,
  author       = {Zirui Wang and Mengzhou Xia and Luxi He and Howard Chen and
                  Yitao Liu and Richard Zhu and Kaiqu Liang and Xindi Wu and
                  Haotian Liu and Sadhika Malladi and Alexis Chevalier and
                  Sanjeev Arora and Danqi Chen},
  title        = {{CharXiv: Charting Gaps in Realistic Chart Understanding in
                   Multimodal LLMs}},
  journal      = {arXiv preprint arXiv:2406.18521},
  year         = {2024}
}

@misc{terminalbench,
  author       = {{Terminal-Bench Team}},
  title        = {{Terminal-Bench: A Benchmark for AI Agents in Terminal Environments}},
  howpublished = {\url{https://www.tbench.ai/}},
  year         = {2025}
}

% ---- Discipline ----
@misc{hickey_simple,
  author       = {Rich Hickey},
  title        = {{Simple Made Easy}},
  howpublished = {Strange Loop Conference},
  year         = {2011},
  note         = {\url{https://www.infoq.com/presentations/Simple-Made-Easy/}}
}