3 papers
cs.SE2026
Localizing Post-Wire Semantic Changes in MCP Agent Frameworks
Aditi Patodiya
Valid Model Context Protocol (MCP) messages do not guarantee that an agent framework preserves the distinctions downstream software needs. We present a differential testing method…
cs.SE2026
Broken on Arrival: Silently Defective LLM Artifacts in Public Model Registries and How to Catch Them
Aditi Patodiya
Developers increasingly run large language models locally by pulling quantized GGUF artifacts from public registries, yet nothing in the distribution pipeline functionally tests th…
cs.SE2026
Same Request, Different Answer: Quantization Amplifies Cache-Induced Divergence in LLM Serving
Aditi Patodiya
Major open-source serving stacks reuse the key-value tensors of a shared prefix by default. We measure what this prefix reuse costs in reproducibility. Holding model, decoding, see…