English(EN) CircuitLens: Reasoning Circuits as Data Selection Signals for Reinforcement Learning with Verifiable Rewards

新的电路推理分数改进了强化学习数据选择

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

研究人员开发了一种名为电路推理分数（CRS）的新方法，以改进可验证奖励强化学习（RLVR）的数据选择。与将数据价值视为问题内在属性的先前方法不同，CRS根据模型对其推理电路的参与度来评估数据价值。这种方法在Qwen2.5-Math-7B上进行了测试，结果表明，推理电路参与度较低的数据在GSM8K和OlympiadBench等基准测试中表现更好。 AI

影响这种新的数据选择方法可能导致更有效和更具影响力的AI模型训练，特别是在复杂的推理任务中。

排序理由介绍AI研究新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 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: 9 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 介绍AI研究新方法的学术论文。[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, infra; 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]

arXiv cs.LG TIER_1 English(EN) · Zhuofan Chen, Ziqian Jiao, Yikai Cui, Zhixin Cai, Jun Bai, Wenge Rong · 2026-09-10 04:00

CircuitLens：将推理电路作为可验证奖励强化学习的数据选择信号

arXiv:2609.07183v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) is sensitive to which problems a model trains on, yet existing selection criteria--difficulty filtering, hand-curation, reward-trajectory scoring--assess data value as an intri…

本文如何被排名

报道来源 [1]

CircuitLens：将推理电路作为可验证奖励强化学习的数据选择信号

相关实体

相关话题