Promptbreeder evolves both task prompts and the mutation prompts that improve them using LLMs, outperforming Chain-of-Thought and Plan-and-Solve on arithmetic and commonsense reasoning benchmarks.
hub Mixed citations
Illuminating search spaces by mapping elites
Mixed citation behavior. Most common role is background (64%).
48
Pith papers citing it
Background
64% of classified citations
abstract
Many fields use search algorithms, which automatically explore a search space to find high-performing solutions: chemists search through the space of molecules to discover new drugs; engineers search for stronger, cheaper, safer designs, scientists search for models that best explain data, etc. The goal of search algorithms has traditionally been to return the single highest-performing solution in a search space. Here we describe a new, fundamentally different type of algorithm that is more useful because it provides a holistic view of how high-performing solutions are distributed throughout a search space. It creates a map of high-performing solutions at each point in a space defined by dimensions of variation that a user gets to choose. This Multi-dimensional Archive of Phenotypic Elites (MAP-Elites) algorithm illuminates search spaces, allowing researchers to understand how interesting attributes of solutions combine to affect performance, either positively or, equally of interest, negatively. For example, a drug company may wish to understand how performance changes as the size of molecules and their cost-to-produce vary. MAP-Elites produces a large diversity of high-performing, yet qualitatively different solutions, which can be more helpful than a single, high-performing solution. Interestingly, because MAP-Elites explores more of the search space, it also tends to find a better overall solution than state-of-the-art search algorithms. We demonstrate the benefits of this new algorithm in three different problem domains ranging from producing modular neural networks to designing simulated and real soft robots. Because MAP- Elites (1) illuminates the relationship between performance and dimensions of interest in solutions, (2) returns a set of high-performing, yet diverse solutions, and (3) improves finding a single, best solution, it will advance science and engineering.
hub tools
citation-role summary
background 7
method 4
citation-polarity summary
representative citing papers
No continuous utility-preserving input wrapper can eliminate all prompt injection risks in connected prompt spaces for language models.
DRSR uses Quality-Diversity to produce diverse symbolic regression expressions differing in residual distributions, enabling post-search selection on synthetic and astronomical data.
FrontierSmith automates synthesis of open-ended coding problems from closed-ended seeds and shows measurable gains on two open-ended LLM coding benchmarks.
PPol uses LLM-driven evolutionary program search to create diverse human-like user personas for simulators, yielding 33-62% fitness gains and +17% agent task success on retail and airline domains.
EvolveSignal applies LLM-driven evolutionary program synthesis to discover heuristic variations of traffic signal control logic that reduce delay and stops compared to Webster's method in simulation.
Meta Agent Search uses a meta-agent to iteratively program novel agentic systems in code, producing agents that outperform state-of-the-art hand-designed ones across coding, science, and math while transferring across domains and models.
EvoPrompt uses LLMs to run evolutionary operators on populations of prompts, outperforming human-engineered prompts by up to 25% on BIG-Bench Hard tasks across 31 datasets.
Phenotypic distance from output differences on fixed inputs enables surrogate models that predict performance of variable-topology neural networks as well as or better than weight-based models on fixed topologies in a robotic navigation task.
QD-LLM evolves prompt embeddings via neuroevolution in a quality-diversity framework, delivering 46% higher coverage and 41% higher QD-score than prior methods on coding and writing benchmarks.
External evolution beats internal deliberation in collective-action tasks with statistical significance but neither helps in trading, and deliberation never discovers punishment while evolution does.
TeLAPA maintains archives of behaviorally diverse yet competent policies aligned in a shared latent space to preserve plasticity and enable faster recovery after interference in continual reinforcement learning.
Autopoiesis uses LLM-driven program synthesis to evolve serving policies online during deployment, delivering up to 53% and average 34% gains over prior LLM serving systems under runtime dynamics.
LensAgent is a training-free LLM agent framework that reconstructs mass distributions in SLACS strong lensing systems to extract sub-galactic substructures.
AlphaEvolve is an LLM-orchestrated evolutionary coding agent that discovered a 4x4 complex matrix multiplication algorithm using 48 scalar multiplications, the first improvement over Strassen's algorithm in 56 years, plus optimizations for Google data centers and hardware.
A universal LLM optimizer for text artifacts achieves SOTA results on six tasks including tripling ARC-AGI accuracy and cutting cloud costs by 40% via cross-task transfer and side information.
PopuLoRA shows that co-evolving populations of LoRA adapters through cross-evaluated self-play can outperform compute-matched single-agent baselines on multiple code and math reasoning benchmarks.
ToolMol integrates evolutionary algorithms with agentic LLMs and precise RDKit tools to optimize multi-objective drug properties, yielding ligands with over 10% better predicted binding affinity and 35% gains in absolute binding free energy on three protein targets.
Kernel-Smith combines evolutionary search with RL post-training to generate optimized GPU kernels, achieving SOTA speedups on KernelBench that beat Gemini-3.0-pro and Claude-4.6-opus on NVIDIA Triton and generalize to MetaX MACA.
Q-DIG applies quality diversity optimization with vision-language models to generate diverse adversarial instructions that reveal VLA robot failures and enable robustness improvements via fine-tuning.
SSPT turns space-syntax integration metrics into post-training feedback signals that improve public-space dominance and functional hierarchy in AI-generated residential floor plans.
ToxSearch-S applies unsupervised speciation to evolutionary prompt search, maintaining capacity-limited species with exemplar leaders and species-aware selection to achieve higher peak toxicity and broader semantic coverage than standard methods.
Tournament-informed task selection in adversarial QD produces higher quality and diversity in coevolved solutions across Pong, cat-and-mouse, and pursuers-evaders games.
MAP-Elites recovers multiple high-quality motif variants from CTCF ChIP-seq data with fitness comparable to MEME while revealing structured diversity.
citing papers explorer
-
Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
Promptbreeder evolves both task prompts and the mutation prompts that improve them using LLMs, outperforming Chain-of-Thought and Plan-and-Solve on arithmetic and commonsense reasoning benchmarks.
-
The Defense Trilemma: Why Prompt Injection Defense Wrappers Fail?
No continuous utility-preserving input wrapper can eliminate all prompt injection risks in connected prompt spaces for language models.
-
Diversified Residual Symbolic Regression
DRSR uses Quality-Diversity to produce diverse symbolic regression expressions differing in residual distributions, enabling post-search selection on synthetic and astronomical data.
-
FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale
FrontierSmith automates synthesis of open-ended coding problems from closed-ended seeds and shows measurable gains on two open-ended LLM coding benchmarks.
-
Beyond Cooperative Simulators: Generating Realistic User Personas for Robust Evaluation of LLM Agents
PPol uses LLM-driven evolutionary program search to create diverse human-like user personas for simulators, yielding 33-62% fitness gains and +17% agent task success on retail and airline domains.
-
EvolveSignal: A Large Language Model Powered Coding Agent for Discovering Traffic Signal Control Strategies
EvolveSignal applies LLM-driven evolutionary program synthesis to discover heuristic variations of traffic signal control logic that reduce delay and stops compared to Webster's method in simulation.
-
Automated Design of Agentic Systems
Meta Agent Search uses a meta-agent to iteratively program novel agentic systems in code, producing agents that outperform state-of-the-art hand-designed ones across coding, science, and math while transferring across domains and models.
-
EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers
EvoPrompt uses LLMs to run evolutionary operators on populations of prompts, outperforming human-engineered prompts by up to 25% on BIG-Bench Hard tasks across 31 datasets.
-
Prediction of neural network performance by phenotypic modeling
Phenotypic distance from output differences on fixed inputs enables surrogate models that predict performance of variable-topology neural networks as well as or better than weight-based models on fixed topologies in a robotic navigation task.
-
Parameter-Efficient Neuroevolution for Diverse LLM Generation: Quality-Diversity Optimization via Prompt Embedding Evolution
QD-LLM evolves prompt embeddings via neuroevolution in a quality-diversity framework, delivering 46% higher coverage and 41% higher QD-score than prior methods on coding and writing benchmarks.
-
Internal vs. External: Comparing Deliberation and Evolution for Multi-Agent Constitutional Design
External evolution beats internal deliberation in collective-action tasks with statistical significance but neither helps in trading, and deliberation never discovers punishment while evolution does.
-
Beyond Single-Model Optimization: Preserving Plasticity in Continual Reinforcement Learning
TeLAPA maintains archives of behaviorally diverse yet competent policies aligned in a shared latent space to preserve plasticity and enable faster recovery after interference in continual reinforcement learning.
-
Autopoiesis: A Self-Evolving System Paradigm for LLM Serving Under Runtime Dynamics
Autopoiesis uses LLM-driven program synthesis to evolve serving policies online during deployment, delivering up to 53% and average 34% gains over prior LLM serving systems under runtime dynamics.
-
LensAgent: A Self Evolving Agent for Autonomous Physical Inference of Sub-galactic Structure
LensAgent is a training-free LLM agent framework that reconstructs mass distributions in SLACS strong lensing systems to extract sub-galactic substructures.
-
AlphaEvolve: A coding agent for scientific and algorithmic discovery
AlphaEvolve is an LLM-orchestrated evolutionary coding agent that discovered a 4x4 complex matrix multiplication algorithm using 48 scalar multiplications, the first improvement over Strassen's algorithm in 56 years, plus optimizations for Google data centers and hardware.
-
optimize_anything: A Universal API for Optimizing any Text Parameter
A universal LLM optimizer for text artifacts achieves SOTA results on six tasks including tripling ARC-AGI accuracy and cutting cloud costs by 40% via cross-task transfer and side information.
-
PopuLoRA: Co-Evolving LLM Populations for Reasoning Self-Play
PopuLoRA shows that co-evolving populations of LoRA adapters through cross-evaluated self-play can outperform compute-matched single-agent baselines on multiple code and math reasoning benchmarks.
-
ToolMol: Evolutionary Agentic Framework for Multi-objective Drug Discovery
ToolMol integrates evolutionary algorithms with agentic LLMs and precise RDKit tools to optimize multi-objective drug properties, yielding ligands with over 10% better predicted binding affinity and 35% gains in absolute binding free energy on three protein targets.
-
Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization
Kernel-Smith combines evolutionary search with RL post-training to generate optimized GPU kernels, achieving SOTA speedups on KernelBench that beat Gemini-3.0-pro and Claude-4.6-opus on NVIDIA Triton and generalize to MetaX MACA.
-
Red-Teaming Vision-Language-Action Models via Quality Diversity Prompt Generation for Robust Robot Policies
Q-DIG applies quality diversity optimization with vision-language models to generate diverse adversarial instructions that reveal VLA robot failures and enable robustness improvements via fine-tuning.
-
Space Syntax-guided Post-training for Residential Floor Plan Generation
SSPT turns space-syntax integration metrics into post-training feedback signals that improve public-space dominance and functional hierarchy in AI-generated residential floor plans.
-
Diversifying Toxicity Search in Large Language Models Through Speciation
ToxSearch-S applies unsupervised speciation to evolutionary prompt search, maintaining capacity-limited species with exemplar leaders and species-aware selection to achieve higher peak toxicity and broader semantic coverage than standard methods.
-
Tournament Informed Adversarial Quality Diversity
Tournament-informed task selection in adversarial QD produces higher quality and diversity in coevolved solutions across Pong, cat-and-mouse, and pursuers-evaders games.
-
Motif Diversity in Human Liver ChIP-seq Data Using MAP-Elites
MAP-Elites recovers multiple high-quality motif variants from CTCF ChIP-seq data with fitness comparable to MEME while revealing structured diversity.
-
JSON-Bag: A generic game trajectory representation
JSON-Bag tokenizes JSON game trajectories, applies Jensen-Shannon distance and prototype nearest-neighbor search to classify agents/parameters/seeds across six tabletop games, outperforming hand-crafted features and correlating with policy distances.
-
Adversarial Coevolutionary Illumination with Generational Adversarial MAP-Elites
GAME is a new adversarial coevolutionary QD algorithm using generational alternation and vision embeddings that outperforms one-sided baselines across battle, wrestling, and deck-building tasks while revealing arms-race dynamics and the role of neutral mutations.
-
Automatic Calibration of Artificial Neural Networks for Zebrafish Collective Behaviours using a Quality Diversity Algorithm
CVT-MAP-Elites quality diversity search calibrates ANN-based agent models of zebrafish collective motion to outperform standard evolutionary methods on both macroscopic group metrics and microscopic individual realism.
-
Diverse Agents for Ad-Hoc Cooperation in Hanabi
Quality Diversity algorithms are proposed to generate diverse agent populations for ad-hoc cooperation evaluation in Hanabi, with discussion of metrics and adaptive agent building.
-
HMACE: Heterogeneous Multi-Agent Collaborative Evolution for Combinatorial Optimization
HMACE deploys Proposer, Generator, Evaluator, and Reflector agents in an evolutionary loop to generate and refine heuristics for NP-hard problems, reporting lower optimality gaps and token costs than baselines on TSP and Online BPP.
-
Agentic Architect: An Agentic AI Framework for Architecture Design Exploration and Optimization
An LLM-driven agentic system evolves microarchitectural policies for cache replacement, data prefetching, and branch prediction, producing designs that match or exceed prior state-of-the-art in IPC on standard benchmarks.
-
QDTraj: Exploration of Diverse Trajectory Primitives for Articulated Objects Robotic Manipulation
QDTraj uses Quality-Diversity algorithms with sparse rewards to produce at least five times more diverse high-performing trajectories for articulated object manipulation than compared methods, validated across 30 objects with hundreds of trajectories per task.
-
Multi-Task Optimization over Networks of Tasks
MONET represents tasks as graph nodes and uses neighbor-based crossover plus per-task mutation to transfer knowledge, matching or exceeding MAP-Elites performance on four large-scale simulation domains.
-
LLM-Guided Prompt Evolution for Password Guessing
LLM-guided evolutionary prompt optimization using MAP-Elites and island models raises password cracking rates from 2.02% to 8.48% on a RockYou-derived test set across local, cloud, and ensemble LLM setups.
-
TurboEvolve: Towards Fast and Robust LLM-Driven Program Evolution
TurboEvolve improves LLM program evolution by running parallel islands with LLM-generated diverse candidates that carry self-assigned weights, an adaptive scheduler, and clustered seed injection to reach stronger solutions at lower evaluation budgets.
-
Uncovering Linguistic Fragility in Vision-Language-Action Models via Diversity-Aware Red Teaming
DAERT generates diverse adversarial instructions via a uniform policy in RL to drop VLA task success rates from 93.33% to 5.85% on benchmarks with models like π0 and OpenVLA.
-
GEAR: Genetic AutoResearch for Agentic Code Evolution
GEAR applies genetic algorithms to maintain and evolve multiple research states in autonomous code agents, outperforming single-path baselines by continuing to discover improvements over extended runs.
-
Evolving the Hearthstone Meta
An evolutionary algorithm searches for minimal card attribute changes in Hearthstone to balance deck win rates near 50%.
-
Distributional Value Estimation Without Target Networks for Robust Quality-Diversity
QDHUAC is a distributional, target-free QD-RL method that enables stable high-UTD training and competitive performance on Brax locomotion tasks using far fewer environment steps than prior approaches.
-
CVT Archives and Chemical Embedding Measures for Multi-Objective Quality Diversity in Molecular Design
CVT archives with learned chemical embeddings improve median global hypervolume and multi-objective quality diversity in NLO molecular design compared to grid-based archives.
-
MadEvolve: Evolutionary Optimization of Trading Systems with Large Language Models
MadEvolve uses LLMs for evolutionary optimization of trading strategies and reports significant backtest improvements on Bitcoin tasks including signal feature evolution and joint strategy optimization.
-
Artificial Adaptive Intelligence: The Missing Stage Between Narrow and General Intelligence
Proposes Artificial Adaptive Intelligence as the regime between narrow and general AI, defined by elimination of human-specified hyperparameters, and introduces an adaptivity index plus parametric minimality principle grounded in minimum description length.
-
Effective Harness Engineering for Algorithm Discovery with Coding Agents
Under fixed token budget on Circle Packing, deeper per-candidate reasoning beats generating more shallow candidates, and capable models produce evaluation hacks at higher rates.
-
Multi-Objective Evolutionary Design of Molecules with Enhanced Nonlinear Optical Properties
Evolutionary algorithms can discover molecules with improved nonlinear optical properties by simultaneously optimizing hyperpolarizability ratio, HOMO-LUMO gap, polarizability, and energy per atom.
-
The Many AI Challenges of Hearthstone
The paper surveys AI challenges in Hearthstone to illustrate the broader field of AI and games research through in-depth analysis of a single game.
-
Spiking Neural Network Architecture Search: A Survey
A survey of Spiking Neural Network architecture search techniques viewed through a hardware/software co-design lens.
- FML-bench: A Controlled Study of AI Research Agent Strategies from the Perspective of Search Dynamics
- CVEvolve: Autonomous Algorithm Discovery for Unstructured Scientific Data Processing
- Stable-GFlowNet: Toward Diverse and Robust LLM Red-Teaming via Contrastive Trajectory Balance