repoGitHubTrust 82 · PrimaryPublished 4d agoLive · 4d ago
Prism-Shadow/GDPevo
A Benchmark for Evaluating Agent Self-Evolution on Real Business Tasks
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Implements
paperMetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill EvolutionpaperSelf-Evolving World Models for LLM Agent PlanningpaperEvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive EnvironmentspaperTestEvo-Bench: An Executable and Live Benchmark for Test and Code Co-Evolution
Covers
Related across the graph
paperMetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill EvolutionpaperSelf-Evolving World Models for LLM Agent PlanningnewsThe real cost, security, and culture problems behind enterprise AI agentsnewsNVIDIA Brings Trusted, 24/7 AI Agents to Telecom OperationspaperEvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive EnvironmentspaperTestEvo-Bench: An Executable and Live Benchmark for Test and Code Co-Evolution
