Research & knowledge
weco.ai
How to improve a research agent
Weco used an autonomous outer research loop to rewrite and evaluate an inner agent harness, reporting seven improvements and testing selected versions on held-out tasks.
Added AIDE²AIDE² ran an outer research loop that rewrote and evaluated an inner research agent, with the source reporting seven improvements over 100 iterations.
Maker: Not stated
See sourced use cases for reported tasks.
Weco used an autonomous outer research loop to rewrite and evaluate an inner agent harness, reporting seven improvements and testing selected versions on held-out tasks.
Added AIDE²