Daily sources / 2026-08-14

候选与来源详情

展示本期公开候选的来源、作者、唯一标识、评分与验证概况。

候选总数: 8
抓取时间: 未记录
来源覆盖: 1

返回本期日报

来源覆盖

本期精选与候选

arXiv11 条 · preprint

3 篇 featured

Editorial selection

arXiv / preprint

AVA-Encoder: Towards Agent-Native Video Representation Learning

作者: Chuyue Li、Jinpeng Yu、Haozhe Wang、Tian Xueyun、Zhijing Zhang、Bingnan Li、Shuqi Gu、Kan Ren、Jiaming Liu、Ruihua Hua
唯一 ID: arXiv 2608.12313
日期: 2026/8/13 01:58:02
验证: passed

总分 99相关 100质量 95新颖 100heuristic-v1@2026-08-13.1

arXiv / preprint

DreamFly: Causal Memory and Receding-Horizon Diffusion Planning for Aerial Vision-Language Navigation

作者: Yan Deng、Fei Xu
唯一 ID: arXiv 2608.12308
日期: 2026/8/13 01:54:33
验证: passed

总分 99相关 100质量 95新颖 100heuristic-v1@2026-08-13.1

arXiv / preprint

Constructing Dynamic Master Logic Models as Knowledge Graphs for Complex System Diagnostics Using Retrieval-Augmented Large Language Models

作者: Saman Marandi、Yu-Shu Hu、Mohammad Modarres
唯一 ID: arXiv 2608.12304
日期: 2026/8/13 01:50:39
验证: passed

总分 99相关 100质量 95新颖 100heuristic-v1@2026-08-13.1

Related / candidate

8 条公开候选

arXiv / preprint

Beyond Trial-and-Error: Agentic Optimization for Image-to-Video Adherence

作者: Aman Tyagi、Hemanth Boinpally、Jonathan Chen、Douglas Gebert、Steven Hickson
唯一 ID: arXiv 2608.12290
日期: 2026/8/13 01:35:16
验证: passed

暂无公开评分记录

arXiv / preprint

VAKRA: Evaluating Multi-Hop Reasoning Across APIs and Retrieval Under Tool-Use Policies

作者: Ankita Rajaram Naik、Anupama Murthi、Benjamin Elder、Siyu Huo、Raavi Gupta、Abhinav Jain、Praveen Venkateswaran、Abdulhamid Adebayo、Danish Contractor
唯一 ID: arXiv 2608.12282
日期: 2026/8/13 01:27:27
验证: passed

暂无公开评分记录

arXiv / preprint

Convergent Detour Hijacking: Task-Preserving Resource Amplification in Skill-Based LLM Agents

作者: Junliang Liu、Ruoyu Li、Wenxin Tang、Jingyu Xiao、Zhenyu Liu、Jingheng Xu、Laizhong Cui
唯一 ID: arXiv 2608.12273
日期: 2026/8/13 01:12:49
验证: passed

暂无公开评分记录

arXiv / preprint

Diagram-MMU: A Multi-Modal Benchmark for Scientific Diagrams

作者: Weihao Bo、Shan Zhang、Yanpeng Sun、Jie Liu、Yongke Yao、Jinhao Du、Wei He、Kai Zou、Zechao Li、Jingdong Wang
唯一 ID: arXiv 2608.12262
日期: 2026/8/13 01:04:13
验证: passed

暂无公开评分记录

arXiv / preprint

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL

作者: Simon Yu、Nicholas Tomlin、Marwa Abdulhai、Ximing Lu、Derek Chong、Abe Hou、Dilara Soylu、Sergey Levine、Christopher D. Manning、Weiyan Shi
唯一 ID: arXiv 2608.12253
日期: 2026/8/13 00:55:50
验证: passed

暂无公开评分记录

arXiv / preprint

VICBench: A Multi-Language Benchmark for Code Vulnerability Detection

作者: Jin Lu、Xuening Han、Yang Zhong、Lin Tan、Kevin Luo、Andrew Gacek、Neha Rungta
唯一 ID: arXiv 2608.12246
日期: 2026/8/13 00:45:49
验证: passed

暂无公开评分记录

arXiv / preprint

SCOUT: Unlocking Enhanced Spatial Reasoning via Structured Chain-of-Thought and Multi-Objective Process Reward

作者: Zile Zhou、Huining Yuan、Weichen Zhang、Xinlei Chen、Xiao-ping Zhang
唯一 ID: arXiv 2608.12220
日期: 2026/8/13 00:14:25
验证: passed

暂无公开评分记录

arXiv / preprint

ScreenShot: A Foundation Model for Few-Shot Combination Drug Screening

作者: Antoine de Mathelin、Christopher Tosh、Wesley Tansey
唯一 ID: arXiv 2608.12219
日期: 2026/8/13 00:13:50
验证: passed

暂无公开评分记录