Portable Semantics, Private Dialects: Reuse and Negative Transfer in Latent Communication Between Language-Model Cells

arXiv:2609.11365 · cs.AI, cs.LG, cs.MA · Submitted 2026-09-10 · Read on arXiv

cs.AI, cs.LG, cs.MA

Submitted: 2026-09-10

Updated: 2026-09-10

Comments: 17 pages, 1 figure, 5 tables. Companion to arXiv:2608.20054. Code and evaluation records: https://github.com/tokenosopher/populus-evidence-partitioning ; checkpoints and fitted alignment maps: https://huggingface.co/tokenosopher/populus-evidence-partitioning-checkpoints

Code: https://github.com/tokenosopher/populus-evidence-partitioning

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

Terminology

• Alignment — 2× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Zero-Shot Transfer — 1× in this paper · explained in 4 episodes

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