Resources for Agent-Editing World Model (AEWM), a world model for improving long-horizon LLM agents through decision-effect modeling and state rev
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Spectral-Driven Adaptive-Rank Optimizer for Large Language Model Reinforcement Learning with Verifiable Rewards
SpectralShift: Effective Context Window Extension of Gated DeltaNet via Spectral Reparameterization
models 31
RUC-AIBOX/AEWM
Text Generation • 35B • Updated • 98
RUC-AIBOX/Perceval-3B-reward
4B • Updated • 37
RUC-AIBOX/Perceval-3B-policy
4B • Updated • 18
RUC-AIBOX/ClawGym-30A3
31B • Updated • 13
RUC-AIBOX/ClawGym-8B
8B • Updated • 14
RUC-AIBOX/ClawGym-4B
4B • Updated • 14
RUC-AIBOX/SWE-World-SWR-72B-w-cot
73B • Updated • 9
RUC-AIBOX/SWE-World-SWT-72B-w-cot
73B • Updated • 10
RUC-AIBOX/SWE-World-SWR-32B-w-cot
33B • Updated • 7
RUC-AIBOX/SWE-World-SWT-32B-wo-cot
33B • Updated • 7
datasets 21
RUC-AIBOX/AEWM-Action-Judge-Bench
Viewer • Updated • 3k • 177
RUC-AIBOX/Evo-Bench
Viewer • Updated • 608 • 5.36k • 3
RUC-AIBOX/ClawGym-Trajectory
Preview • Updated • 335 • 4
RUC-AIBOX/ClawGym-Bench
Viewer • Updated • 200 • 224 • 2
RUC-AIBOX/ClawGym-Task
Preview • Updated • 363 • 7
RUC-AIBOX/OlymMATH
Viewer • Updated • 550 • 2.57k • 14
RUC-AIBOX/Passk_Training_Maze
Viewer • Updated • 40.8k • 87 • 2
RUC-AIBOX/Llama-3-SynE-Dataset
Viewer • Updated • 168M • 3.26k • 10
RUC-AIBOX/0.8k-data-SimpleDeepSearcher
Viewer • Updated • 871 • 98 • 5
RUC-AIBOX/ORION
Preview • Updated • 90 • 1