Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement Learning
Paper
•
2505.24726
•
Published
•
272
Melisa Russak
melisa
AI & ML interests
I love definitions
Recent Activity
upvoted
an
article
9 days ago
Introducing the Palmyra-mini family: Powerful, lightweight, and ready to reason!
upvoted
a
paper
2 months ago
A New Pair of GloVes
updated
a model
2 months ago
Writer/colab
Organizations
authored
a
paper
4 months ago
authored
a
paper
6 months ago
authored
3
papers
about 1 year ago
Writing in the Margins: Better Inference Pattern for Long Context Retrieval
Paper
•
2408.14906
•
Published
•
144
OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web
Paper
•
2402.17553
•
Published
•
25
Becoming self-instruct: introducing early stopping criteria for minimal instruct tuning
Paper
•
2307.03692
•
Published
•
26