Automated failure discovery can be framed as a diversity problem: the objective is to expose distinct ways a system fails rather than a single critical adversarial case. Yet uniform parent sampling provides no way to allocate search effort toward individuals likely to produce durable archive contributions. We study this credit assignment problem in an unstructured Quality-Diversity (QD) archive, testing whether signals available before an individual has reproduced distinguish offspring that merely enter the archive from those still retained generations later. Across a planar-arm benchmark and two robotic-locomotion tasks, the same signals are often associated with entry and persistence in opposite directions. In particular, lineage depth is the clearest such signal, and its persistence discrimination grows with population capacity, which is associated with lower turnover. Biasing parent selection toward the signals with the strongest measured association to survival nevertheless does not improve search: moderate bias matches uniform sampling, and strong bias reduces QD-score.
Figures & tables
Group
Cold-start?
Signals
Lineage at birth
yes
depth; ancestral-fitness EWMA; ancestry entropy; competition fitness at birth
Current state
yes
age
Archive state
yes
parent fitness; current competition fitness
Mating event
no
∣λ∣ ; compositional residual; child fitness
Offspring feedback
no
curiosity; offspring survival rate
Table 1: Signal availability.
Figure 1: Entry against persistence AUC at capacity 1024 and H=1000 , one panel per domain. Points are cold-start-selectable signals averaged across seeds; blue denotes lineage- and current-state signals, grey the contemporaneous archive-state baselines. Grey lines mark chance. Signals on opposite sides of chance for the two outcomes are associated with entry and persistence in opposite directions.
Figure 2: Signed lineage-depth AUC across archive capacities for entry and persistence. Larger archives have lower turnover because the number of offspring stays fixed.
Appendix figures & tables3 assets
Supplementary material from the paper’s appendix.
Appendix
Task
256
1024
4096
Omnidirectional Ant
≈94
≈32
≈16
Arm
≈16
≈15
≈13
Walker 2D
≈22
≈23
≈16
Appendix
Table 2: Interquartile range of lineage depth among retained individuals.
Experiment
Domains
Capacity
Gens
Parent selection
Seeds
Signal measurement
all three
256
10,000
uniform
5
all three
1024
10,000
uniform
10
all three
4096
10,000
uniform
5
Fitness sweep
Omnidirectional Ant
1024
4,000
uniform, τ∈{0.1,0.5}
10
Omnidirectional Ant
4096
4,000
uniform, τ∈{0.1,0.5}
10
Depth sweep
Omnidirectional Ant
1024
10,000
± depth, τ∈{0.5,2.0}
10
Appendix
Table 3: Experimental configuration. Seed counts differ by capacity in the measurement sweep.
Domain
λ=0.25
λ=0.50
λ=1.00
Arm
98.9
96.0
66.0
Omnidirectional Ant
97.0
94.2
78.5
Walker 2D
95.8
94.6
60.9
Appendix
Table 4: Final projected QD-score as a percentage of unmodified DNS ( λ=0 ). The ladder is monotone on every domain.
Sequential agent search accumulates changes from its current champion but discards alternative branches; independent proposals preserve breadth but restart from the root. Loreley instead retains complete repository states in a Quality-Diversity (QD) archive and samples them as parents or supplies them as context for later edits. Candidates are Git commits produced in isolated worktrees and judged by a project-supplied evaluator. We compare configured Loreley QD, sequential champion editing, and independent root proposals in a matched Zstandard experiment: seven paired blocks and 48 physical candidate jobs per policy and block (1,008 total), with root-only initialization and each policy's native concurrency. Validation selected a winner at each budget checkpoint; an agent-hidden holdout measured the fixed candidate. At 48 jobs, QD was 0.135% below Sequential Champion (95% BCa interval for the paired effect: -0.556% to +0.161%) and 0.320% above Independent Root (-0.082% to +0.686%). Neither contrast established a QD advantage; Sequential had the highest observed 48-job mean and median. Archive retention and later sampling did occur. Four of seven final QD winners had a non-incumbent state in their primary-parent ancestry under a retrospective one-incumbent rule applied only to the observed QD stream. Including inspiration edges raised the count to six, without showing that supplied context caused an edit. Three earlier capability campaigns produced generation-4, multi-file improvements in two Python libraries and a separate Zstandard revision. Loreley engaged the intended stepping-stone mechanism, but the controlled experiment did not show an endpoint benefit at 48 jobs.
We present DEI: Diversity in Evolutionary Inference, a distributed Quality-Diversity (QD) search framework that assigns heterogeneous large language models (LLMs) as mutation operators across peer nodes communicating with non-blocking collective operations. Unlike homogeneous parallel search, which replicates a single model's inductive biases across all workers, DEI treats each LLM's distinct creative prior as a complementary source of behavioral novelty. Extending the Digital Red Queen framework with DEI, nodes share local optimal solutions at the end of each round to seed the next round's population. This creates cross-model adversarial pressure that drives robustness beyond intra-model self-play. Evaluated on the Core War domain, a competitive programming benchmark in which Redcode warrior programs battle inside a simulated machine, a four-node heterogeneous ensemble (GPT-5.4-mini, Claude Sonnet 4.6, GPT-5.2, and Claude Haiku 4.5) achieves 124 percent higher merged-archive QD-Score (45.90 vs. 20.46) and 28 percent higher coverage (80.6 percent vs. 63.0 percent of cells) than a single-node baseline at equal total LLM-call budget. The heterogeneous ensemble also outperforms an equally-budgeted homogeneous ensemble on QD-Score, coverage, and held-out solution generality across all four model families. These results provide the first empirical evidence that model diversity, not merely parallelism, is the key driver of gain in distributed LLM-based QD search.
Quality-Diversity (QD) algorithms excel at discovering diverse repertoires of skills, but are hindered by poor sample efficiency and often require tens of millions of environment steps to solve complex locomotion tasks. Recent advances in Reinforcement Learning (RL) have shown that high Update-to-Data (UTD) ratios accelerate Actor-Critic learning. While effective, standard high-UTD algorithms typically utilise target networks to stabilise training. This requirement introduces a significant computational bottleneck, rendering them impractical for resource-intensive Quality-Diversity (QD) tasks where sample efficiency and rapid population adaptation are critical. In this paper, we introduce QDHUAC, a sample-efficient, target-free and distributional QD-RL algorithm that provides dense and low-variance gradient signals, which enables high-UTD training for Dominated Novelty Search whilst requiring an order of magnitude fewer environment steps. We demonstrate that our method enables stable training at high UTD ratios, achieving competitive coverage and fitness on high-dimensional Brax environments with an order of magnitude fewer samples than baselines. Our results suggest that combining target-free distributional critics with dominance-based selection is a key enabler for the next generation of sample-efficient evolutionary RL algorithms.