tencent/ContextPilot-14B
Text Generation • 15B • Updated • 859 • 23
Self-improvement
-
-
FINAL-Bench/Darwin-180B-RSI
Image-Text-to-Text • 180B • Updated • 1.14k • 126 -
FINAL-Bench/Darwin-180B-RSI-R3
Image-Text-to-Text • 180B • Updated • 522 • 21 -
FINAL-Bench/POCKET-Darwin-180B-GGUF
Text Generation • 177B • Updated • 167k • 64 -
FINAL-Bench/Darwin-27B-RSI
Text Generation • 27B • Updated • 1.52k • 35 -
ValiantLabs/gpt-oss-20b-ShiningValiant3
Text Generation • 21B • Updated • 114 • 20 -
sequelbox/Celestia3-DeepSeek-R1-0528
Viewer • Updated • 91k • 511 • 37 -
sequelbox/Mitakihara-DeepSeek-R1-0528
Viewer • Updated • 16.9k • 79 • 6 -
sequelbox/Raiden-DeepSeek-R1
Viewer • Updated • 62.9k • 556 • 53 -
ValiantLabs/Ministral-3-14B-Reasoning-2512-ShiningValiant3
Text Generation • 14B • Updated • 45 • 5 -
ValiantLabs/Qwen3.6-27B-Esper4
Image-Text-to-Text • 28B • Updated • 145 • 22 -
ValiantLabs/Qwen3.5-27B-Esper3.1
Image-Text-to-Text • 28B • Updated • 98 • 15 -
ValiantLabs/Qwen3-14B-Cobalt2
Text Generation • 15B • Updated • 33 • • 3 -
RSI-Exam/RSI-Exam
Updated • 7.86k • 7 -
CosmosMind/RSI-Harness
Updated • 6 -
dayll/SEAD-14B
Text Generation • 15B • Updated • 28 • 3 -
SEAD: Self-Evolving Agent for Multi-Turn Service Dialogue
Paper • 2602.03548 • Published • 4 -
togethercomputer/Llama-3.1-8B-Instruct-MoAA-DPO
Text Generation • 8B • Updated • 84 • 1 -
Prime Agent: A Self-Improving RLM Harness
Paper • 2608.23552 • Published • 57 -
Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks
Paper • 2610.11794 • Published • 47 -
REMORY: Learning Residual Memory for Context Compaction
Paper • 2610.11287 • Published • 164