WebShop

The 'WebShop' dataset/benchmark contains a collection of multi-turn interactions designed to evaluate the performance of reinforcement learning algorithms in training large language models as autonomous agents.

Papers using WebShop (38)

Retrospex: Language Agent Meets Offline Reinforcement Learning Critic2025 · 7 citesBeyond Policy Optimization: A Data Curation Flywheel for Sparse-Reward Long-Horizon Planning2025 · 3 cites3SPO: State-Score-Supervised Policy Optimization for LLM Agents2026Semantic Consistency Policy Optimization for Reinforcement Learning of LLM Agents2026Hera: Learning Long-Horizon Coordination for Device-Cloud Collaborative LLM Agents2026Turn-PPO: Turn-Level Advantage Estimation with PPO for Improved Multi-Turn RL in Agentic LLMs2025Graph-Enhanced Policy Optimization in LLM Agent Training2025 · 2 citesLearn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning2025 · 1 citesGroup-in-Group Policy Optimization for LLM Agent Training2025 · 1 citesSIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training2026When Denser Credit Is Not Enough: Evidence-Calibrated Policy Optimization for Long-Horizon LLM Agent Training2026T$^2$PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning2026Milestone-Guided Policy Learning for Long-Horizon Language Agents2026Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning2026StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction2026GAGPO: Generalized Advantage Grouped Policy Optimization2026Self-Distilled Agentic Reinforcement Learning2026CLEAR: Context Augmentation from Contrastive Learning of Experience via Agentic Reflection2026HiMAC: Hierarchical Macro-Micro Learning for Long-Horizon LLM Agents2026Hindsight Credit Assignment for Long-Horizon LLM Agents2026Dynamic Dual-Granularity Skill Bank for Agentic RL2026SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning2026TSR: Trajectory-Search Rollouts for Multi-Turn RL of LLM Agents2026HiPER: Hierarchical Reinforcement Learning with Explicit Credit Assignment for Large Language Model Agents2026Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Tasks2026Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization2026CuES: A Curiosity-driven and Environment-grounded Synthesis Framework for Agentic RL2025Meta-RL Induces Exploration in Language Agents2025SALT: Step-level Advantage Assignment for Long-horizon Agents via Trajectory Graph2025DeepAgent: A General Reasoning Agent with Scalable Toolsets2025Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents2025Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success2025Enhancing Decision-Making of Large Language Models via Actor-Critic2025SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attribution2025RRO: LLM Agent Optimization Through Rising Reward Trajectories2025Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents2024 · 6 citesAn Extremely Data-efficient and Generative LLM-based Reinforcement Learning Agent for Recommenders2024Enhancing Decision-Making for LLM Agents via Step-Level Q-Value Models2024