Batch Prompting Suppresses Overthinking Reasoning Under Constraint: How Batch Prompting Suppresses Overthinking in Reasoning Models

Large Reasoning Models (LRMs) achieve strong performance through explicit chain-of-thought reasoning but suffer from $\mathit{\text{overthinking}}$: generating excessive reasoning tokens even for trivial queries. {Beyond inflating cost, overthinking can be self-defeating: models enter recursive self-doubt loops that exhaust token budgets without producing an answer, causing API timeouts that directly hurt accuracy.} We present an empirical study showing that $\mathbf{\text{batch}}\mathbf{\text{prompting}}$, originally introduced for throughput optimization, effectively suppresses overthinking at inference time. Across 13 diverse benchmarks with DeepSeek-R1 and OpenAI-o1, batch prompting {reduces reasoning tokens by 76% (2{,}950$\mapsto$710), on average, while preserving or improving accuracy}. Through behavioral analysis, we find that batching induces three beneficial effects: (1) it reduces per-query reasoning effort when multiple queries share a context; (2) it enables pattern induction, where models generalize from earlier examples to solve later ones; and (3) it suppresses hedging behavior (e.g., \texttt{wait,}'' $\mathtt{\text{let}}\mathtt{\text{me}}\mathtt{\text{double-check}}$‘’) that signals metacognitive loops. We also show that explicit prompt constraints (``$\mathtt{\text{Use}}\mathtt{\text{no}}\mathtt{\text{more}}\mathtt{\text{than}}\mathtt{\text{100}}\mathtt{\text{tokens}}\mathtt{\text{in}}\mathtt{\text{thinking.}}$‘’) fail to reduce overthinking; models either ignore them or sacrifice accuracy. These findings reframe batch prompting as more than a cost optimization: it is a practical inference-time technique that improves efficiency and reliability without model modification.