Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems
Paper • 2607.21627 • Published • 2
Xiaoyang Cao
Sean13
·
AI & ML interests
RLFH, Deep Reinfrocement Learning
Recent Activity
upvoted a paper 4 days ago
Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems updated a model 3 months ago
Sean13/responsibility-decomposition published a model 3 months ago
Sean13/responsibility-decompositionOrganizations
None yet
upvoted a paper 4 days ago
updated a
model 3 months ago
published a
model 3 months ago
upvoted a paper 9 months ago
upvoted 3
papers 10 months ago
RLinf-VLA: A Unified and Efficient Framework for VLA+RL Training
Paper • 2510.06710 • Published • 43
Cache-to-Cache: Direct Semantic Communication Between Large Language Models
Paper • 2510.03215 • Published • 99
Latent Collective Preference Optimization: A General Framework for Robust LLM Alignment
Paper • 2509.24159 • Published • 1