LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Memory for Large Language Models
EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery
models 85
THU-KEG/SAEVerbalizer-27B
Text Generation • 27B • Updated • 445
THU-KEG/LongTraceRL-30B
Reinforcement Learning • 31B • Updated • 8 • 1
THU-KEG/LongTraceRL-8B
Reinforcement Learning • Updated • 1
THU-KEG/LongTraceRL-4B
Reinforcement Learning • 4B • Updated • 8 • 1
THU-KEG/DeepDive-30B-A3B-C-GRPO
31B • Updated • 8
THU-KEG/DeepDive-4B-C-GRPO
4B • Updated • 40
THU-KEG/DeepDive-30B-A3B-SFT
31B • Updated • 10
THU-KEG/DeepDive-4B-SFT
4B • Updated • 9
THU-KEG/WildReward-8B
Text Classification • 8B • Updated • 11 • 3
THU-KEG/WildReward-4B
Text Classification • 4B • Updated • 14 • 4
datasets 24
THU-KEG/SAEVerbalizer-Data
Viewer • Updated • 2.2k
THU-KEG/LongTraceRL
Viewer • Updated • 2.82k • 204 • 2
THU-KEG/CaRR-DeepDive
Preview • Updated • 423 • 1
THU-KEG/WildFB
Updated • 128 • 3
THU-KEG/AgentIF
Viewer • Updated • 707 • 167 • 8
THU-KEG/DeepPrune
Preview • Updated • 8 • 2
THU-KEG/LinguaLens-Data
Viewer • Updated • 7.25k • 24 • 2
THU-KEG/RM-Bench
Viewer • Updated • 1.33k • 1.15k • 11
THU-KEG/LongWriter-Zero-RLData
Viewer • Updated • 8.61k • 151 • 24
THU-KEG/Arena-Write
Viewer • Updated • 595 • 118 • 5