mlsanityData to 14 Oct 2026

Mergenetic: a Simple Evolutionary Model Merging Library

arXiv 2505.11427 ↗First posted 16 May 2025cs.LG cs.AI cs.NEcited by 5

Not on the map. Why?

Abstract (arXiv)

Model merging allows combining the capabilities of existing models into a new one - post hoc, without additional training. This has made it increasingly popular thanks to its low cost and the availability of libraries that support merging on consumer GPUs. Recent work shows that pairing merging with evolutionary algorithms can boost performance, but no framework currently supports flexible experimentation with such strategies in language models. We introduce Mergenetic, an open-source library for evolutionary model merging. Mergenetic enables easy composition of merging methods and evolutionary algorithms while incorporating lightweight fitness estimators to reduce evaluation costs. We describe its design and demonstrate that Mergenetic produces competitive results across tasks and languages using modest hardware.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 25 of its 36 references that are in the map. First posted on arXiv 16 May 2025.

Builds on

25 of 36 references.

References · 25

  1. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  2. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,886
  3. 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timecited by 1,396
  4. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 909
  5. 2016Bag of Tricks for Efficient Text Classificationcited by 876
  6. 2023TIES-Merging: Resolving Interference When Merging Modelscited by 818
  7. 2023Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunchcited by 694
  8. 2021Merging Models with Fisher-Weighted Averagingcited by 621
  9. 2022Language Models are Multilingual Chain-of-Thought Reasonerscited by 530
  10. 2022Git Re-Basin: Merging Models modulo Permutation Symmetriescited by 471
  11. 2016The CMA Evolution Strategy: A Tutorialcited by 377
  12. 2024tinyBenchmarks: evaluating LLMs with fewer examplescited by 310
13 more
  1. 2024Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunitiescited by 254
  2. 2024Evolutionary Optimization of Model Merging Recipescited by 208
  3. 2020pymoo: Multi-objective Optimization in Pythoncited by 200
  4. 2024Arcee's MergeKit: A Toolkit for Merging Large Language Modelscited by 194
  5. 2023ZipIt! Merging Models from Different Tasks without Trainingcited by 179
  6. 2019Gradio: Hassle-Free Sharing and Testing of ML Models in the Wildcited by 178
  7. 2024Task Singular Vectors: Reducing Task Interference in Model Mergingcited by 147
  8. 2023Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Maskscited by 133
  9. 2024Localizing Task Information for Improved Model Merging and Compressioncited by 131
  10. 2022Fusing finetuned models for better pretrainingcited by 110
  11. 2022Re-basin via implicit Sinkhorn differentiationcited by 62
  12. 2024ATM: Improving Model Merging by Alternating Tuning and Mergingcited by 11
  13. 2025MERGE3: Efficient Evolutionary Merging on Consumer-grade GPUscited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2025CapBencher: Give Your LLM Benchmark a Built-in Alarm for Test-Set Overfittingcited by 7
  2. 2026From Parameters to Behaviors: A Survey of Model Fusion for Large Language Modelscited by 1
  3. 2026Sparsity-Aware Evolution for Model Mergingcited by 0
  4. 2026Model Merging: Foundations and Algorithmscited by 0
  5. 2026Model Merging to Evolution: Parameter Space Exploration for Expert Modelscited by 0