PulseAugur
中
实时 10:26:10

新的“Follow the Winners”算法增强了LLM的强化学习

研究人员推出了一种名为“Follow the Winners”(FTW)的新型无批评者强化微调算法,专为代理式大型语言模型(LLM)设计。与依赖于有状态环境中不切实际的重复回滚的现有GRPO风格方法不同,FTW使用回放缓冲区样本上的序数滤波器来适应交叉熵方法。这种方法允许回报的顺序统计量具有多项式集中性,使其适用于无法进行重复回滚的场景。在代理式LLM的后训练中,FTW在Sokoban和Search-R1基线上表现出与GRPO和PPO相当的性能,提供了一种可行的替代方案,并减少了CPU内存使用量。 AI

影响 该新算法为LLM在复杂环境中的强化学习提供了一种更实用的方法,有望提高其适应性并降低计算要求。

排序理由 该集群包含一篇学术论文,详细介绍了LLM强化学习的新算法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

新的“Follow the Winners”算法增强了LLM的强化学习

本文如何被排名

Signal score
11 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群包含一篇学术论文,详细介绍了LLM强化学习的新算法。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Same-day
Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.AI TIER_1 English(EN) · Joery Ari\"en de Vries, Neil David Lawrence, Zhenwen Dai ·

    跟随赢家:使用交叉熵方法对无批评者RFT进行保守策略改进

    arXiv:2610.03361v1 Announce Type: cross Abstract: Critic-free reinforcement fine-tuning (RFT) for agentic large language models is often done through GRPO-style methods, which compute a group baseline over repeated rollouts to reduce target variance. However, this setup is ill-su…