English(EN) Direct Diversity Optimization for Diverse Successful Trajectories in Preference Post-Training

新的DDO方法增强了LLM代理策略的多样性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-10 04:00

研究人员推出了一种新颖的大型语言模型代理离线后训练方法——直接多样性优化（DDO）。DDO旨在通过结合发散树收集（DTC）和参考相对目标赔率目标（RTO）来提高代理可采用的成功策略的广度。该方法构建了与状态对齐的分支集，并训练模型在成功的替代方案中匹配参考相对目标。与BabyAI、BabaIsAI和WebShop等基准上的现有方法相比，DDO在任务成功率和策略覆盖率方面均表现出优越的性能。 AI

影响该方法有望带来更强大、更多功能的AI代理，能够处理更广泛的任务和场景。

排序理由该集群包含一篇详细介绍LLM代理新训练方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 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: 13 / 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LLM代理新训练方法的论文。[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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Junwon Ko, Dong-Jae Lee, Minchan Kwon, Sunghyun Baek, Junmo Kim · 2026-09-10 04:00

面向偏好后训练中多样化成功轨迹的直接多样性优化

arXiv:2609.10052v1 Announce Type: new Abstract: LLM agents for sequential decision tasks are often post-trained with trajectory-level outcome labels, but such labels provide little supervision for preserving multiple successful branches from the same decision state. We study this…

本文如何被排名

报道来源 [1]

面向偏好后训练中多样化成功轨迹的直接多样性优化

相关实体

相关话题