Local Multi-Agent SWE-RL Collection Shared-policy local bug-injection and repair self-play; preregistered bounded pilot and held-out evaluations. • 1 item • Updated about 8 hours ago
BurnyCoder/multi-agent-swe-rl-qwen3.5-2b-pilot Reinforcement Learning • Updated about 8 hours ago • 2
BurnyCoder/multi-agent-swe-rl-qwen3.5-2b-pilot Reinforcement Learning • Updated about 8 hours ago • 2
PCam hill-climbing of Hibou-L Collection Pre-registered hill-climbing of Hibou-L on PatchCamelyon: heads, adapters, results. • 1 item • Updated 5 days ago