LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks (github.com) 1 points by tingletech 2mo ago ↗ HN
[–] deadcatfound 2mo ago ↗ Long horizon agents need checkpoints and recovery more than bigger context windows. I’d score safe resume after tool failure, not just task completion.
1 comment
[ 3.3 ms ] story [ 18.2 ms ] thread