GitHub - google-research/harness2
2026-10-31
![]()
Harness² is Google Research's framework for improving an agent's harness, its prompts, memory, tool guidance and skills, while the model's weights stay fixed. It recurses at two levels: for each task it proposes harness edits, probes them and composes the ones that help, with no ground-truth answers needed, and across tasks it carries the lessons forward. On three professional benchmarks it reports gains of up to 11.5 points on WorkBuddy-Bench and 11.8 points on LAB's partial pass rate. It is one more entry in the Harness Wars, which feel to me a lot like the Browser Wars of 20 or 25 years ago.
Was this useful?