diff --git a/evalharness/config/thinking.yaml b/evalharness/config/thinking.yaml index 1a001fe..76d958b 100644 --- a/evalharness/config/thinking.yaml +++ b/evalharness/config/thinking.yaml @@ -58,3 +58,9 @@ general_fc: max_tokens: 4096 tau2_bench: max_tokens: 16384 + +swe_bench_verified_agentic: + max_tokens: 4096 + temperature: 0.0 + env: swe_agentic + max_turns: 250