1Show HN: Cua-Bench – a benchmark for AI agents in GUI environments (opens in new tab)(github.com)40someguy1010101mo ago8
2Solve Hi-Q with AlphaZero and Curriculum Learning (opens in new tab)(robw.fyi)1someguy1010102mo ago0
3Simple Control Flow for Automatically Steering Agents (opens in new tab)(robw.fyi)1someguy1010105mo ago0
4Constraint satisfaction to optimize item selection for bundles in Minecraft (opens in new tab)(robw.fyi)41someguy1010105mo ago11
5Show HN: An Agent That Resolves Merge Conflicts Automatically (opens in new tab)(github.com)3someguy10101010mo ago2