GAE: Graph-Augmented Evolution for Scientific Discovery via Reinforcement Optimization

• URL: http://arxiv.org/abs/2607.10127v1
• Date: Sat, 11 Jul 2026 05:32:54 GMT
• Title: GAE: Graph-Augmented Evolution for Scientific Discovery via Reinforcement Optimization
• Abstract summary: We present GAE (Graph-Augmented Evolution), a framework for program search guided by Large Language Models (LLMs)<n>We use a relational graph neural network (GNN) to parse programs into typed computation graphs, producing structure-aware embeddings.<n>An RL-optimized meta-controller leverages these embeddings to replace blind evolutionary sampling with a directed policy.
• Score: 1.7188280334580195
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Evolutionary program search guided by Large Language Models (LLMs) has emerged as a powerful paradigm for automated scientific discovery. However, current approaches are fundamentally constrained by three bottlenecks: structurally blind parent selection, sparse whole-program evaluation rewards, and static mutation operators that fail to adapt during search. We present GAE (Graph-Augmented Evolution), a framework that resolves these limitations through a tightly coupled, three-pillar architecture. First, a relational graph neural network (GNN) parses programs into typed computation graphs, producing structure-aware embeddings. Second, an RL-optimized meta-controller leverages these embeddings to replace blind evolutionary sampling with a directed policy, dynamically selecting optimal parents and mutation directions based on reward history. Third, an online GRPO fine-tuning loop continuously updates the LLM mutation operator at test-time using group-normalized evaluation rewards, directly aligning the model's generation distribution with high-fitness structural edits. We evaluate GAE on a challenging scientific discovery task: symbolic regression for complex nonlinear oscillator systems. By transforming stochastic search into a directed, self-improving trajectory, GAE efficiently discovers closed-form physical equations, consistently matching or outperforming static LLM-driven baselines and achieving state-of-the-art out-of-distribution performance.

Related papers

• Temporal Memory-Aware Online Test-Time Adaptation on Dynamic Graphs [52.31268996286955]
  Test-time adaptation (TTA) on graphs aims to adapt a graph neural network (GNN) that is well-trained on the training graph to the test graph.<n>We propose a novel framework of temporal memory-aware Online Test-Time Adaptation on Dynamic Graphs, named DGOTTA, to effectively adapt well-trained DGNNs during test time.
  arXiv  Detail & Related papers  (2026-08-28T05:41:39Z)
• EvoOptiGraph: Weakness-Driven Coevolution via Graph-Based Structural Generation for Optimization Modeling [19.76518386029908]
  EvoOptiGraph is a framework where data and model co-evolve, driven by model weaknesses.<n>Training proceeds in two stages: supervised fine-tuning (SFT) on an initial dataset, followed by reinforcement learning with verifiable rewards (RLVR)<n>Results show that EvoOptiGraph significantly outperforms larger generalist models, agentic methods, and specialized baselines in accuracy, executability, and generalization.
  arXiv  Detail & Related papers  (2026-06-25T03:57:07Z)
• Graph Neural Networks for Fast Operator Selection in Adaptive VQE [0.0]
  We introduce a graph neural network (GNN) policy that predicts the next entangling operator directly from the interaction graph and state-dependent observables.<n>The learned policy accurately reproduces the dominant structure of the greedy gradient-based selection rule.<n> integrated into a variational quantum eigensolver (VQE) workflow, this GNN-VQE approach achieves energy errors close to standard ADAPT-VQE.
  arXiv  Detail & Related papers  (2026-06-07T19:18:47Z)
• CliffSearch: Structured Agentic Co-Evolution over Theory and Code for Scientific Algorithm Discovery [8.600891931062277]
  We present CliffSearch, an agentic evolutionary framework in which the core evolution operators are implemented as LLM agents.<n>We illustrate the framework on three benchmark-grounded studies: transformer hyper-connection evolution, discovery on a fixed nanoGPT stack, and a smaller native-optimizer ablation.
  arXiv  Detail & Related papers  (2026-04-01T17:51:26Z)
• AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization [61.535567824938205]
  We introduce AdaEvolve, a framework that reformulates LLM-driven evolution as a hierarchical adaptive optimization problem.<n>AdaEvolve consistently outperforms the open-ended baselines across 185 different open-ended optimization problems.
  arXiv  Detail & Related papers  (2026-02-23T18:45:31Z)
• Evolutionary Router Feature Generation for Zero-Shot Graph Anomaly Detection with Mixture-of-Experts [60.60414602796664]
  We propose a novel MoE framework with evolutionary router feature generation (EvoFG) for zero-shot GAD.<n>EvoFG consistently outperforms state-of-the-art baselines, achieving strong and stable zero-shot GAD performance.
  arXiv  Detail & Related papers  (2026-02-12T06:16:51Z)
• Large Language Model-Powered Evolutionary Code Optimization on a Phylogenetic Tree [17.08113692977552]
  PhyloEvolve is a system that reframes GPU-oriented algorithm optimization as an In-Context Reinforcement Learning problem.<n>We introduce a phylogenetic tree representation that captures inheritance, divergence, and recombination among algorithm variants.<n>We evaluate PhyloEvolve on scientific computing workloads including PDE solvers, manifold learning, and spectral graph algorithms.
  arXiv  Detail & Related papers  (2026-01-20T22:32:52Z)
• Predict the Retrieval! Test time adaptation for Retrieval Augmented Generation [66.36556189794526]
  TTARAG is a test-time adaptation method that dynamically updates the language model's parameters during inference to improve RAG system performance in specialized domains.<n>Our method introduces a simple yet effective approach where the model learns to predict retrieved content, enabling automatic parameter adjustment to the target domain.
  arXiv  Detail & Related papers  (2026-01-16T17:07:01Z)
• Think-on-Graph 3.0: Efficient and Adaptive LLM Reasoning on Heterogeneous Graphs via Multi-Agent Dual-Evolving Context Retrieval [35.65907480060404]
  Think-on-Graph 3.0 (ToG-3) is a novel framework that introduces Multi-Agent Context Evolution and Retrieval (MACER) mechanism to overcome limitations.<n>Our core innovation is the dynamic construction and refinement of a Chunk-Triplets-Community heterogeneous graph index.<n>A multi-agent system engages in an iterative process of evidence retrieval, answer generation, sufficiency, and, crucially, evolving query and subgraph.
  arXiv  Detail & Related papers  (2025-09-26T00:13:10Z)
• Pre-trained Graphformer-based Ranking at Web-scale Search (Extended Abstract) [56.55728466130238]
  We introduce the novel MPGraf model, which aims to integrate the regression capabilities of Transformers with the link prediction strengths of GNNs. We conduct extensive offline and online experiments to rigorously evaluate the performance of MPGraf.
  arXiv  Detail & Related papers  (2024-09-25T03:33:47Z)
• End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes [52.818579746354665]
  This paper proposes the first end-to-end differentiable meta-BO framework that generalises neural processes to learn acquisition functions via transformer architectures. We enable this end-to-end framework with reinforcement learning (RL) to tackle the lack of labelled acquisition data.
  arXiv  Detail & Related papers  (2023-05-25T10:58:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.