Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Look Before You Leap: Thermodynamic Arbitration of Parametric and Non-Parametric Knowledge in LLM Agents via Self-Regulating Memory Architectures
Akash Das, Ishan Roy
The architecture of modern LLMs consists of a profound cognitive polarization. LLMs possess implicit intuition encoded in their parameters, yet rely on a disconnected, explicit mec…
cs.AI2026
Safe Context Switching for Agents in the Wild: Mitigating Subspace Interference via Orthogonal Adaptation
Akash Das, Ishan Roy
Most Large Language Models exhibit a fundamental tension between two sequential tasks, such as logical reasoning and safety alignment. The high-variance internal states required fo…