Self-Evolving Coding Agents

Hugging Face Daily Papers Papers
survey coding-agents self-evolving software-engineering llm-agents arxiv

Summary

This paper surveys self-evolving coding agents, which improve their future behavior by updating frameworks, memory, skills, tools, or models from prior coding interactions, and presents a taxonomy of what evolves, when, and what software-specific evidence drives it.

Large language models are increasingly embedded in software engineering workflows as coding agents that can inspect repositories, invoke tools, execute tests, debug failures, and generate patches. Yet most existing agents remain largely static after deployment, even though software development is a dynamic, feedback-rich process in which repositories evolve, dependencies change, tests fail, and repair attempts leave reusable experience. This tension has motivated a growing body of work on self-evolving coding agents, where the agent improves its future behavior by updating its framework, memory, skills, tools, models, or collaboration structures from prior coding interactions. In this survey, we provide a systematic synthesis of this emerging area. We first define self-evolving coding agents and distinguish them from conventional coding agents and general self-evolving agents. We then develop an object-centered taxonomy that characterizes what evolves in these systems, and complement it with two orthogonal perspectives: when evolution occurs and what software-specific evidence drives it. Across the literature, we find that executable feedback, repository-level context, and coding trajectories give software engineering a distinctive role as a natural domain for agent self-evolution, but also introduce new challenges in feedback reliability, benchmark overfitting, safety, maintainability, cost, and generalization. By organizing existing work around these dimensions, this survey aims to clarify the conceptual boundaries of self-evolving coding agents and provide a foundation for designing more adaptive, reliable, and software-aware agentic systems. The papers we collect can be found at https://github.com/zhouhao1024/Awesome-Self-Evolving-Coding-Agents.
Original Article
View Cached Full Text

Cached at: 08/06/26, 09:50 AM

Paper page - Self-Evolving Coding Agents

Source: https://huggingface.co/papers/2608.03392

Abstract

Largelanguagemodelsareincreasinglyembeddedinsoftwareengineeringworkflowsascodingagentsthatcaninspectrepositories,invoketools,executetests,debugfailures,andgeneratepatches.Yetmostexistingagentsremainlargelystaticafterdeployment,eventhoughsoftwaredevelopmentisadynamic,feedback-richprocessinwhichrepositoriesevolve,dependencieschange,testsfail,andrepairattemptsleavereusableexperience.Thistensionhasmotivatedagrowingbodyofworkonself-evolvingcodingagents,wheretheagentimprovesitsfuturebehaviorbyupdatingitsframework,memory,skills,tools,models,orcollaborationstructuresfrompriorcodinginteractions.Inthissurvey,weprovideasystematicsynthesisofthisemergingarea.Wefirstdefineself-evolvingcodingagentsanddistinguishthemfromconventionalcodingagentsandgeneralself-evolvingagents.Wethendevelopanobject-centeredtaxonomythatcharacterizeswhatevolvesinthesesystems,andcomplementitwithtwoorthogonalperspectives:whenevolutionoccursandwhatsoftware-specificevidencedrivesit.Acrosstheliterature,wefindthatexecutablefeedback,repository-levelcontext,andcodingtrajectoriesgivesoftwareengineeringadistinctiveroleasanaturaldomainforagentself-evolution,butalsointroducenewchallengesinfeedbackreliability,benchmarkoverfitting,safety,maintainability,cost,andgeneralization.Byorganizingexistingworkaroundthesedimensions,thissurveyaimstoclarifytheconceptualboundariesofself-evolvingcodingagentsandprovideafoundationfordesigningmoreadaptive,reliable,andsoftware-awareagenticsystems.Thepaperswecollectcanbefoundathttps://github.com/zhouhao1024/Awesome-Self-Evolving-Coding-Agents.

View arXiv pageView PDFGitHub7Add to collection

Get this paper in your agent:

hf papers read 2608\.03392

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/2608.03392 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.03392 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.03392 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

A Taxonomy of Self-evolving Agents (15 minute read)

TLDR AI

Shilong Liu proposes a taxonomy classifying self-evolving agents into artifact optimization, harness self-improvement, and model learning, providing a common language for emerging agent research.

@qinzytech: https://x.com/qinzytech/status/2066585405479371092

X AI KOLs Timeline

A technical analysis of two approaches to building self-evolving AI agents: model-based (via architecture like SSMs or transformer with fast-weight updates, and training methods) and harness-based (via memory or meta harness that can rewrite itself). The author provides practical recommendations for different audiences.