English(EN) From Trajectories to Prefixes: Reusing Teacher Trajectories via Replayed Prefixes and Online Continuation

Prefix-GRPO 增强小型语言模型以用于交互式代理

作者 PulseAugur 编辑部 · [1 个来源] · 2026-07-23 04:00

研究人员推出了一种新颖的强化学习框架 Prefix-GRPO，旨在增强小型语言模型在交互式代理任务中的性能。该方法将教师轨迹分解为与重放对齐的前缀查询和在线续接，使学生模型能够在长视界环境中更有效地学习。在 TextCraft、BabyAI 和 ALFWorld 上的实验表明，Prefix-GRPO 通过在统一的策略优化框架内优化前缀学习和续接学习，其性能优于标准的蒸馏和强化学习基线。 AI

影响通过实现从教师轨迹中更有效的学习，提高了小型模型代理在交互式任务中的性能。

排序理由该集群包含一篇详细介绍训练 AI 代理新方法的论文。[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 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍训练 AI 代理新方法的论文。[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: 77 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Yihan Wang, Zhong Guan, Haoran Sun, Jiale Huang, Likang Wu, Hongke Zhao · 2026-07-23 04:00

从轨迹到前缀：通过重放前缀和在线续接重用教师轨迹

arXiv:2607.19395v1 Announce Type: cross Abstract: Small language models are attractive backbones for interactive agents, but direct distillation from strong teacher trajectories often turns rich multi-turn behavior into one-shot imitation targets. This is inefficient in long-hori…

本文如何被排名

报道来源 [1]

从轨迹到前缀：通过重放前缀和在线续接重用教师轨迹

相关实体

相关话题