paper-with-me

Papers

LoHoSearch: Benchmarking Long-Horizon Search Agents Beyond the Human Difficulty Ceiling

2026-06-11 · Jiarui Zhao, Rongzhi Zhang, Lingchuan Liu, Hao Yang, Xunliang Cai, Xi Su arxiv

Search agent benchmarks exemplified by BrowseComp have rapidly saturated over the past year, with the strongest models surpassing 90% accuracy. Since these benchmarks are predominantly human-authored, annotators lack a global perspective on entity statistics and cannot systematically maximize search space size and structural complexity. This creates a difficulty ceiling that is hard to break. To address this, we introduce LoHoSearch (Long-Horizon Search Agents), a challenging benchmark comprising 544 human-verified questions across 11 domains. LoHoSearch is constructed via an automated pipeline built upon a knowledge graph covering over 7 million Wikipedia entities, which selects relations with large search spaces and assembles them into structurally complex questions with KG-verified unique answers. Our evaluation demonstrates that even the strongest model achieves only 34.74% accuracy, and existing context management strategies (best +6.8%) yield far smaller gains than on prior benchmarks. LoHoSearch provides a more demanding standard for evaluating long-horizon reasoning and context management in search agents.

📄 PDF Abstract BibTeX arXiv:2606.12837

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks?

2026-06-03 · Zhangchen Xu, Junda Chen, Yue Huang, Dongfu Jiang 외 arxiv

Scientific and engineering progress is fundamentally a long-horizon iterative process: proposing changes, running experiments, measuring outcomes, and continuously refining artifacts. Yet existing benchmarks for frontier…

AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks

2026-02-18 · Tanqiu Jiang, Yuhui Wang, Jiacheng Liang, Ting Wang arxiv

LLM agents are increasingly deployed in long-horizon, complex environments to solve challenging problems, but this expansion exposes them to long-horizon attacks that exploit multi-turn user-agent-environment interaction…

CoffeeBench: Benchmarking Long-Horizon LLM Agents in Heterogeneous Multi-Agent Economies

2026-06-15 · Issa Sugiura, Daichi Hattori, Kazuo Araragi, Keita Ogawa 외 arxiv

As LLM agents become capable of increasingly long-horizon tasks, evaluating their performance in economic systems is becoming increasingly important. Unlike existing benchmarks that primarily evaluate a single agent inte…

Odysseys: Benchmarking Web Agents on Realistic Long Horizon Tasks

2026-04-27 · Lawrence Keunho Jang, Jing Yu Koh, Daniel Fried, Ruslan Salakhutdinov arxiv

Existing web agent benchmarks have largely converged on short, single-site tasks that frontier models are approaching saturation on. However, real world web use consists of long-horizon, multi-site workflows. Common web …

LongMedBench: Benchmarking Medical Agents for Long-Horizon Clinical Decision-Making

2026-07-10 · Yanzhen Chen, Zihan Xu, Xiaocheng Zhang, Zhiting Fan 외 arxiv

In this work, we introduce LongMedBench, a real-world EHR-based benchmark for long-horizon clinical decision-making. Prior evaluations of LLM-based medical agents have largely emphasized short-context knowledge QA and to…

Information Retrieval