Safe Context Switching for Agents in the Wild: Mitigating Subspace Interference via Orthogonal Adaptation
cs.AI, cs.CL
Submitted: 2026-10-04
Updated: 2026-10-04
Journal ref: ICLR 2026 the 2nd Workshop on World Models: Understanding, Modelling and Scaling
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Program Synthesis with Large Language Models
- Training Verifiers to Solve Math Word Problems
- Activated LoRA: Fine-tuned LLMs for Intrinsics
- TruthfulQA: Measuring How Models Mimic Human Falsehoods
- AdapterFusion: Non-Destructive Task Composition for Transfer Learning
- Orthogonal Subspace Learning for Language Model Continual Learning
- Instruction-Following Evaluation for Large Language Models
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
- Agents' Last Exam
- 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