paper-with-me

홈 › Papers

The Long-Horizon Task Mirage? Diagnosing Where and Why Agentic Systems Break

2026-04-13 · Xinyu Jessica Wang, Haoyue Bai, Yiyou Sun, Haorui Wang, Shuibai Zhang, Wenjie Hu, Mya Schroder, Bilge Mutlu, Dawn Song, Robert D Nowak arxiv

Large language model (LLM) agents perform strongly on short- and mid-horizon tasks, but often break down on long-horizon tasks that require extended, interdependent action sequences. Despite rapid progress in agentic systems, these long-horizon failures remain poorly characterized, hindering principled diagnosis and comparison across domains. To address this gap, we introduce HORIZON, an initial cross-domain diagnostic benchmark for systematically constructing tasks and analyzing long-horizon failure behaviors in LLM-based agents. Using HORIZON, we evaluate state-of-the-art (SOTA) agents from multiple model families (GPT-5 variants and Claude models), collecting 3100+ trajectories across four representative agentic domains to study horizon-dependent degradation patterns. We further propose a trajectory-grounded LLM-as-a-Judge pipeline for scalable and reproducible failure attribution, and validate it with human annotation on trajectories, achieving strong agreement (inter-annotator κ=0.61; human-judge κ=0.84). Our findings offer an initial methodological step toward systematic, cross-domain analysis of long-horizon agent failures and offer practical guidance for building more reliable long-horizon agents. We release our project website at \href{https://xwang2775.github.io/horizon-leaderboard/}{HORIZON Leaderboard} and welcome contributions from the community.

📄 PDF Abstract BibTeX arXiv:2604.11978

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Mirage-1: Augmenting and Updating GUI Agent with Hierarchical Multimodal Skills

2025-06-12 · Yuquan Xie, Zaijing Li, Rui Shao, Gongwei Chen 외

Recent efforts to leverage the Multi-modal Large Language Model (MLLM) as GUI agents have yielded promising outcomes. However, these agents still struggle with long-horizon tasks in online environments, primarily due to …

Large Language ModelTask Planning

Modular Jets for Supervised Pipelines: Diagnosing Mirage vs Identifiability

2025-12-05 · Suman Sanyal arxiv

Classical supervised learning evaluates models primarily via predictive risk on hold-out data. Such evaluations quantify how well a function behaves on a distribution, but they do not address whether the internal decompo…

MIRAGE: Mobile Agents with Implicit Reasoning and Generative World Models

2026-06-03 · Zhichao Yang, Yuanze Hu, Haojie Hao, Longkun Hao 외 arxiv

Mobile agents are increasingly expected to operate everyday applications from screenshots and language goals, where reliable control requires reasoning over screen affordances, multi-step navigation, and future state cha…

MirageRoom: 3D Scene Segmentation with 2D Pre-trained Models by Mirage Projection

2024-01-01 · CVPR 2024 1 · Haowen Sun, Yueqi Duan, Juncheng Yan, Yifan Liu 외

Nowadays leveraging 2D images and pre-trained models to guide 3D point cloud feature representation has shown a remarkable potential to boost the performance of 3D fundamental models. While some works rely on additio…

Point Cloud SegmentationScene Segmentation

MIRAGE: Defending Long-Form RAG Against Misinformation Pollution

2026-07-06 · Saadeldine Eletter, Ruihong Zeng, Yuxia Wang, Maxim Panov 외 arxiv

Retrieval-Augmented Generation (RAG) improves factuality by grounding LLMs in external evidence, but real-world retrieval is often polluted: semantically relevant passages may contain subtle misinformation, misleading fr…