FLEET：用记忆机制替代重复采样，提速3倍
FLEET: From Logits Entropy to Enhanced Trajectories in Text Generation
一篇来自 arXiv 的新方法，把记忆机制塞进文本生成，同样的算力下 LiveCodeBench 准确率从 59.9% 提到 66.2%，还能快 3 倍。
论文提出 FLEET，为 LLM 生成过程加入记忆机制，用稀疏轨迹和 per-token 效用分数调整 logits。在相同预算下，FLEET 达到重复采样基线相同精度并实现 3 倍加速。在 LiveCodeBench 上，Pass@32 从 59.9% 提升到 66.2%。该方法只需单次校准即可确定主要超参数，对现有 LLM 管线的改动很小。
FLEET: From Logits Entropy to Enhanced Trajectories in Text Generation
Solutions based on large language models (LLMs) often rely on temperature sampling to improve accuracy and stability by aggregating multiple samples from the completion distribution. However, this memoryless approach is inherently suboptimal: because it lacks awareness of prior generations and their evaluations, it produces an increasing proportion of semantically duplicate answers as more samples are drawn, leading to diminishing returns. To address this limitation, we introduce FLEET, a novel method that integrates a memory mechanism into the generation process. FLEET represents each generation as a sparse trajectory through states whose entropy exceeds a predefined threshold and uses these trajectories to infer per-token utility scores that adjust the logits. Benchmark evaluations demonstrate that FLEET achieves the same accuracy as the repeated sampling baseline, with a 3x speedup, and substantially improves accuracy on complex coding tasks (LiveCodeBench Pass@32 increases from 59.9% to 66.2%) under the same budget. Furthermore, in the greedy-decoding configuration evaluated here, the approach is deterministic and uses a single calibration pass to derive its principal hyperparameters, requiring only minimal modifications to existing LLM pipelines.
