#swebench

0 stories this week · 0 this month · 3 in 6 months · mostly AI

Stories per day · 30 days

3 stories, newest first · one card per story

Audit of 254 SWE-bench submissions finds top coding-agent entries statistically inseparable, so small leaderboard gaps no longer establish rank.

ExecCritic separates test generation from patching for coding agents, lifting SWE-bench Verified resolution to 72.6%.

Paper models multi-agent LLM orchestration as a bilevel game, proving transcript-only gating limits and introducing grounded-memory SRMA.

Stories tagged #swebench