AVO: Agentic Variation Operators for Autonomous Evolutionary Search

• URL: http://arxiv.org/abs/2603.24517v1
• Date: Wed, 25 Mar 2026 16:55:04 GMT
• Title: AVO: Agentic Variation Operators for Autonomous Evolutionary Search
• Abstract summary: Agentic Variation Operators (AVO) are evolutionary variation operators that replace the fixed mutation, crossover, and hand-designeds of classical evolutionary search.<n>We evaluate AVO on attention, among the most aggressively optimized kernel targets in AI, on NVIDIA Blackwell (B200)<n>AVO instantiates variation as a self-directed agent loop that can consult the current lineage, a domain-specific knowledge base, and execution feedback.
• Score: 38.64857334672555
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Agentic Variation Operators (AVO) are a new family of evolutionary variation operators that replace the fixed mutation, crossover, and hand-designed heuristics of classical evolutionary search with autonomous coding agents. Rather than confining a language model to candidate generation within a prescribed pipeline, AVO instantiates variation as a self-directed agent loop that can consult the current lineage, a domain-specific knowledge base, and execution feedback to propose, repair, critique, and verify implementation edits. We evaluate AVO on attention, among the most aggressively optimized kernel targets in AI, on NVIDIA Blackwell (B200) GPUs. Over 7 days of continuous autonomous evolution on multi-head attention, AVO discovers kernels that outperform cuDNN by up to 3.5% and FlashAttention-4 by up to 10.5% across the evaluated configurations. The discovered optimizations transfer readily to grouped-query attention, requiring only 30 minutes of additional autonomous adaptation and yielding gains of up to 7.0% over cuDNN and 9.3% over FlashAttention-4. Together, these results show that agentic variation operators move beyond prior LLM-in-the-loop evolutionary pipelines by elevating the agent from candidate generator to variation operator, and can discover performance-critical micro-architectural optimizations that produce kernels surpassing state-of-the-art expert-engineered attention implementations on today's most advanced GPU hardware.

Related papers

• AgenticCANN: Automated Ascend C Operator Generation via Knowledge-Augmented Agentic Evolution [16.709206818546317]
  AgenticCANN is a knowledge-augmented agentic evolution framework specifically tailored for automated Ascend C operator synthesis in low-corpus NPU environments.<n>Our method achieves 90 to 100 percent feasibility on elementwise and normalization operators, 56% on fusion operators, and up to 6.65$times$ speedup on 1B Pangu model inference kernels.
  arXiv  Detail & Related papers  (2026-07-29T09:19:17Z)
• CurateEvo: Data-Curation Evolving for Agentic Post-Training [53.68149869349268]
  We propose CurateEvo, a failure-driven dynamic evolution framework for agentic post-training data curation.<n>CurateEvo represents the curation strategy as executable code and iteratively rewrites it using failed trajectories from a held-out development set.<n>At each epoch, the evolved strategy transforms a fixed raw corpus into supervised fine-tuning data, reinforcement learning data, and an inference-time memory bank.
  arXiv  Detail & Related papers  (2026-07-07T11:07:00Z)
• NOVA: A Verification-Aware Agent Harness for Architecture Evolution in Industrial Recommender Systems [24.27056236910489]
  NOVA is a level-aware agent harness for verification-aware architecture evolution.<n>It achieves the highest effective pass rate on L2 ScaleUp and L3 Literature-to-Production tasks.<n>It shortens one literature-to-production cycle by over 13x in human-attended time.
  arXiv  Detail & Related papers  (2026-06-25T16:30:39Z)
• Perception, Verdict, and Evolution: Hindsight-Driven Self-Refining Forensics Agent for AI-Generated Image Detection [80.15317858033534]
  ForeAgent is an agentic forensics framework for AI-generated image detection with iterative self-evolution.<n>ForeAgent achieves state-of-the-art performance on the Chameleon benchmark, reaching 82.18% accuracy.<n>ForeAgent produces more consistent and causally grounded reasoning compared to GPT-5 and GPT-5-mini.
  arXiv  Detail & Related papers  (2026-06-25T02:59:33Z)
• APEX: Adaptive Principle EXtraction A Three-Layer Self-Evolution Framework for Production AI Agents [0.0]
  Self-improvement in AI agents has emerged as a key research frontier.<n>We propose APEX, a three-layer co-evolution framework that simultaneously evolves.<n>Our results demonstrate that multi-dimensional co-evolution substantially outperforms single-axis harness optimisation.
  arXiv  Detail & Related papers  (2026-06-13T15:47:27Z)
• EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments [100.23277774720928]
  EvoArena is a benchmark suite that models environment changes as sequences of progressive updates across terminal, software, and social domains.<n>EvoMem is a patch-based memory paradigm that records memory evolution as structured update histories.
  arXiv  Detail & Related papers  (2026-06-11T17:59:59Z)
• AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation [59.964989458924585]
  AdaExplore is an agent framework that enables self-improvement via accumulated execution feedback for performance-critical kernel code generation.<n>In the adaptation stage, the agent synthesizes tasks and converts recurring failures into a reusable memory of validity rules.<n>In the search stage, the agent organizes candidate kernels as a tree and alternates between small local refinements and larger structural regeneration.
  arXiv  Detail & Related papers  (2026-04-17T18:25:03Z)
• EvoClaw: Evaluating AI Agents on Continuous Software Evolution [47.49468375065129]
  We introduce DeepCommit, an agentic pipeline that reconstructs verifiable Milestone DAGs from noisy commit logs.<n>These executable sequences enable EvoClaw, a novel benchmark that requires agents to sustain system integrity and limit error accumulation.
  arXiv  Detail & Related papers  (2026-03-13T03:20:40Z)
• AdaptEvolve: Improving Efficiency of Evolutionary AI Agents through Adaptive Model Selection [14.17960333915609]
  Evolutionary agentic systems intensify the trade-off between computational efficiency and reasoning capability.<n>We introduce AdaptEvolve: Adaptive Selection for Multi-LLM Evolutionary Refinement.
  arXiv  Detail & Related papers  (2026-02-12T13:26:56Z)
• Group-Evolving Agents: Open-Ended Self-Improvement via Experience Sharing [26.102738613616456]
  Group-Evolving Agents (GEA) treats a group of agents as the fundamental evolutionary unit.<n>We evaluate GEA on challenging coding benchmarks, where it significantly outperforms state-of-the-art self-evolving methods.
  arXiv  Detail & Related papers  (2026-02-04T18:29:36Z)
• Hypernetworks That Evolve Themselves [3.4524024382493774]
  We propose Self-Referential Graph HyperNetworks, systems where variation and inheritance is embedded in the network.<n>By uniting hypernetworks, parameter generation, and graph-based representations, Self-Referential GHNs mutate and evaluate themselves while adapting selectable traits.<n>Our findings support the idea that evolvability itself can emerge from neural self-reference.
  arXiv  Detail & Related papers  (2025-12-18T11:05:34Z)
• LLM4EO: Large Language Model for Evolutionary Optimization in Flexible Job Shop Scheduling [4.782301990330074]
  This work leverages Large Language Models (LLMs) to perceive evolutionary dynamics and enable operator-level meta-evolution.<n>The proposed framework, LLM4EO, comprises three components: knowledge-transfer-based operator design, evolution perception and analysis, and adaptive operator evolution.
  arXiv  Detail & Related papers  (2025-11-20T15:56:09Z)
• From Agentification to Self-Evolving Agentic AI for Wireless Networks: Concepts, Approaches, and Future Research Directions [70.72279728350763]
  Self-evolving agentic artificial intelligence (AI) offers a new paradigm for future wireless systems.<n>Unlike static AI models, self-evolving agents embed an autonomous evolution cycle that updates models, tools, and in response to environmental dynamics.<n>This paper presents a comprehensive overview of self-evolving agentic AI, highlighting its layered architecture, life cycle, and key techniques.
  arXiv  Detail & Related papers  (2025-10-07T05:45:25Z)
• SEEA-R1: Tree-Structured Reinforcement Fine-Tuning for Self-Evolving Embodied Agents [58.174206358223415]
  Self-Evolving Embodied Agents-R1, or SEEA-R1, is the first reinforcement fine-tuning framework designed for self-evolving embodied agents.<n>We show that SEEA-R1 can support autonomous adaptation and reward-driven self-evolution.
  arXiv  Detail & Related papers  (2025-06-26T18:00:07Z)
• Trackable Agent-based Evolution Models at Wafer Scale [0.0]
  We focus on the problem of extracting phylogenetic information from agent-based evolution on the 850,000 processor Cerebras Wafer Scale Engine (WSE) We present an asynchronous island-based genetic algorithm (GA) framework for WSE hardware. We validate phylogenetic reconstructions from these trials and demonstrate their suitability for inference of underlying evolutionary conditions.
  arXiv  Detail & Related papers  (2024-04-16T19:24:14Z)
• Investigate-Consolidate-Exploit: A General Strategy for Inter-Task Agent Self-Evolution [92.84441068115517]
  Investigate-Consolidate-Exploit (ICE) is a novel strategy for enhancing the adaptability and flexibility of AI agents. ICE promotes the transfer of knowledge between tasks for genuine self-evolution. Our experiments on the XAgent framework demonstrate ICE's effectiveness, reducing API calls by as much as 80%.
  arXiv  Detail & Related papers  (2024-01-25T07:47:49Z)
• Involution: Inverting the Inherence of Convolution for Visual Recognition [72.88582255910835]
  We present a novel atomic operation for deep neural networks by inverting the principles of convolution, coined as involution. The proposed involution operator could be leveraged as fundamental bricks to build the new generation of neural networks for visual recognition. Our involution-based models improve the performance of convolutional baselines using ResNet-50 by up to 1.6% top-1 accuracy, 2.5% and 2.4% bounding box AP, and 4.7% mean IoU absolutely.
  arXiv  Detail & Related papers  (2021-03-10T18:40:46Z)

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.