AppWorld

The 'AppWorld' dataset is a benchmark used to evaluate the effectiveness of context engineering approaches for large language model agents in decision-making tasks.

Papers using AppWorld (11)

Hera: Learning Long-Horizon Coordination for Device-Cloud Collaborative LLM Agents2026Reinforcement Learning for Long-Horizon Interactive LLM Agents2025 · 2 citesKeep Policy Gradient in Charge: Sibling-Guided Credit Distillation for Long-Horizon Tool-Use Agents2026Learning and Reusing Policy Decompositions for Hierarchical Generalized Planning with LLM Agents2026HINT-SD: Targeted Hindsight Self-Distillation for Long-Horizon Agents2026CLEAR: Context Augmentation from Contrastive Learning of Experience via Agentic Reflection2026Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents2026SeeUPO: Sequence-Level Agentic-RL with Convergence Guarantees2026CuES: A Curiosity-driven and Environment-grounded Synthesis Framework for Agentic RL2025Reinforcement Learning for Self-Improving Agent with Skill Library2025SALT: Step-level Advantage Assignment for Long-horizon Agents via Trajectory Graph2025