From f(x) and g(x) to f(g(x)): LLMs Learn New Skills in RL by Composing Old Ones
Paper
•
2509.25123
•
Published
•
20
Hanbin Wang
hanbin
AI & ML interests
Code Intelligence and LLM Reasoning (Code, Math)
Recent Activity
upvoted
a
paper
4 months ago
From f(x) and g(x) to f(g(x)): LLMs Learn New Skills in RL by
Composing Old Ones
upvoted
a
paper
4 months ago
A Survey of Reinforcement Learning for Large Reasoning Models
upvoted
a
paper
5 months ago
UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn
Reinforcement Learning
Organizations
upvoted
2
papers
4 months ago
upvoted
a
paper
5 months ago
published
a
dataset
5 months ago
updated
a
dataset
5 months ago
published
a
dataset
5 months ago
updated
2
models
6 months ago
published
2
models
6 months ago
updated
2
models
6 months ago
published
2
models
6 months ago
updated
a
model
6 months ago
published
a
model
6 months ago
updated
a
model
6 months ago
published
a
model
6 months ago
updated
a
model
10 months ago
published
a
model
10 months ago