AI论文速递
菜单

Daily edition / 2026-08-14

AI 论文简章 · 2026-08-14

今日关注 AVA-Encoder: Towards Agent-Native Video Representation Learning、DreamFly: Causal Memory and Receding-Horizon Diffusion Planning for Aerial Vision-Language Navigation、Constructing Dynamic Master Logic Models as Knowledge Graphs for Complex System Diagnostics Using Retrieval-Augmented Large Language Models，共收录 100 篇论文。

查看候选、来源、评分与验证详情

精选论文
3
关联阅读
8
发布日期
2026-08-14
Selected with editorial context
01
  • 自然语言处理
  • 计算机视觉

AVA-Encoder: Towards Agent-Native Video Representation Learning

AVA-Encoder: Towards Agent-Native Video Representation Learning

arXiv:2608.12313

Creative agents still lack an effective way to learn from high-quality human films, limiting their ability to produce cinematic-grade videos. A key challenge is the absence of a structured video representation that is both faithful to film content and directly usable for agentic reasoning and manipulation. To address the challenge, we propose the Agentic Video Auto-Encoder (AVA-Encoder), a framework for learning agent-native video representations via agentic auto-encoding. AVA-Encoder transforms a video into a knowledge graph (KG) representation and then reconstructs it back into video. Its hierarchy and state nodes store structured text, while a linked asset layer holds generated images, audio, and video. Typed edges preserve the relations between these text descriptions and assets in a form that agents can easily understand, query, and edit. The video reconstruction differences drive a textual-gradient optimization framework, which expresses evaluation feedback as natural-language

编辑观察相关性 100，质量 95，新颖度 100

作者Chuyue Li、Jinpeng Yu、Haozhe Wang、Tian Xueyun、Zhijing Zhang、Bingnan Li、Shuqi Gu、Kan Ren、Jiaming Liu、Ruihua Hua

机构机构未提供

来源arXiv

阅读原文
02
  • 人工智能
  • 计算机视觉

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

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

arXiv:2608.12308

Aerial vision-language navigation (VLN) requires an embodied agent to integrate visual evidence over time, plan future actions, and determine when it has reached a navigation goal under partial observability. Although recent VLA models offer a promising perception-to-action paradigm, adapting them to aerial navigation remains challenging due to limited historical context, short planning horizons, and unreliable implicit termination. To address these challenges, we propose DreamFly, a diffusion-based aerial VLN framework built on Dream-VLA. DreamFly introduces a causally aligned historical memory that augments the current visual representation using only observations preceding the current decision step, enabling temporal reasoning without future information leakage. We further formulate navigation as receding-horizon diffusion planning, where the policy predicts a $K$-step action chunk but executes only the first action before replanning. This plan-$K$, execute-one strategy uses future

编辑观察相关性 100，质量 95，新颖度 100

作者Yan Deng、Fei Xu

机构机构未提供

来源arXiv

阅读原文
03
  • 人工智能

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

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

arXiv:2608.12304

Dynamic Master Logic (DML) provides a hierarchical framework for representing system behavior by linking functional objectives to underlying structural elements. However, DML construction typically relies on expert interpretation of technical documentation, limiting scalability for complex systems. This study presents a framework for automated construction of DML models from system descriptions and their representation as Knowledge Graphs (KG-DML), using Retrieval-Augmented Generation and Large Language Models as enabling tools. Building on prior work with small-scale systems, the framework extends automated KG-DML construction and evaluation to substantially larger and more complex systems. Model construction proceeds across the DML hierarchy using targeted retrieval while preserving functional dependencies and explicit logical relationships. The resulting KG-DML supports diagnostic reasoning, safety assessment, upward failure propagation, and downward dependency tracing. A multi-leve

编辑观察相关性 100，质量 95，新颖度 100

作者Saman Marandi、Yu-Shu Hu、Mohammad Modarres

机构机构未提供

来源arXiv

阅读原文
8 related signals

01

arXiv

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

Modern black-box Image-to-Video (I2V) models offer powerful capabilities in automated content creation, yet their lack of fine-grained control and reliability presents significant challenges in professional workflows. Their inherent stochasticity causes minor variations in textual prompts or hyperparameters to yield drastically different outputs often necessitating inefficient, brute-force trial-and-error processes. To address these limitations, we introduce the ``Agentic Self-Improvement" framework, which reframes video synthesis into a closed-loop, goal-directed optimization. Our framework s

  • Aman Tyagi、Hemanth Boinpally、Jonathan Chen、Douglas Gebert、Steven Hickson
  • 人工智能

02

arXiv

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

Agents deployed in enterprise settings must reason across structured APIs and document collections, yet existing benchmarks evaluate these capabilities in isolation. We introduce VAKRA (e\textbf{V}aluating \textbf{A}PI and \textbf{K}nowledge \textbf{R}etrieval \textbf{A}gents), a benchmark of over $8{,}000$ executable APIs across $62$ domains with tasks spanning three settings of increasing difficulty: diverse API interaction styles, multi-hop reasoning over structured APIs, and multi-source reasoning with natural-language tool-use policy constraints. Correctness is verified by re-executing pr

  • Ankita Rajaram Naik、Anupama Murthi、Benjamin Elder、Siyu Huo、Raavi Gupta、Abhinav Jain、Praveen Venkateswaran、Abdulhamid Adebayo、Danish Contractor
  • 人工智能

03

arXiv

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

LLM agents increasingly rely on third-party skills, using natural-language descriptions for selection and instruction bodies for planning. This progressive-disclosure design exposes two sequential control points to untrusted publishers: a static skill may steer an otherwise correct task onto an unnecessarily costly trajectory. Prior work studies selection manipulation, malicious skill instructions, and tool-chain resource amplification largely separately, leaving their end-to-end composition unclear. We introduce Convergent Detour Hijacking (CDH), a text-only, runtime-independent attack that c

  • Junliang Liu、Ruoyu Li、Wenxin Tang、Jingyu Xiao、Zhenyu Liu、Jingheng Xu、Laizhong Cui
  • 人工智能

04

arXiv

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

Multimodal Large Language Models (MLLMs) have been growing the capability for scientific writing and collaboration. For example, OpenAI Prism is a free workspace for scientific writing and collaboration. One important feature in Prism is turning scientific diagrams directly into LaTeX TikZ code. In this paper, we build a benchmark, Diagram-MMU, a multi-modal benchmark designed to assess MLLMs' ability for scientific diagram parsing and understanding. Diagram-MMU features 3.7k curated diagrams and 18.3k human-validated questions across six domains. It evaluates MLLMs on three tasks common in vi

  • Weihao Bo、Shan Zhang、Yanpeng Sun、Jie Liu、Yongke Yao、Jinhao Du、Wei He、Kai Zou、Zechao Li、Jingdong Wang
  • 人工智能

05

arXiv

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

Multi-agent reinforcement learning for human-AI interaction typically relies on a single large language model to simulate user behavior. We show that this approach systematically fails to generalize, and trace the failure to simulator collapse: because the simulator LLM is mode-collapsed, an LLM policy trained against it overfits to narrow strategies that exploit the simulator's dominant mode, and such a policy transfers poorly to unseen simulators and real users. We formalize this collapse theoretically and propose two complementary solutions, one at inference time and one at training time. T

  • Simon Yu、Nicholas Tomlin、Marwa Abdulhai、Ximing Lu、Derek Chong、Abe Hou、Dilara Soylu、Sergey Levine、Christopher D. Manning、Weiyan Shi
  • 人工智能

06

arXiv

VICBench: A Multi-Language Benchmark for Code Vulnerability Detection

Evaluating security vulnerability detection tools requires benchmark datasets with vulnerability-inducing commits (VICs) - the commits that first introduce vulnerabilities into codebases. VICs are essential for determining the full range of vulnerable software versions. Existing vulnerability datasets suffer from limited programming language coverage, restricted patch complexity, and narrow project scope. Through our dual annotation by human experts and an agentic workflow, we create a benchmark - VICBench - of 100 verified VICs for 100 CVEs across 88 projects in Python, Java, and C++, coverin

  • Jin Lu、Xuening Han、Yang Zhong、Lin Tan、Kevin Luo、Andrew Gacek、Neha Rungta
  • 人工智能

07

arXiv

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

Existing Vision-Language Models (VLMs) exhibits a critical bottleneck in robust spatial reasoning. Recent reinforcement learning (RL) methods aim to close this gap with verifiable outcomes, yet they suffer from poor credit assignment across intermediate reasoning steps. Concurrently, structured reasoning approaches overlook the critical depth perception necessary for comprehensive 3D understanding. To address these challenges, we propose SCOUT (Structured Chain-Of-Thought Utilizing Process-Supervised RL Training). Specifically, we design a structured Chain-of-Thought (CoT) framework that expli

  • Zile Zhou、Huining Yuan、Weichen Zhang、Xinlei Chen、Xiao-ping Zhang
  • 人工智能

08

arXiv

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

Treating patients with combinations of drugs reduces the risk of resistance to any individual drug. Finding effective combinations is difficult because the large search space makes combinatorial screens prohibitively expensive, time consuming, and often technically infeasible. Predictive models can fill this gap, yet existing methods typically require molecular profiling of each sample and per-cohort training, limiting their applicability when time and tissue are scarce. To address this challenge, we introduce ScreenShot, a hierarchical transformer pretrained on 40 drug screening datasets cove

  • Antoine de Mathelin、Christopher Tosh、Wesley Tansey
  • 机器学习