Awesome-Self-Improving-Agents vs Awesome-Self-Evolving-Agents
Curated research guides to agents that improve or evolve
Awesome-Self-Improving-Agents and Awesome-Self-Evolving-Agents are curated research indexes for exploring how AI agents change over time. The first emphasizes improvements to foundation models and agent scaffolds, while the second organizes research around model evolution, environment evolution, and their co-evolution.
Awesome-Self-Improving-Agents: Explore Self-Improving Agent Research
A curated research hub for self-improving foundation-model agents, organized around model and agent-scaffold improvements. Researchers and practitioners can use it to find papers, benchmarks, and related resources by topic.
Awesome-Self-Evolving-Agents: Explore Research on Evolving Agents
A curated research index and survey companion covering self-evolving AI agents. It organizes papers, benchmarks, libraries, and applications for researchers and practitioners exploring how agents improve through model, environment, and combined evolution.
| Awesome-Self-Improving-Agents | Awesome-Self-Evolving-Agents | |
|---|---|---|
| Language | TeX | — |
| License | MIT | — |
| Stars | 525 | 463 |
| Forks | 54 | 38 |
| Last analyzed | Oct 4, 2026 | Oct 3, 2026 |
Key differences
- Awesome-Self-Improving-Agents separates foundation-model improvements from scaffold changes such as prompts, memory, tools, and workflows; Awesome-Self-Evolving-Agents groups work into model-centric, environment-centric, and model-environment co-evolution.
- Awesome-Self-Improving-Agents highlights self-generated demonstrations, evaluative feedback, and exploratory experience; Awesome-Self-Evolving-Agents also catalogs themes such as self-correction, online learning, skills, and agent architecture.
- Awesome-Self-Improving-Agents covers evaluation approaches and related learning materials such as blogs, podcasts, videos, and courses; Awesome-Self-Evolving-Agents catalogs benchmarks, libraries, infrastructure, and applications.
- Awesome-Self-Improving-Agents is listed as using TeX and having an MIT license; Awesome-Self-Evolving-Agents lists libraries and infrastructure but does not provide language or license details here.
- Awesome-Self-Improving-Agents has 525 stars and 54 forks, compared with 463 stars and 38 forks for Awesome-Self-Evolving-Agents.
Choose Awesome-Self-Improving-Agents if you…
- need a taxonomy focused on foundation-model and agent-scaffold improvements.
- want a survey companion with categorized papers, evaluation approaches, and learning resources.
- are comparing examples of prompt, memory, tool, and workflow changes.
Choose Awesome-Self-Evolving-Agents if you…
- need a map spanning model evolution, environment evolution, and their co-evolution.
- want to browse benchmarks, agent libraries, infrastructure, and application examples alongside papers.
- are exploring research themes such as online learning, self-correction, and agent skills.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.