FeiZhuNiU-INFJA/LIFT

Agent self-evolution evaluation — not static snapshots, but longitudinal growth curves. Measures transfer efficiency, error avoidance, and skill-hit quality through controlled experiments with and without evolution.

Self-evolution for any agent harness. Plug in. Evolve. Measure.

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 simple, feasible repository to reproduce and learn self-evolving/recursive self-improvement agent.

The official repository of "Position: Agentic Evolution is the Path to Evolving LLMs".

Open survey and evidence map for AI agent evolution, self-evolving agents, memory, skills, harnesses, benchmarks, and agent-swarm systems.

🐕 Beagle is designed to be the unified platform for the broader Recursive Self-Improvement (RSI) ecosystem. Think of it as Hugging Face Trainer for agent evolution. Its efficient rollout engine enables evaluation and evolution at scale across different agents, datasets, benchmarks, and evolution methods.

Open-World Self-Evolution for LLM Agents — agents that build both their skills and their own verification signals from scratch, with no target-task supervision. (Code coming soon.)

A Benchmark for Evaluating Agent Self-Evolution on Real Business Tasks