FlashEvolve: Accelerating Agent Self-Evolution with Asynchronous Stage Orchestration

Hugging Face Daily Papers Papers

Summary

FlashEvolve is a framework that accelerates LLM-based agent self-evolution by using asynchronous stage orchestration and artifact version tracking. It significantly improves throughput and token efficiency compared to synchronous execution methods.

LLM-based evolution has emerged as a promising way to improve agents by refining non-parametric artifacts, but its wall-clock cost remains a major bottleneck. We identify that this cost comes from synchronized stage execution and imbalance inside each LLM-heavy stage. We present FlashEvolve, an efficient framework that replaces synchronized execution with asynchronous workers and queues, allowing different stages and steps to overlap. To handle data staleness introduced by asynchrony, FlashEvolve tracks artifact versions and applies different policies to update, discard, or patch stale artifacts. Unlike weight-space staleness in asynchronous RL, language-space staleness is inspectable and repairable: a stale artifact is not just delayed work, but readable evidence that the LLM can reflect on, revise, and turn into useful evolution signal. FlashEvolve further improves throughput and token efficiency with speculative stage completion and adaptive workflow control. On GEPA workloads, FlashEvolve improves proposal throughput by 3.5times on local vLLM and 4.9times on API serving over synchronous GEPA. The same design also applies to ACE and Meta-Harness.
Original Article
View Cached Full Text

Cached at: 05/12/26, 07:28 AM

Paper page - FlashEvolve: Accelerating Agent Self-Evolution with Asynchronous Stage Orchestration

Source: https://huggingface.co/papers/2605.08520 Authors:

,

,

,

,

,

,

,

,

,

Abstract

FlashEvolve enhances LLM-based evolution frameworks by implementing asynchronous execution and artifact version tracking to reduce computational bottlenecks while maintaining evolutionary quality.

LLM-based evolutionhas emerged as a promising way to improve agents by refining non-parametric artifacts, but its wall-clock cost remains a major bottleneck. We identify that this cost comes from synchronized stage execution and imbalance inside each LLM-heavy stage. We present FlashEvolve, an efficient framework that replacessynchronized executionwithasynchronous workersand queues, allowing different stages and steps to overlap. To handle data staleness introduced by asynchrony, FlashEvolve tracks artifact versions and applies different policies to update, discard, or patch stale artifacts. Unlike weight-space staleness in asynchronous RL, language-space staleness is inspectable and repairable: a stale artifact is not just delayed work, but readable evidence that the LLM can reflect on, revise, and turn into useful evolution signal. FlashEvolve further improves throughput and token efficiency withspeculative stage completionandadaptive workflow control. OnGEPAworkloads, FlashEvolve improves proposal throughput by 3.5times on localvLLMand 4.9times onAPI servingover synchronousGEPA. The same design also applies to ACE and Meta-Harness.

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2605\.08520

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2605.08520 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.08520 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.08520 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

EvoMap/evolver

GitHub Trending (daily)

Evolver is a GEP-powered self-evolution engine for AI agents that automates prompt optimization and creates auditable, reusable evolution assets. The project is transitioning from fully open source to source-available while maintaining backward compatibility with existing MIT and GPL-3.0 releases.

CoEvolve: Training LLM Agents via Agent-Data Mutual Evolution

arXiv cs.CL

CoEvolve proposes an agent-data mutual evolution framework for training LLM agents through closed-loop, interaction-driven learning that adapts both the agent and its training data distribution. The method extracts feedback signals from rollout trajectories to guide LLM-based task synthesis, demonstrating significant improvements (15-19% absolute gains) across multiple Qwen models on AppWorld and BFCL benchmarks.

Step 3.7 Flash

Product Hunt

Step 3.7 Flash is a fast agents model designed to see and act in real time.

MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery

Hugging Face Daily Papers

MLEvolve is a self-evolving LLM-based multi-agent framework for automated ML algorithm discovery that extends tree search to Progressive MCGS with graph-based cross-branch information flow and retrospective memory. It achieves state-of-the-art performance on MLE-Bench and outperforms AlphaEvolve on mathematical algorithm optimization tasks.