WebShop

The 'WebShop' dataset is a benchmark used to evaluate the performance of reinforcement learning agents in complex task environments.

Papers using WebShop (25)

Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization2026Hindsight Credit Assignment for Long-Horizon LLM Agents2026RSPO: Reward-Swap Policy Optimization for Multi-Turn LLM Agents2026Uncertainty Decomposition for Clarification Seeking in LLM Agents2026Hera: Learning Long-Horizon Coordination for Device-Cloud Collaborative LLM Agents2026SELAUR: Self Evolving LLM Agent via Uncertainty-aware Rewards2026Group-in-Group Policy Optimization for LLM Agent Training2025 · 1 citesSkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning2026SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories2026Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning2026HiMAC: Hierarchical Macro-Micro Learning for Long-Horizon LLM Agents2026Meta-RL Induces Exploration in Language Agents2025Learning Hierarchical Procedural Memory for LLM Agents through Bayesian Selection and Contrastive Refinement2025DEPO: Dual-Efficiency Preference Optimization for LLM Agents2025Reflect before Act: Proactive Error Correction in Language Models2025Enhancing Decision-Making of Large Language Models via Actor-Critic2025Exploring Expert Failures Improves LLM Agent Tuning2025Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents2025Where LLM Agents Fail and How They can Learn From Failures2025Structured Agent Distillation for Large Language Model2025Retrospex: Language Agent Meets Offline Reinforcement Learning Critic2025A Training-free LLM Framework with Interaction between Contextually Related Subtasks in Solving Complex Tasks2025EDGE: Efficient Data Selection for LLM Agents via Guideline Effectiveness2025ReSpAct: Harmonizing Reasoning, Speaking, and Acting Towards Building Large Language Model-Based Conversational AI Agents2024 · 3 citesStateAct: Enhancing LLM Base Agents via Self-prompting and State-tracking2024