paper-with-me

Papers

OdysseyBench: Evaluating LLM Agents on Long-Horizon Complex Office Application Workflows

2025-08-12 · Weixuan Wang, Dongge Han, Daniel Madrigal Diaz, Jin Xu, Victor Rühle, Saravan Rajmohan arxiv

Autonomous agents powered by large language models (LLMs) are increasingly deployed in real-world applications requiring complex, long-horizon workflows. However, existing benchmarks predominantly focus on atomic tasks that are self-contained and independent, failing to capture the long-term contextual dependencies and multi-interaction coordination required in realistic scenarios. To address this gap, we introduce OdysseyBench, a comprehensive benchmark for evaluating LLM agents on long-horizon workflows across diverse office applications including Word, Excel, PDF, Email, and Calendar. Our benchmark comprises two complementary splits: OdysseyBench+ with 300 tasks derived from real-world use cases, and OdysseyBench-Neo with 302 newly synthesized complex tasks. Each task requires agent to identify essential information from long-horizon interaction histories and perform multi-step reasoning across various applications. To enable scalable benchmark creation, we propose HomerAgents, a multi-agent framework that automates the generation of long-horizon workflow benchmarks through systematic environment exploration, task generation, and dialogue synthesis. Our extensive evaluation demonstrates that OdysseyBench effectively challenges state-of-the-art LLM agents, providing more accurate assessment of their capabilities in complex, real-world contexts compared to existing atomic task benchmarks. We believe that OdysseyBench will serve as a valuable resource for advancing the development and evaluation of LLM agents in real-world productivity scenarios. In addition, we release OdysseyBench and HomerAgents to foster research along this line.

📄 PDF Abstract BibTeX arXiv:2508.09124

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

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…

RetailBench: Evaluating Long-Horizon Autonomous Decision-Making and Strategy Stability of LLM Agents in Realistic Retail Environments

2026-03-17 · Linghua Zhang, Jun Wang, Jingtong Wu, Zhisong Zhang arxiv

Large language model (LLM) agents have made rapid progress on short-horizon, well-scoped tasks, yet their ability to sustain coherent decisions in dynamic long-horizon environments remains uncertain. We introduce RetailB…

Decision Making

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

2026-06-11 · Jiarui Zhao, Rongzhi Zhang, Lingchuan Liu, Hao Yang 외 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 g…

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…

SidConArena: An Environment Evaluating Agents in Open-Ended,Positive-Sum Bargaining Game

2026-06-24 · Yeqi Feng, Yuxin Chen, Tianxing He arxiv

Evaluating LLM agents requires dynamic environments that go beyond static reasoning and zero-sum games. Real-world economic interaction is often open-ended and mixed-motive: agents must negotiate, create positive-sum sur…