Copertina

Odysseys: Benchmarking Web Agents on Realistic Long Horizon Tasks

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Jang, Lawrence Keunho, Koh, Jing Yu, Fried, Daniel, Salakhutdinov, Ruslan
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks
di: Koh, Jing Yu, et al.
Pubblicazione: (2024)

Multi-Agent Computer Use
di: Koh, Jing Yu, et al.
Pubblicazione: (2026)

Tree Search for Language Model Agents
di: Koh, Jing Yu, et al.
Pubblicazione: (2024)

Dissecting Adversarial Robustness of Multimodal LM Agents
di: Wu, Chen Henry, et al.
Pubblicazione: (2024)

Towards a Realistic Long-Term Benchmark for Open-Web Research Agents
di: Mühlbacher, Peter, et al.
Pubblicazione: (2024)

WebArena: A Realistic Web Environment for Building Autonomous Agents
di: Zhou, Shuyan, et al.
Pubblicazione: (2023)

WebChoreArena: Evaluating Web Browsing Agents on Realistic Tedious Web Tasks
di: Miyai, Atsuyuki, et al.
Pubblicazione: (2025)

Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks
di: Dalal, Murtaza, et al.
Pubblicazione: (2024)

AgentFold: Long-Horizon Web Agents with Proactive Context Management
di: Ye, Rui, et al.
Pubblicazione: (2025)

OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web
di: Kapoor, Raghav, et al.
Pubblicazione: (2024)

Evaluating Language-Model Agents on Realistic Autonomous Tasks
di: Kinniment, Megan, et al.
Pubblicazione: (2023)

Capable but Unreliable: Canonical Path Deviation as a Causal Mechanism of Agent Failure in Long-Horizon Tasks
di: Lee, Wilson Y.
Pubblicazione: (2026)

Training a Generally Curious Agent
di: Tajwar, Fahim, et al.
Pubblicazione: (2025)

RealWebAssist: A Benchmark for Long-Horizon Web Assistance with Real-World Users
di: Ye, Suyu, et al.
Pubblicazione: (2025)

POPE: Learning to Reason on Hard Problems via Privileged On-Policy Exploration
di: Qu, Yuxiao, et al.
Pubblicazione: (2026)

Mem-T: Densifying Rewards for Long-Horizon Memory Agents
di: Yue, Yanwei, et al.
Pubblicazione: (2026)

LHAW: Controllable Underspecification for Long-Horizon Tasks
di: Pu, George, et al.
Pubblicazione: (2026)

Scaling Long-Horizon LLM Agent via Context-Folding
di: Sun, Weiwei, et al.
Pubblicazione: (2025)

Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents
di: Wang, Jiawei, et al.
Pubblicazione: (2025)

Self-Regulation and Requesting Interventions
di: Min, So Yeon, et al.
Pubblicazione: (2025)

Intrinsic Language-Guided Exploration for Complex Long-Horizon Robotic Manipulation Tasks
di: Triantafyllidis, Eleftherios, et al.
Pubblicazione: (2023)

Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe
di: Wu, Xixi, et al.
Pubblicazione: (2026)

Memex(RL): Scaling Long-Horizon LLM Agents via Indexed Experience Memory
di: Wang, Zhenting, et al.
Pubblicazione: (2026)

The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution
di: Li, Junlong, et al.
Pubblicazione: (2025)

Hybrid-Gym: Training Coding Agents to Generalize Across Tasks
di: Xie, Yiqing, et al.
Pubblicazione: (2026)

OdysseyBench: Evaluating LLM Agents on Long-Horizon Complex Office Application Workflows
di: Wang, Weixuan, et al.
Pubblicazione: (2025)

RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems
di: Qu, Yuxiao, et al.
Pubblicazione: (2025)

Recursive Models for Long-Horizon Reasoning
di: Yang, Chenxiao, et al.
Pubblicazione: (2026)

Dive into the Agent Matrix: A Realistic Evaluation of Self-Replication Risk in LLM Agents
di: Zhang, Boxuan, et al.
Pubblicazione: (2025)

Merging Methods for Multilingual Knowledge Editing for Large Language Models: An Empirical Odyssey
di: Lee, Kunil, et al.
Pubblicazione: (2026)

HINT-SD: Targeted Hindsight Self-Distillation for Long-Horizon Agents
di: Yeo, Woongyeng, et al.
Pubblicazione: (2026)

OdysseyArena: Benchmarking Large Language Models For Long-Horizon, Active and Inductive Interactions
di: Xu, Fangzhi, et al.
Pubblicazione: (2026)

WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning
di: Wei, Zhepei, et al.
Pubblicazione: (2025)

WEBSERV: A Full-Stack and RL-Ready Web Environment for Training Web Agents at Scale
di: Lu, Yuxuan, et al.
Pubblicazione: (2025)

Exposing Limitations of Language Model Agents in Sequential-Task Compositions on the Web
di: Furuta, Hiroki, et al.
Pubblicazione: (2023)

Large Language Models Can Self-Improve At Web Agent Tasks
di: Patel, Ajay, et al.
Pubblicazione: (2024)

AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning
di: Xi, Zhiheng, et al.
Pubblicazione: (2025)

EconWebArena: Benchmarking Autonomous Agents on Economic Tasks in Realistic Web Environments
di: Liu, Zefang, et al.
Pubblicazione: (2025)

Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning
di: Qu, Yuxiao, et al.
Pubblicazione: (2025)

HEMM: Holistic Evaluation of Multimodal Foundation Models
di: Liang, Paul Pu, et al.
Pubblicazione: (2024)