ALFWorld

ALFWorld is a benchmark dataset that evaluates agent systems' performance in executing tasks using textual skills, measuring success rates across seen and unseen splits while minimizing context overhead.

Papers using ALFWorld (46)

Reinforcement World Model Learning for LLM-based Agents2026MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution2026Hindsight Credit Assignment for Long-Horizon LLM Agents2026No Time Like the Present: Agentic Test-Time Training for LLM Agents2026RSPO: Reward-Swap Policy Optimization for Multi-Turn LLM Agents2026ACCORD: Action-Conditioned Contextual Grounding for Language Agents2026Uncertainty Decomposition for Clarification Seeking in LLM Agents2026The Interplay of Harness Design and Post-Training in LLM Agents2026DuoMem: Towards Capable On-Device Memory Agents via Dual-Space Distillation2026Hera: Learning Long-Horizon Coordination for Device-Cloud Collaborative LLM Agents2026Spinning Straw into Gold: Relabeling LLM Agent Trajectories in Hindsight for Successful Demonstrations2026SELAUR: Self Evolving LLM Agent via Uncertainty-aware Rewards2026Group-in-Group Policy Optimization for LLM Agent Training2025 · 1 citesBlueprint First, Model Second: A Framework for Deterministic LLM Workflow2025Selective Memory Retention for Long-Horizon LLM Agents2026AgentOCR: Reimagining Agent History via Optical Self-Compression2026Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Training for LLM Agents2026Accurate Failure Prediction in Agents Does Not Imply Effective Failure Prevention2026SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning2026LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents2026Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning2026Hierarchical Reinforcement Learning with Augmented Step-Level Transitions for LLM Agents2026SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization2026HiMAC: Hierarchical Macro-Micro Learning for Long-Horizon LLM Agents2026MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents2026Think Fast and Slow: Step-Level Cognitive Depth Adaptation for LLM Agents2026Reflecting with Two Voices: A Co-Adaptive Dual-Strategy Framework for LLM-Based Agent Decision Making2025Learning Hierarchical Procedural Memory for LLM Agents through Bayesian Selection and Contrastive Refinement2025SkillGen: Learning Domain Skills for In-Context Sequential Decision Making2025Reflect before Act: Proactive Error Correction in Language Models2025Memory-Driven Self-Improvement for Decision Making with Large Language Models2025Enhancing Decision-Making of Large Language Models via Actor-Critic2025Memp: Exploring Agent Procedural Memory2025GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators2025GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training2025WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents2025Self-Generated In-Context Examples Improve LLM Agents for Sequential Decision-Making Tasks2025Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents2025Where LLM Agents Fail and How They can Learn From Failures2025Self-Generated In-Context Examples Improve LLM Agents for Sequential Decision-Making Tasks2025Cache-Efficient Posterior Sampling for Reinforcement Learning with LLM-Derived Priors Across Discrete and Continuous Domains2025Structured Agent Distillation for Large Language Model2025Retrospex: Language Agent Meets Offline Reinforcement Learning Critic2025ReSpAct: Harmonizing Reasoning, Speaking, and Acting Towards Building Large Language Model-Based Conversational AI Agents2024 · 3 citesRAG-Modulo: Solving Sequential Tasks using Experience, Critics, and Language Models2024StateAct: Enhancing LLM Base Agents via Self-prompting and State-tracking2024