S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?
Paper • 2608.31100 • Published • 38
👋 Open to Work
Zehao Jin
Lunamos
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 2 days ago
S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement? upvoted a paper 2 days ago
Aspire: Can Models Self-Evolve from Vague Goals? upvoted a paper 2 days ago
HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?Organizations
upvoted 3
papers 2 days ago
updated a
Space 2 months ago
liked a
model 2 months ago
Add persona examples (validated v1 PERSONA concepts)
#16 opened 3 months ago
by Lunamos
liked 2
models 3 months ago
Add Gemma-4-12B-IT (gemma4_unified): transformers main + flas checkpoint20260605
#15 opened 3 months ago
by Lunamos
updated 7
models 3 months ago
flas-ai/flas-gemma-3-4b-pt
Updated • 10 • 1
flas-ai/flas-gemma-3-4b-it
Updated • 6
flas-ai/flas-llama-3.1-8b
Updated • 5
flas-ai/flas-llama-3.1-8b-instruct
Updated • 5
flas-ai/flas-qwen3-8b-base
Updated • 5
flas-ai/flas-qwen3-8b
Updated • 13 • 2
flas-ai/flas-gemma-4-12b-it
Updated • 5 • 2
published a
model 3 months ago
Remove Stop button — keep just Generate
#14 opened 3 months ago
by Lunamos
Sliders 2-per-row + min_width (no more wrapped labels); native loading spinner (drop text notice)
#13 opened 3 months ago
by Lunamos
Stream baseline too; loading notice on first-use download; fill_width=True; relabel Steps
#12 opened 3 months ago
by Lunamos