Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning
Paper
ā¢
2508.03501
ā¢
Published
ā¢
59
Mikhail Arkhipov
Mshn
Ā·
AI & ML interests
Generative Models, Latent Variable Models
Recent Activity
reacted
to
danielhanchen's
post
with š„
4 days ago
Mistral's new Ministral 3 models can now be Run & Fine-tuned locally! (16GB RAM)
Ministral 3 have vision support and the best-in-class performance for their sizes.
14B Instruct GGUF: https://huggingface.co/unsloth/Ministral-3-14B-Instruct-2512-GGUF
14B Reasoning GGUF: https://huggingface.co/unsloth/Ministral-3-14B-Reasoning-2512-GGUF
š± Step-by-step Guide: https://docs.unsloth.ai/new/ministral-3
All GGUFs, BnB, FP8 etc. variants uploads: https://huggingface.co/collections/unsloth/ministral-3
upvoted
a
paper
4 months ago
Training Long-Context, Multi-Turn Software Engineering Agents with
Reinforcement Learning
Organizations
None yet
upvoted
a
paper
4 months ago
upvoted
a
paper
8 months ago
upvoted
a
collection
9 months ago
upvoted
a
paper
over 1 year ago
upvoted
a
paper
almost 2 years ago