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

+1959新增论文
+1550其中 AI 相关
+212已有论文修订
+59新增 AI 导读

arXiv 最近完成扫描:2026-11-18 03:26 · 全站最近入库:2026-11-17 23:35各信源进度 →

统计口径与数据新鲜度

统计 2026-11-17 03:55 — 2026-11-18 03:55(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:2026-11-18 03:26最近发现新增版本:2026-11-17 23:35库内论文最新更新时间:2026-11-17 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。

25,786 已收录论文21,491 AI 相关7,725 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 2 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-18 03:24(北京时间)
新论文 · v1arXiv:2611.20335

When Should Decision Models Compare Candidates?

Fangzhi Li, Quan Shi, Wenting Yang, Yueqiao Chen, Jiayu Chang, Shuting Zhao, Zhaowei Xu, Yizhao Chen 等 10 位作者

原文摘要

Language-model agents frequently select among candidate actions, such as tools and web elements. Should decision models score candidates independently or allow their scores to depend on other candidates? We investigate this question by comparing three approaches: Pointwise scoring, Setwise scoring, and Candidate Attention. Across five agent-decision benchmarks, Pointwise scoring remains competitive, while Setwise scoring performs better on some tool-selection and binary-decision tasks. Candidate Attention does not consistently improve upon Pointwise scoring, despite allowing cross-candidate interaction. Using two controlled synthetic tasks, we further examine whether models learn to use candidate-set information. With targeted relational training, Setwise models learn candidate dependencies and generalize to shifted inputs, while Candidate Attention shows weaker transfer. Our results show that access to other candidates does not guarantee effective comparison, and that its benefits depend on both task requirements and training.

cs.CL · cs.LG

版本更新 · v4arXiv:2603.25184

Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model

Jiahao Wu, Ning Lu, Shengcai Liu, Kun Wang, Yanting Yang, Baijiong Lin, Chen Jason Zhang, Li Qing 等 9 位作者

原文摘要

Reinforcement learning (RL) has become essential for post-training large language models (LLMs) in reasoning tasks. While scaling rollouts can stabilize training and enhance performance, the computational overhead is a critical issue. In algorithms like GRPO, multiple rollouts per prompt incur prohibitive costs, as a large portion of prompts provide negligible gradients and are thus of low utility. To address this problem, we investigate how to select high-utility prompts before the rollout phase. Our experimental analysis reveals that sample utility is non-uniform and evolving: the strongest learning signals concentrate at the ``learning edge", the intersection of intermediate difficulty and high uncertainty, which shifts as training proceeds. Motivated by this, we propose HIVE (History-Informed and online-VErified prompt selection), a dual-stage framework for data-efficient RL. HIVE utilizes historical reward trajectories for coarse selection and employs prompt entropy as a real-time proxy to prune instances with stale utility. By evaluating HIVE across multiple math reasoning benchmarks and models, we show that HIVE yields significant rollout efficiency without compromising performance.

cs.LG · cs.AI