Researchers from Meta’s FAIR team and The Hebrew University of Jerusalem have discovered that forcing large language models to “think” less actually improves their performance on complex reasoning tasks. The study found that shorter reasoning processes in AI systems lead to more accurate results while significantly reducing computational costs. The researchers discovered that within the same reasoning task, “shorter reasoning chains are significantly more likely to yield correct answers — up to 34.5% more accurate than the longest chain sampled for the same question.” This finding held true across multiple leading AI models and benchmarks. Based on these findings, the team developed a novel approach called “short-m@k,” which executes multiple reasoning attempts in parallel but halts computation once the first few processes complete. The final answer is then selected through majority voting among these shorter chains. The researchers found their method could reduce computational resources by up to 40% while maintaining the same level of performance as standard approaches. “Our findings suggest rethinking current methods of test-time compute in reasoning LLMs, emphasizing that longer ‘thinking’ does not necessarily translate to improved performance and can, counter-intuitively, lead to degraded results,” the researchers conclude. The study points toward potential cost savings and performance improvements by optimizing for efficiency rather than raw computing power.