Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2605.20086

What Do Evolutionary Coding Agents Evolve?

Nico Pelleriti·Sree Harsha Nelaturu·Zhanke Zhou·Zongze Li·Max Zimmer·Bo Han·Sebastian Pokutta
View original source ↗Read source document ↗Export metadata ↓

Abstract

Recent work pairs LLMs with evolutionary search to iteratively generate, modify, and select code using task-specific feedback. These systems have produced strong results in mathematical discovery and algorithm design, yet a fundamental question remains: what do they actually evolve? Progress is typically summarized by the best score a run reaches under a task-specific evaluator, but that score can reflect several different mechanisms: new algorithmic structure, re-tuning an existing strategy, recombining ideas already in the model's internal knowledge, or overfitting to the evaluator. Distinguishing these mechanisms requires inspecting the search process itself, not only its final outcome. We introduce EvoTrace, a dataset of evolutionary coding traces spanning four evolutionary frameworks, reasoning and non-reasoning models, and 16 tasks across mathematics and algorithm design. To analyze these traces, we develop EvoReplay, a replay-based methodology that reconstructs the local search states behind high-scoring solutions and tests controlled interventions, including adjusting constants, removing program components and substituting models or prompting contexts. We annotate every code edit in EvoTrace with one of nine recurring edit types using an LLM-as-judge pipeline validated against blind human re-annotation. Across EvoTrace, most score gains come from a small subset of these edit types. We further find a deterministic cycling pattern: about 30% of code lines added during search are byte-identical re-introductions of previously-deleted lines, present throughout nearly every run. These results show that benchmark gains in evolutionary coding agents can arise from qualitatively different mechanisms, only some of which correspond to new algorithmic structure. EvoTrace enables more diagnostic evaluation of evolutionary coding agents beyond final benchmark scores.

Explore related subjects

cs.NEcs.AIcs.LG

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Nico Pelleriti, Sree Harsha Nelaturu, Zhanke Zhou, Zongze Li, Max Zimmer, Bo Han, Sebastian Pokutta. 2026-05-19. What Do Evolutionary Coding Agents Evolve?. https://arxiv.org/abs/2605.20086

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Continuous Spiking Graph Neural Networks

Continuous graph neural networks (CGNNs) have garnered significant attention due to their ability to generalize existing discrete graph neural networks (GNNs) by introducing continuous dynamics. They typically draw inspiration from diffusion-based methods to introduce a novel propagation scheme, which is analyzed using ordinary differential equations (ODE). However, the implementation of CGNNs requires significant computational power, making them challenging to deploy on battery-powered devices. Inspired by recent spiking neural networks (SNNs), which emulate a biological inference process and provide an energy-efficient neural architecture, we incorporate the SNNs with CGNNs in a unified framework, named Continuous Spiking Graph Neural Networks (COS-GNN). We employ SNNs for graph node representation at each time step, which are further integrated into the ODE process along with time. To enhance information preservation and mitigate information loss in SNNs, we introduce the high-order structure of COS-GNN, which utilizes the second-order ODE for spiking representation and continuous propagation. Moreover, we provide the theoretical proof that COS-GNN effectively mitigates the issues of exploding and vanishing gradients, enabling us to capture long-range dependencies between nodes. Experimental results on graph-based learning tasks demonstrate the effectiveness of the proposed COS-GNN over competitive baselines.

cs.NE↗
arXiv2026

Emergent Intelligence: Resonant Oscillators Produce Proactive Adaptive Behavior

Most artificial neural systems are built to map given inputs to outputs. Adaptive agents face a prior problem: they must act without enough evidence, seek encounters with the world, and revise behavior when evidence appears. We propose another starting point for intelligent neural networks: proactive search without signals, curiosity at its most basic. We ask whether it can come from a minimal untrained circuit. The spiking unit studied here inverts its response to input: with no signal in its window it fires faster; once signals arrive it switches to a slower, inverted regime. Search needs three or more such oscillators in counter-phase, each reading the same input in a different time window. With no training, supervision, parameter tuning, or controller, the composite switches on its own between exploratory spiral search and exploitative tracking, finding both first-degree symmetry and second-degree groups. The switch comes from temporal disagreement between its fast and slow readings of the same signal. We view the circuit as evolutionarily trained: its abilities come from structure, not experience. Ablation over 63 configurations and 63,000 trials shows the switch needs both temporal staggering and counter-phase opposition, neither enough alone: the behavior is emergent, not programmed. The spiral persists at zero rotational diffusion, so it is structural, and degrades gently under perturbation. More oscillators improve spiral regularity but cut resource capture, so the smallest sufficient circuit wins. We propose that this principle underlies search in simple organisms, navigation and decisions in complex ones, and, being so simple and common, goes unnoticed unless you strip the logic bare. Eventually, networks of such proactive primitives may offer another foundation for AI architectures that explore our world rather than merely predict the next symbol in a sequence.

cs.NE↗
arXiv2026

A Confidence-Driven Evolutionary Algorithm for Noisy Optimization with Joint Chance Constraints

Many real-world optimization problems involve noisy objective evaluations and probabilistic constraints, particularly in the form of joint chance constraints, which are computationally expensive to evaluate. In this work, we propose CR-EA-C, a confidence-driven evolutionary algorithm for solving noisy black-box optimization problems under joint chance constraints. CR-EA-C introduces three key components: (1) analytical feasibility estimation for joint chance constraints, (2) a pairwise statistical ranking mechanism for robust comparison under noise, and (3) a modified infeasibility-driven survival strategy to accelerate convergence. These components enable statistically reliable decision-making while improving the efficiency of function evaluations. The proposed method is evaluated against four recent metaheuristic algorithms under various uncertainty distributions. Furthermore, its practical effectiveness is also assessed on two additional real-world optimization problems and compared with conventional static sampling methods. Experimental results show that CR-EA-C consistently satisfies the prescribed joint chance constraints while achieving competitive objective values overall. This demonstrates that CR-EA-C is an effective general-purpose approach for noisy optimization.

cs.NE↗