Self-Guided Plan Extraction for Instruction-Following Tasks with Goal-Conditional Reinforcement Learning

ACL ARR 2026 January Submission1626 Authors

Keywords: Instruction Following, Reinforcement Learning, Multimodal RL

Abstract: We introduce SuperIgor, a framework for instruction-following tasks. Unlike prior methods that rely on predefined subtasks, SuperIgor enables a language model to generate and refine high-level plans through a self-learning mechanism, reducing the need for manual dataset annotation. Our approach involves iterative co-training: an RL agent is trained to follow the generated plans, while the language model adapts and modifies these plans based on RL feedback and preferences. This creates a feedback loop where both the agent and the planner improve jointly. We validate our framework in environments with rich dynamics and stochasticity. Results show that SuperIgor agents adhere to instructions more strictly than baseline methods, while also demonstrating strong generalization to previously unseen instructions.

Paper Type: Long

Research Area: Multimodality and Language Grounding to Vision, Robotics and Beyond

Research Area Keywords: multimodality, vision language navigation, spoken language grounding

Contribution Types: Publicly available software and/or pre-trained models, Position papers

Languages Studied: english

Submission Number: 1626