Author

Muhammad Usama

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

Control-Token Injection Suppresses Chain-of-Thought and Defeats Reasoning-Based Oversight in Tool-Using Agents

The safety of a tool-using language model agent is usually treated as a property of the model alone. We give controlled, full-precision evidence that it is instead a joint property of the model and the software that renders its chat template and parses its tool calls, the decoding harness, and that both halves are atta...

Muhammad Usama, Khairatul Nisa, Summer Yeoreum Jung · 0 citations

#machine learning Preprint Sep 2026

The System Prompt Illusion: How Instruction Preambles Modify Computation in Language Models

System prompts are the primary lever practitioners use to control language model behavior, yet what they actually do to the computation inside the transformer remains poorly understood. Across 17 instruction-tuned models spanning 8 architecture families and 1.5B to 72B parameters, we use Centered Kernel Alignment (CKA)...

Muhammad Usama, Dong Eui Chang · 0 citations