Asking Is Not Enough: Protocol Sensitivity in LLM Confidence Calibration

arXiv:2604.13206v1 Announce Type: new Abstract: As Large Language Models (LLMs) are increasingly integrated into agentic workflows, their unpredictability stemming from numerical

arXiv:2608.13591v1 Announce Type: new Abstract: High-confidence errors in large language models are often treated as evidence of fragile internal inference. We study a different

arXiv:2610.01006v1 Announce Type: new Abstract: Decision models return probabilities intended for routing, abstention and automated action. Calibration makes those probabilities

arXiv:2603.29953v1 Announce Type: new Abstract: How reliably can structured intent representations preserve user goals across different AI models, languages, and prompting

arXiv:2607.09665v1 Announce Type: new Abstract: Prompt wrappers often differ only in formatting, yet they can change model scores enough to flip leaderboard conclusions. We study

arXiv:2610.03894v1 Announce Type: new Abstract: A deployed LLM agent emits tool calls, queries, and code that can be silently wrong -- by the time the error surfaces, the action

arXiv:2608.11403v1 Announce Type: new Abstract: Self-consistency (SC) via majority vote is a widely used way to spend inference-time compute: sample N chains of thought, return

arXiv:2608.24314v1 Announce Type: new Abstract: Evaluating conversational voice agents at scale re- quires reliable assessment methods that capture both observ- able interaction