repoGitHubTrust 82 · PrimaryPublished 1mo agoLive · 1mo ago
Shiyao-Huang/awesome-agent-evolution
Open survey and evidence map for AI agent evolution, self-evolving agents, memory, skills, harnesses, benchmarks, and agent-swarm systems.
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 57%A field guide to AI agents in 2026 →
- PossiblePossibly related (embedding) · 56%LangChain Engineer Introduces Harbor for Complex AI Agent Evaluation - TechGig →
- PossiblePossibly related (embedding) · 52%I made a superhuman Generals.io agent with self-play RL [P] →
- PossiblePossibly related (embedding) · 52%Agentic AI for Robot Teams →
- PossiblePossibly related (embedding) · 51%A study found that artificial intelligence (AI) agents who perform smartly complex tasks use up to 1.. - 매일경제 →
- PossiblePossibly related (embedding) · 56%Who Grades the Grader? Co-Evolving Evaluation Metrics and Skills for Self-Improving LLM Agents →
- PossiblePossibly related (embedding) · 51%Unveiling Complex Collective Behaviors from Simple Rewards →
- PossiblePossibly related (embedding) · 57%Jadepuffer: Agentic attack evolves to destroy AI models - Computing UK →
Related to
Covers
Covers (incoming)
Implements (incoming)
Related across the graph
newsLangChain Engineer Introduces Harbor for Complex AI Agent Evaluation - TechGigpaperUnveiling Complex Collective Behaviors from Simple RewardspaperWho Grades the Grader? Co-Evolving Evaluation Metrics and Skills for Self-Improving LLM AgentsnewsAgentic AI for Robot TeamsnewsI made a superhuman Generals.io agent with self-play RL [P]articleA field guide to AI agents in 2026newsA study found that artificial intelligence (AI) agents who perform smartly complex tasks use up to 1.. - 매일경제newsJadepuffer: Agentic attack evolves to destroy AI models - Computing UK