GitHub PR trajectories extracted by operation-prometheus for SE model training.
🔄 In a Training Loop
Raul Cardenas Montoya
rmems
·
AI & ML interests
Early-career AI/ML experimental systems and Agentic systems
Recent Activity
liked a model about 14 hours ago
Xiaoye08/HRM-Text-0.6B liked a model about 14 hours ago
nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16 liked a model about 15 hours ago
meta-models/Muse-Spark-Open-816B-A42B-NVFP4Organizations
None yet
datasets 68
rmems/agent-trajectory-preference-pairs
Viewer • Updated • 46 • 52
rmems/delegation-planning-trajectories
Viewer • Updated • 7 • 41
rmems/mcp-tool-use-episodes
Viewer • Updated • 17 • 45
rmems/execution-verified-repair-trajectories
Viewer • Updated • 243 • 47
rmems/agent-honest-stop-episodes
Updated • 30
rmems/operation-prometheus-trajectories
Viewer • Updated • 96 • 62
rmems/python-function-repair-20261006
Viewer • Updated • 132 • 153
rmems/oracle-grounded-neuromorphic-20261006
Viewer • Updated • 150 • 109
rmems/observability-debug-trajectories
Viewer • Updated • 2.87k • 243
rmems/llm-eval-flakiness-trajectories
Preview • Updated • 272 • 1