EvoGM: Learning to Merge LLMs via Evolutionary Generative Optimization

• URL: http://arxiv.org/abs/2605.29295v1
• Date: Thu, 28 May 2026 03:22:54 GMT
• Title: EvoGM: Learning to Merge LLMs via Evolutionary Generative Optimization
• Abstract summary: We propose Evolutionary Generative Merging (EvoGM), a framework that employs learnable generative modeling to optimize merging coefficients.<n>EvoGM features a dual-generator architecture with cycle-consistent learning to adaptively sample and refine promising merging candidates.<n>Experiments across diverse benchmarks demonstrate that EvoGM significantly outperforms state-of-the-art baselines.
• Score: 27.31325788417927
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Evolutionary model merging provides a powerful framework for the automated, training-free composition of LLMs through parameter-space search. However, existing methods predominantly rely on stochastic, hand-crafted operators that overlook the underlying performance landscape of the coefficient space. We propose Evolutionary Generative Merging (EvoGM), a framework that transcends manual heuristics by employing learnable generative modeling to optimize merging coefficients. Specifically, EvoGM features a dual-generator architecture with cycle-consistent learning to adaptively sample and refine promising merging candidates. By constructing winner-loser pairs from historical search trajectories, our framework effectively captures high-performance parameter distributions and maximizes data efficiency. This generative process is seamlessly integrated into a multi-round evolutionary pipeline, where elite merged models iteratively serve as new expert foundations. Extensive experiments across diverse benchmarks demonstrate that EvoGM significantly outperforms state-of-the-art baselines, exhibiting robust performance on both seen and unseen tasks. Code and data are available at https://github.com/JiangTao97/evogm.

Related papers

• EvoSelect: Data-Efficient LLM Evolution for Targeted Task Adaptation [79.71802168256542]
  Adapting large language models (LLMs) to a targeted task efficiently and effectively remains a fundamental challenge.<n>One straightforward approach is through an iterative generation-training loop, where candidate data are synthesized through an external generator.<n>We introduce a refined paradigm, namely an iterative generation-selection-training loop, which incorporates a selection step prior to model updates.
  arXiv  Detail & Related papers  (2026-04-28T23:26:16Z)
• Merging Beyond: Streaming LLM Updates via Activation-Guided Rotations [55.047454145941366]
  Streaming Merging is an innovative model updating paradigm that conceptualizes merging as an iterative optimization process.<n> ARM is a strategy designed to approximate gradient descent dynamics.<n> ARM requires only early SFT checkpoints and, through iterative merging, surpasses the fully converged SFT model.
  arXiv  Detail & Related papers  (2026-02-03T08:15:57Z)
• Learning to Evolve with Convergence Guarantee via Neural Unrolling [37.99564850768798]
  We introduce Learning to Evolve (L2E), a unified bilevel meta-optimization framework.<n>L2E reformulates evolutionary search as a Neural Unrolling process grounded in Krasnosel'skii-Mann (KM) fixed-point theory.<n>Experiments demonstrate the scalability of L2E in high-dimensional spaces and its robust zero-shot generalization across synthetic and real-world control tasks.
  arXiv  Detail & Related papers  (2025-12-12T10:46:25Z)
• Middo: Model-Informed Dynamic Data Optimization for Enhanced LLM Fine-Tuning via Closed-Loop Learning [44.53583316198435]
  Supervised Fine-Tuning (SFT) Large Language Models rely on high-quality training data.<n>We introduce Middo, a self-evolving Model-informed dynamic data optimization framework.<n>We show that Middo consistently enhances the quality of seed data and boosts LLM's performance with improving accuracy by 7.15% on average.
  arXiv  Detail & Related papers  (2025-08-29T12:47:27Z)
• CALM: Co-evolution of Algorithms and Language Model for Automatic Heuristic Design [11.639825726501659]
  Large language models (LLMs) can autonomously discover high-performings at a fraction of the traditional cost.<n>We propose a hybrid framework that combines verbal and numerical guidance.<n>Our method outperforms state-of-the-art (SOTA) baselines across various optimization tasks.
  arXiv  Detail & Related papers  (2025-05-18T07:48:47Z)
• Direct Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language Models [83.8639566087953]
  We propose a direct retrieval-augmented optimization framework, named DRO, that enables end-to-end training of two key components.<n>DRO alternates between two phases: (i) document permutation estimation and (ii) re-weighted, progressively improving RAG components.<n>Our theoretical analysis reveals that DRO is analogous to policy-gradient methods in reinforcement learning.
  arXiv  Detail & Related papers  (2025-05-05T23:54:53Z)
• Reinforced Model Merging [53.84354455400038]
  We present an innovative framework termed Reinforced Model Merging (RMM), which encompasses an environment and agent tailored for merging tasks.<n>By utilizing data subsets during the evaluation process, we addressed the bottleneck in the reward feedback phase, thereby accelerating RMM by up to 100 times.
  arXiv  Detail & Related papers  (2025-03-27T08:52:41Z)
• Exploring Model Kinship for Merging Large Language Models [73.98345036483299]
  We study model evolution through iterative merging, drawing an analogy to biological evolution.<n>We show that model kinship is closely linked to the performance improvements achieved by merging.<n>We propose a new model merging strategy: Top-k Greedy Merging with Model Kinship.
  arXiv  Detail & Related papers  (2024-10-16T14:29:29Z)
• Model-GLUE: Democratized LLM Scaling for A Large Model Zoo in the Wild [84.57103623507082]
  This paper introduces Model-GLUE, a holistic Large Language Models scaling guideline.<n>We benchmark existing scaling techniques, especially selective merging, and variants of mixture.<n>We then formulate an optimal strategy for the selection and aggregation of a heterogeneous model zoo.<n>Our methodology involves the clustering of mergeable models and optimal merging strategy selection, and the integration of clusters.
  arXiv  Detail & Related papers  (2024-10-07T15:55:55Z)
• Evolutionary Large Language Model for Automated Feature Transformation [44.64296052383581]
  We propose an evolutionary Large Language Model (LLM) framework for automated feature transformation.<n>This framework consists of two parts: 1) constructing a multi-population database through an RL data collector, and 2) utilizing the ability of Large Language Model (LLM) in sequence understanding.<n>We empirically demonstrate the effectiveness and generality of our proposed method.
  arXiv  Detail & Related papers  (2024-05-25T12:27:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.