[2604.01413] Adaptive Stopping for Multi-Turn LLM Reasoning

Computer Science > Computation and Language arXiv:2604.01413 (cs) [Submitted on 1 Apr 2026 (v1), last revised 5 Apr 2026 (this version, v2)] Title:Adaptive Stopping for Multi-Turn LLM Reasoning Authors:Xiaofan Zhou, Huy Nguyen, Bo Yu, Chenxi Liu, Lu Cheng View a PDF of the paper titled Adaptive Stopping for Multi-Turn LLM Reasoning, by Xiaofan Zhou and 4 other authors View PDF HTML (experimental) Abstract:Large Language Models (LLMs) increasingly rely on multi-turn reasoning and interaction, such as adaptive retrieval-augmented generation (RAG) and ReAct-style agents, to answer difficult questions. These methods improve accuracy by iteratively retrieving information, reasoning, or acting, but introduce a key challenge: \textbf{When should the model stop?} Existing approaches rely on heuristic stopping rules or fixed turn budgets and provide no formal guarantees that the final prediction still contains the correct answer. This limitation is particularly problematic in high-stakes domains such as finance and healthcare, where unnecessary turns increase cost and latency, while stopping too early risks incorrect decisions. Conformal prediction (CP) provides formal coverage guarantees, but existing LLM-CP methods only apply to a single model output and cannot handle multi-turn pipelines with adaptive stopping. To address this gap, we propose Multi-Turn Language Models with Conformal Prediction (MiCP), the first CP framework for multi-turn reasoning. MiCP allocates different err...