mlsanityData to 14 Oct 2026

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

arXiv 2604.20601 ↗First posted 22 Apr 2026cs.AI cs.CLcited by 0

On the map: Deep reinforcement learning methods → RL training of language and agent models

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL training of language and agent models, one of 15 directions in Deep reinforcement learning methods. Builds on 5 of its 31 references that are in the map. First posted on arXiv 22 Apr 2026.

Builds on

5 of 31 references.

References · 5

  1. 2018BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learningcited by 244
  2. 2024MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World Controlcited by 53
  3. 2025SIMA 2: A Generalist Embodied Agent for Virtual Worldscited by 31
  4. 2019CraftAssist: A Framework for Dialogue-enabled Interactive Agentscited by 28
  5. 2025Adapting Interleaved Encoders with PPO for Language-Guided Reinforcement Learning in BabyAIcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Learning Instruction-Following Policies through Open-Ended Instruction Relabeling with Large Language Models
  2. 2018Guiding Policies with Language via Meta-Learning
  3. 2025Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models' Instruction Following
  4. 2025Towards Continuous Intelligence Growth: Self-Training, Continual Learning, and Dual-Scale Memory in SuperIntelliAgent
  5. 2025Instructions are all you need: Self-supervised Reinforcement Learning for Instruction Following
  6. 2025InstructRAG: Leveraging Retrieval-Augmented Generation on Instruction Graphs for LLM-Based Task Planning
  7. 2026SEIF: Self-Evolving Reinforcement Learning for Instruction Following
  8. 2018Learning to Understand Goal Specifications by Modelling Reward