Decoupling Logic from Persona: Structural Immunity of Edge LLM Agents to Context Pollution

arXiv:2610.09772 · cs.CL, cs.AI · Submitted 2026-10-07 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-10-07

Updated: 2026-10-09

Comments: 28 pages, 3 figures. Experiment code, scoring rubric, pollution fixtures, adapters and run logs are released (see Appendix G)

Code: https://github.com/ml-explore/mlx

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

Terminology

• Decoupling — 1× in this paper · explained in 2 episodes

Sources

• A General Language Assistant as a Laboratory for Alignment
• The Llama 3 Herd of Models
• Gemma 3 Technical Report
• LLMs Get Lost In Multi-Turn Conversation
• Character-LLM: A Trainable Agent for Role-Playing
• Towards Understanding Sycophancy in Language Models
• Efficient Guided Generation for Large Language Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering