When Does Diversity Rescue Evolutionary Search of LLM Agent Strategies? A Controlled Landscape Study of Monoculture Collapse and the Novelty Escape
Open accessThe DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.
Abstract
Population-based and evolutionary search is increasingly used to design LLM-agent strategies, motivated by the promise of robustness through behavioural diversity — yet such populations tend to lose diversity first. We ask when maintaining behavioural diversity rescues evolutionary search of natural-language agent strategies, and when it does not. To isolate search dynamics from the cost and noise of LLM rollouts, we use a fast deterministic surrogate: deceptive two-basin and tunable NK fitness landscapes that share the combinatorial structure of a modular agent-strategy genome. We run paired, equal-budget comparisons of eight selection strategies across up to 28 seeds, reporting Wilson intervals and paired-bootstrap tests. Objective-only selection escapes the deceptive trap in 11% of runs and collapses behavioural diversity from 0.75 to 0.17, whereas adaptive novelty-blending and novelty with local competition escape 46% and 43% of the time (p=0.0015, p=0.0007) while retaining 0.65-0.67 diversity. Four further results delimit the mechanism: a learned behaviour space (AURORA) backfires when the descriptor is already task-aligned; the advantage appears only as epistasis rises (K=6); it vanishes when a landscape offers multiple routes upward; and a real-LLM probe shows the effect requires both a fitness gradient and behavioural variance, neither of which two natural tasks supplied. Diversity maintenance is therefore a targeted remedy, not a universal one. We map where it helps and where it cannot apply, and pre-register an engineered-deception real-LLM experiment as the decisive transfer test. All data, generators, and protocols are released; no agent-benchmark results are claimed.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Genetic Algorithms and Machine Learning
Goldberg, D. E., & Holland, J. H. (1988) · Machine Learning · doi:10.1023/a:1022602019183 · Cited by 3,193
Self-Refine: Iterative Refinement with Self-Feedback
Madaan, A., Tandon, N., Gupta, P., Hallinan, S., Gao, L., Wiegreffe, S., Alon, U., Dziri, N., Prabhumoye, S., Yang, Y., et al. (2023) · arXiv · doi:10.48550/arxiv.2303.17651 · Cited by 2,314
Tree of Thoughts: Deliberate Problem Solving with Large Language Models
Yao, S., Yu, D., Zhao, J., Shafran, I., Griffiths, T. L., Cao, Y., & Narasimhan, K. (2023) · arXiv · doi:10.48550/arxiv.2305.10601 · Cited by 1,158
Reflexion: Language Agents with Verbal Reinforcement Learning
Shinn, N., Cassano, F., Berman, E., Gopinath, A., Narasimhan, K., & Yao, S. (2023) · arXiv · doi:10.48550/arxiv.2303.11366 · Cited by 1,087
Mathematical discoveries from program search with large language models
Romera-Paredes, B., Barekatain, M., Novikov, A., Balog, M., Kumar, M. P., Dupont, E., Ruiz, F. J. R., Ellenberg, J. S., Wang, P., Fawzi, O., et al. (2024) · Nature · doi:10.1038/s41586-023-06924-6 · Cited by 544
Illuminating search spaces by mapping elites
Mouret, J.-B., & Clune, J. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1504.04909 · Cited by 386
Evolving a diversity of virtual creatures through novelty search and local competition
Lehman, J., & Stanley, K. O. (2011) · Proceedings of the 13th annual conference on Genetic and evolutionary computation · doi:10.1145/2001576.2001606 · Cited by 385
Evolutionary Algorithms for Reinforcement Learning
Moriarty, D. E., Schultz, A. C., & Grefenstette, J. J. (1999) · Journal of Artificial Intelligence Research · doi:10.1613/jair.613 · Cited by 340
Large Language Models Are Human-Level Prompt Engineers
Zhou, Y., Muresanu, A. I., Han, Z., Paster, K., Pitis, S., Chan, H., & Ba, J. (2022) · arXiv · doi:10.48550/arxiv.2211.01910 · Cited by 330
Automatic Prompt Optimization with "Gradient Descent" and Beam Search
Pryzant, R., Iter, D., Li, J., Lee, Y. T., Zhu, C., & Zeng, M. (2023) · arXiv · doi:10.48550/arxiv.2305.03495 · Cited by 191
EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms
Yuan, S., Song, K., Chen, J., Tan, X., Li, D., & Yang, D. (2025) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2025.naacl-long.315 · Cited by 162
Large Language Models as Optimizers
Yang, C., Wang, X., Lu, Y., Liu, H., Le, Q. V., Zhou, D., & Chen, X. (2023) · arXiv · doi:10.48550/arxiv.2309.03409 · Cited by 151
Autonomous skill discovery with quality-diversity and unsupervised descriptors
Cully, A. (2019) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/3321707.3321804 · Cited by 130
Unsupervised Behavior Discovery With Quality-Diversity Optimization
Grillotti, L., & Cully, A. (2022) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2022.3159855 · Cited by 75
Language Model Crossover: Variation through Few-Shot Prompting
Meyerson, E., Nelson, M. J., Bradley, H., Gaier, A., Moradi, A., Hoover, A. K., & Lehman, J. (2024) · ACM Transactions on Evolutionary Learning and Optimization · doi:10.1145/3694791 · Cited by 75
Evolution Through Large Models
Lehman, J., Gordon, J., Jain, S., Ndousse, K., Yeh, C., & Stanley, K. O. (2024) · Genetic and Evolutionary Computation · doi:10.1007/978-981-99-3814-8_11 · Cited by 74
Surprise Search: Beyond Objectives and Novelty
Gravina, D., Liapis, A., & Yannakakis, G. N. (2016) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/2908812.2908817 · Cited by 61
Promptbreeder: Self-Referential Self-Improvement via Prompt Evolution
Fernando, C., Banarse, D., Michalewski, H., Osindero, S., & Rocktäschel, T. (2023) · arXiv · doi:10.48550/arxiv.2309.16797 · Cited by 31
TextGrad: Automatic "Differentiation" via Text
Yuksekgonul, M., Bianchi, F., Boen, J., Liu, S., Huang, Z., Guestrin, C., & Zou, J. (2024) · arXiv · doi:10.48550/arxiv.2406.07496 · Cited by 12
Research works printed but not linked: 14
- Maxence Bahlous-Boldi, 2025, Dominated novelty search: Parameter-free quality-diversity
- Hao-An, 2025, A survey of self-evolving agents
- Qingyan Guo, Connecting large language models with evolutionary algorithms yields powerful prompt optimizers, International Conference on Learning Representations (ICLR)
- John H Holland, 1975, Adaptation in Natural and Artificial Systems
- Shengran Hu, Automated design of agentic systems, International Conference on Learning Representations (ICLR)
- A Stuart, 1993, The Origins of Order: Self-Organization and Selection in Evolution
- Omar Khattab, Dspy: Compiling declarative language model calls into self-improving pipelines, International Conference on Learning Representations (ICLR)
- Sung Joon, Generative agents: Interactive simulacra of human behavior, Proceedings of the ACM Symposium on User Interface Software and Technology
- Timo Schick, Toolformer: Language models can teach themselves to use tools, Advances in Neural Information Processing Systems (NeurIPS)
- Guanzhi Wang, Voyager: An open-ended embodied agent with large language models, Transactions on Machine Learning Research
- Xuezhi Wang, Self-consistency improves chain of thought reasoning in language models, International Conference on Learning Representations (ICLR)
- Jason Wei, Chain-of-thought prompting elicits reasoning in large language models, Advances in Neural Information Processing Systems (NeurIPS)
- Shunyu Yao, React: Synergizing reasoning and acting in language models, International Conference on Learning Representations (ICLR)
- Jiayi Zhang, Aflow: Automating agentic workflow generation, International Conference on Learning Representations (ICLR)
Metadata
- Authors
- ALOBED, M.
- Affiliations
- Idlib University (SY)
- Corresponding author
- ALOBED, MOHAMMAD
- ORCID
- ALOBED, MOHAMMAD
- Venue
- SSRN Electronic Journal
- Publisher
- Elsevier BV
- Published
- 2026
- ISSN
- 1556-5068 (ISSN-L)
- OpenAlex
- W7203539670
- Cited by
- 0
- References
- 6
- Type
- posted content
- Language
- en
- Open access
- green
- doi.org
- Locations
- SSRN Electronic Journal (acceptedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Evolutionary Algorithms and Applications
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Genetics › Evolution and Genetic Dynamics
- Physical Sciences › Computer Science › Artificial Intelligence › Metaheuristic Optimization Algorithms Research
- Keywords
- behavioral diversity, evolutionary search, NK fitness landscapes, selection strategies, epistasis, diversity maintenance
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.