# ANative-Lab/Awesome-Self-Evolving-Agents

[Survey] A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

Repository: https://github.com/ANative-Lab/Awesome-Self-Evolving-Agents
Canonical: https://ross.abutalabs.com/products/awesome-self-evolving-agents
Homepage: https://arxiv.org/abs/2508.07407
License: MIT
License Family: permissive
Topics: agent, agentic-ai, ai, llms, multi-agent-systems, natural-language-processing, self-evolving
Last push: 2026-05-16T14:49:18+00:00

## Health v2 (maintenance only)
Score: 56/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 82, release rhythm 35, longevity 34
- inputs: {"age_days": 482, "days_push": 109, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2458, forks 187 (observed 2026-08-28T04:06:53.358442+00:00)

## What it is
A curated awesome-list accompanying an arXiv survey on self-evolving AI agents, cataloguing papers and open-source frameworks for agent optimisation. It organises research into single-agent, multi-agent, and domain-specific evolution techniques bridging foundation models and lifelong agentic systems.

## Use cases
- find research papers on self-evolving AI agents
- learn how LLM agents can improve after deployment
- survey techniques for lifelong agentic systems
- find open-source frameworks for evolving agentic workflows
- research multi-agent optimisation methods
- study agent adaptation from environmental feedback

## When to choose
- you need a curated reading list on agent evolution and optimisation
- you are writing a literature review on self-improving LLM agents
- you want links to papers and codebases for agent training techniques

## When to avoid
- you need a runnable agent framework rather than a paper collection
- you want production-ready agent tooling
- you need non-agent machine learning resources

## Facets
- artifact type: learning-resource
- maturity: active
- function: agent-framework, llm-training, machine-learning
- domain: artificial-intelligence, large-language-models, awesome-lists, tutorials
- platform: cross-platform
- tags: awesome-list, survey, self-evolving-agents, lifelong-learning, multi-agent-systems, research-paper, ai-agents

## Member repositories
- ANative-Lab/Awesome-Self-Evolving-Agents (main) score 56

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:53.358442+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:29:21.980945+00:00, confidence not recorded.
  - readme: https://github.com/ANative-Lab/Awesome-Self-Evolving-Agents (fetched 2026-08-28T04:06:53.358442+00:00, sha 0be7d7abeb2a)
  - homepage: https://arxiv.org/abs/2508.07407 (fetched 2026-08-29T10:11:30.416581+00:00, sha 14fb7dd2866e)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T10:11:30.425730+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T10:11:30.429162+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T10:11:30.430975+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T10:11:30.427443+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.