SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and multi-agent evolution. Accepted at COLM 2026.
AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation
Autonomous self-evolving agents. Vision-grounded layered memory and self-written skills for LLM agents that operate your computer.
Yunjue Agent: A Fully Reproducible, Zero-Start In-Situ Self-Evolving Agent System for Open-Ended Tasks
Evolutionary multi-agent runtime that breeds, evaluates, and improves autonomous agents across reproducible epochs to converge on optimization of a goal.
Gradient descent, but the parameters are agents — a parallel, asynchronous framework for self-evolving agents (skills, prompts, harnesses). Diffs are the gradients; the aggregator is the optimizer.
A failure-aware harness for reproducible quantitative-strategy research, with typed agent workflows and inspectable experiment memory.
Group Evolving Agents: Open-Ended Self-Improvement via Experience Sharing
Self-evolution for any agent harness. Plug in. Evolve. Measure.
Awesome list for medical imaging agents: radiology agents, pathology agents, segmentation agents, medical VLM agents, self-evolving agents, benchmarks, datasets, tools, and papers.
PTCG-Bench: Can LLM Agents Master Pokémon Trading Card Game? (EMNLP 2026 Findings)
Curated map of self-evolving LLM agents — 240+ papers across 18 topics incl. recursive self-improvement, harness evolution, misevolution safety, and two runnable demos. Every link machine-checked.
Reference implementation of Double Ratchet: co-evolving an inspectable evaluation metric with a lifecycle-managed skill library for self-improving LLM agents (arXiv:2607.12790)
Reference implementation of Ratchet: a minimal hygiene recipe for self-evolving LLM agents (arXiv:2605.22148)
Evidence-gated Recursive Self-Improvement (RSI) runtime for self-improving LLM agents, self-evolving agents, agentic AI, AI safety, evaluation, lineage, and rollback.
[EMNLP 2026 Main] ST-EVO: Towards Generative Spatio-Temporal Evolution of Multi-Agent Communication Topologies
Collections of recursive self-improvement (RSI): papers where the loop that improves a system also changes the thing doing the improving.
Agent Operating Environment — agents work through workflow hooks where knowledge, tools, and capabilities enter; real work feeds evolution
To associate your repository with the self-evolving-agents topic, visit your repo's landing page and select "manage topics."