Relay, Don't Route: Adaptive Population Handoff for Cost-Efficient LLM-Driven Evolution

• URL: http://arxiv.org/abs/2608.05651v1
• Date: Thu, 06 Aug 2026 06:48:08 GMT
• Title: Relay, Don't Route: Adaptive Population Handoff for Cost-Efficient LLM-Driven Evolution
• Abstract summary: Large language model (LLM)-driven evolution has shown promise for program search and algorithm discovery.<n>We propose textbfmodel, a training-free framework that shifts budget allocation from individual calls to evolving populations.<n>Our results suggest that in stateful search, budget allocation should be organized around the population, not the individual call.
• Score: 32.25060721536872
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language model (LLM)-driven evolution has shown promise for program search and algorithm discovery, but relying on strong models throughout long evolutionary runs is costly. A natural alternative is to combine cheap and strong models under a fixed inference budget. However, existing approaches typically allocate models at the level of individual queries or mutation steps, overlooking that evolutionary search is \textit{stateful}: each generated candidate changes the population from which subsequent mutations are produced. We empirically analyze LLM-driven evolutionary trajectories and find that search progress is strongly front-loaded, early trajectory performance is informative but noisy, and cheap models recover much of the early progress achieved by strong models at lower cost. Motivated by these findings, we propose \textbf{\model}, a training-free framework that shifts budget allocation from individual calls to evolving populations through adaptive \textit{population handoff}. A cheap model explores multiple trajectories in short blocks allocated by a bandit scheduler. Relay Gain, defined as the marginal improvement of a compact, quality-diverse candidate bank constructed for handoff, serves as the scheduler reward and determines when to hand off. The curated candidates initialize a shared strong model population for refinement. Across four benchmarks and three budgets, \model achieves the highest mean score in 11 of 12 settings, outperforming competitive baselines. Our results suggest that in stateful search, budget allocation should be organized around the population, not the individual call.

Related papers

• Dynamically Allocating Evaluation Effort for Model Ranking [60.00410111594536]
  We formalize multi-model human evaluation as a best-arm identification problem in a multi-armed bandit setup with correlated arms.<n>We show that it improves discrimination between top-performing models.<n>This makes evaluations faster, cheaper and more aligned with large-scale competition evaluation goals.
  arXiv  Detail & Related papers  (2026-08-04T10:33:04Z)
• Generative Frontier Planning for Adaptive Peer-Referral Recruitment under Covariate-Dependent Arrivals [28.082278231005997]
  Peer-referral recruitment systems are critical for studying and intervening on hidden populations affected by infectious diseases.<n>We propose emphGenerative Frontier Planning (GFP), a model-based planner that replaces per-step Monte-Carlo sampling with a deterministic backup.<n>GFP outperforms random, reinforcement-learning, and i.i.d. dynamic-programming baselines across four discount factors.
  arXiv  Detail & Related papers  (2026-06-06T22:31:07Z)
• Self-Improving Language Models with Bidirectional Evolutionary Search [93.21736992722835]
  Bidirectional Evolutionary Search (BES) is a search framework that couples forward candidate evolution with backward goal decomposition.<n>We provide theoretical motivation showing that candidates generated by expansion-only search are confined to a narrow entropy shell while evolutionary operators can escape it.<n> Experiments show that on challenging post-training tasks where mainstream post-training algorithms fail to improve, BES enables consistent gains.
  arXiv  Detail & Related papers  (2026-05-27T17:59:15Z)
• Squeeze Evolve: Unified Multi-Model Orchestration for Verifier-Free Evolution [81.46210789228296]
  We introduce Squeeze Evolve, a unified multi-model orchestration framework for verifier-free evolutionary inference.<n>Our approach is guided by a simple principle: allocate model capability where it has the highest marginal utility.
  arXiv  Detail & Related papers  (2026-04-09T02:14:45Z)
• AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization [61.535567824938205]
  We introduce AdaEvolve, a framework that reformulates LLM-driven evolution as a hierarchical adaptive optimization problem.<n>AdaEvolve consistently outperforms the open-ended baselines across 185 different open-ended optimization problems.
  arXiv  Detail & Related papers  (2026-02-23T18:45:31Z)
• Intention-Conditioned Flow Occupancy Models [80.42634994902858]
  Large-scale pre-training has fundamentally changed how machine learning research is done today.<n>Applying this same framework to reinforcement learning is appealing because it offers compelling avenues for addressing core challenges in RL.<n>Recent advances in generative AI have provided new tools for modeling highly complex distributions.
  arXiv  Detail & Related papers  (2025-06-10T15:27:46Z)
• From Search To Sampling: Generative Models For Robust Algorithmic Recourse [24.730097141422537]
  We introduce GenRe, a generative recourse model designed to train the three recourse objectives jointly.<n>We show GenRe provides the best trade-off between cost, plausibility and validity, compared to state-of-art baselines.
  arXiv  Detail & Related papers  (2025-05-12T08:44:28Z)
• Which LLM to Play? Convergence-Aware Online Model Selection with Time-Increasing Bandits [43.65904435249823]
  We propose a time-increasing bandit algorithm TI-UCB, which effectively predicts the increase of model performances. Our results highlight the importance of utilizing increasing-then-converging pattern for more efficient and economic model selection.
  arXiv  Detail & Related papers  (2024-03-11T23:52:46Z)
• A Bandit Approach with Evolutionary Operators for Model Selection [0.4604003661048266]
  This work formulates model selection as an infinite-armed bandit problem, namely, a problem in which a decision maker iteratively selects one of an infinite number of fixed choices (i.e., arms) The arms are machine learning models to train and selecting an arm corresponds to a partial training of the model (resource allocation) We propose the algorithm Mutant-UCB that incorporates operators from evolutionary algorithms into the UCB-E bandit algorithm introduced by Audiber et al. Tests carried out on three open source image classification data sets attest to the relevance of this novel combining approach, which outperforms the state-of
  arXiv  Detail & Related papers  (2024-02-07T08:01:45Z)
• MILO: Model-Agnostic Subset Selection Framework for Efficient Model Training and Tuning [68.12870241637636]
  We propose MILO, a model-agnostic subset selection framework that decouples the subset selection from model training. Our empirical results indicate that MILO can train models $3times - 10 times$ faster and tune hyperparameters $20times - 75 times$ faster than full-dataset training or tuning without performance.
  arXiv  Detail & Related papers  (2023-01-30T20:59:30Z)

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.