LLM-guided evolutionary search yields the first domain-independent C++ planning heuristics that exceed the strongest hand-engineered baselines on coverage and speed trade-offs across unseen domains.
hub Mixed citations
Illuminating search spaces by mapping elites
Mixed citation behavior. Most common role is background (64%).
55
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
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.
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.
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.
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.
Non-monotonic safety alignment appears in Gemma models, with Gemma 3 at 68.7% ASR versus 45.5% in Gemma 2 and 33.9% in Gemma 4 via MAP-Elites red-teaming and cross-generational attack transfer.
Applies MAP-Elites quality-diversity optimization to evolve semantic attack strategies across dimensions like strategy type, encoding, and length, uncovering distinct vulnerability profiles in four LLMs including GPT-4o-mini and Claude 3.5 Sonnet.
New Point-Line and Spatial-Layout map representations enable MAP-Elites to produce FPS maps with higher diversity and quality than prior All-Black and Grid-Graph methods.
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.
citing papers explorer
-
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.
-
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.
-
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.
- Beyond Single-Model Optimization: Preserving Plasticity in Continual Reinforcement Learning