GEAR Open-Sources Modular RSI Framework for Self-Improving Agents

1 reports archived1 independent sourcesupdated 11/11/2026, 12:12:00

Synthesis & Latest Updates

1 Sources Cross-Validated

Researchers from Imperial College London, Duke and other institutions have released GEAR, an open-source modular toolkit for recursive self-improvement (RSI) of LLM agents, styled after Scikit-learn. It decomposes parent selection, mutation planning, task sampling, scoring and candidate ranking into swappable modules while sharing execution, evaluation and versioning infrastructure. Experiments built on the GEPA algorithm show notable gains on marketing, customer service and coding tasks with frozen model weights.

LATEST/Researchers from Imperial College London, Duke and other institutions have released GEAR, an open-source modular toolkit for recursive self-improvement (RSI) of LLM agents, styled after Scikit-learn. It decomposes parent selection, mutation planning, task sampling, scoring and candidate ranking into swappable modules while sharing execution, evaluation and versioning infrastructure. Experiments built on the GEPA algorithm show notable gains on marketing, customer service and coding tasks with frozen model weights.

Hourly heat curve

5 fully observed hours

Now

8.6

Peak

9.622:00

24h change

–

The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.

Coverage timeline

Total 1 reports · Latest first

机器之心 (微信公众号)T2Nov 11, 12:12·72 pts
GEAR Open-Sources Modular RSI Framework for Self-Improving Agents
- GEAR decomposes RSI into swappable modules for rapid construction, comparison and reuse of evolution strategies
- Shared infrastructure records candidate code versions, run conditions and evaluation evidence for reproducibility
- Validation targets harness evolution, mutating prompts, tools, skills and workflows while freezing model weights
View Related Reports & Analysis Original Source