跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1171新增论文
+938其中 AI 相关
+130已有论文修订
+94新增 AI 导读

arXiv 最近完成扫描:2026-11-19 06:59 · 全站最近入库:2026-11-19 17:46各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 18:44 — 2026-11-19 18:44(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-19 06:59最近发现新增版本:2026-11-19 17:46库内论文最新更新时间:2026-11-19 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

27,410 已收录论文22,788 AI 相关8,343 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 1 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-19 06:57(北京时间)
版本更新 · v2arXiv:2610.27012

Activation-Space Exploration for Visual and Textual Reasoning with RLVR

Yunan Zeng, Jinhao Jing, Xi Cheng, Yuwang Wang

原文摘要

Reinforcement learning with verifiable rewards (RLVR) improves visual and textual reasoning by sampling responses, scoring them with an automatic verifier, and updating the policy from the resulting rewards. The policy therefore receives direct learning signals only from trajectories that appear in its rollouts. Yet repeated sampling from the same policy can concentrate on similar reasoning paths, leaving useful alternatives unexplored under a fixed rollout budget. We introduce Activation-Space Exploration (ASE), an online method for diversifying training rollouts. By clustering activation differences between correct and incorrect responses to the same problem, ASE builds a structured bank of latent exploration vectors. Different vectors are then applied to subsequent rollouts to explore alternative reasoning paths. Under the same rollout budget, ASE improves average accuracy over GRPO on Qwen3-VL-2B-Instruct by 5.41 and 3.15 percentage points across six visual mathematical and six general visual reasoning benchmarks, respectively. On Qwen3-1.7B-Base, it improves average Mean@8 over GRPO across six mathematical reasoning benchmarks by 4.87 percentage points, with gains also observed on Qwen3-8B-Base.

cs.LG · cs.AI