From Atomic to Composite: Reinforcement Learning Enables Generalization in Complementary Reasoning
Paper
•
2512.01970
•
Published
•
1
DERL_Group
non-profit
AI & ML interests
None defined yet.
Recent Activity
View all activity
sitao
authored
a
paper
4 days ago
sitao
updated
6
models
8 days ago
DifferentiableEvolutionaryRL/DERL-ALFWorld-L2-Qwen2.5-1.5B
2B
•
Updated
•
34
•
1
DifferentiableEvolutionaryRL/DERL-ALFWorld-L1-Qwen2.5-1.5B
2B
•
Updated
•
20
DifferentiableEvolutionaryRL/DERL-ScienceWorld-L0-Qwen2.5-1.5B
2B
•
Updated
•
14
DifferentiableEvolutionaryRL/DERL-ScienceWorld-L1-Qwen2.5-1.5B
2B
•
Updated
•
17
DifferentiableEvolutionaryRL/DERL-ScienceWorld-L2-Qwen2.5-1.5B
2B
•
Updated
•
14
DifferentiableEvolutionaryRL/DERL-ALFWorld-L0-Qwen2.5-1.5B
2B
•
Updated
•
40
•
1
L3133625978
updated
a
model
12 days ago
L3133625978
published
a
model
12 days ago
L3133625978
updated
a
model
12 days ago
L3133625978
published
a
model
12 days ago
L3133625978
updated
a
model
12 days ago
L3133625978
published
a
model
12 days ago
L3133625978
updated
a
model
12 days ago
L3133625978
published
a
model
12 days ago
L3133625978
updated
a
model
12 days ago
L3133625978
published
a
model
12 days ago
sitao
updated
a
model
12 days ago
L3133625978
updated
a
model
12 days ago
L3133625978
published
a
model
12 days ago