Everything in Moderation: Per-Domain Coverage Optima and Alignment-Resistant Domain Gaps in Multi-Domain Mid-Training

arXiv:2609.09081 · cs.AI · Submitted 2026-09-08 · Read on arXiv

cs.AI

Submitted: 2026-09-08

Updated: 2026-09-08

Comments: About to commit to ICLR

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Alignment — 4× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection