EmbodiSkill uses skill-aware reflection on execution trajectories to update skills in embodied agents, achieving 93.28% success on ALFWorld with a frozen Qwen3.5-27B model, outperforming direct GPT-5.2 use by 31.58%.
ALFWorld: Aligning text and embodied environments for interactive learning
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
dataset 2
background 1
citation-polarity summary
fields
cs.AI 3years
2026 3representative citing papers
CLI agents trained with RL benefit from selective observation via σ-Reveal and structured credit assignment via A³ that leverages AST action sub-chains and trajectory margins.
citing papers explorer
-
EmbodiSkill: Skill-Aware Reflection for Self-Evolving Embodied Agents
EmbodiSkill uses skill-aware reflection on execution trajectories to update skills in embodied agents, achieving 93.28% success on ALFWorld with a frozen Qwen3.5-27B model, outperforming direct GPT-5.2 use by 31.58%.
-
Learning CLI Agents with Structured Action Credit under Selective Observation
CLI agents trained with RL benefit from selective observation via σ-Reveal and structured credit assignment via A³ that leverages AST action sub-chains and trajectory margins.
- Evidence Over Plans: Online Trajectory Verification for Skill Distillation