paper-with-me

홈 › Papers

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

2026-04-22 · Zoya Volovikova, Nikita Sorokin, Dmitriy Lukashevskiy, Aleksandr Panov, Alexey Skrynnik 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.

📄 PDF Abstract BibTeX arXiv:2604.20601

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Pragmatic Instruction Following and Goal Assistance via Cooperative Language-Guided Inverse Planning

2024-02-27 · Tan Zhi-Xuan, Lance Ying, Vikash Mansinghka, Joshua B. Tenenbaum

People often give instructions whose meaning is ambiguous without further context, expecting that their actions or goals will disambiguate their intentions. How can we build assistive agents that follow such instructions…

Bayesian InferenceInstruction Following

EIPE-text: Evaluation-Guided Iterative Plan Extraction for Long-Form Narrative Text Generation

2023-10-12 · Wang You, Wenshan Wu, Yaobo Liang, Shaoguang Mao 외

Plan-and-Write is a common hierarchical approach in long-form narrative text generation, which first creates a plan to guide the narrative writing. Following this approach, several studies rely on simply prompting large …

FormIn-Context LearningText Generation

RePlan-Bot: Multi-Level Replanning for Embodied Instruction Following

2026-05-25 · Xicheng Gong, Guozheng Sun, Peiran Xu, Yadong Mu arxiv

Embodied instruction following (EIF) requires agents to understand and execute complex natural language commands within interactive 3D environments. Despite recent advances, existing methods often fail in long-horizon pl…

Instruction FollowingObject Localization

Socratic Planner: Self-QA-Based Zero-Shot Planning for Embodied Instruction Following

2024-04-21 · Suyeon Shin, Sujin jeon, Junghyun Kim, Gi-Cheon Kang 외

Embodied Instruction Following (EIF) is the task of executing natural language instructions by navigating and interacting with objects in interactive environments. A key challenge in EIF is compositional task planning, t…

In-Context LearningInstruction FollowingLanguage ModelingLanguage Modelling+2

From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning

2023-08-23 · Ming Li, Yong Zhang, Zhitao Li, Jiuhai Chen 외

In the realm of Large Language Models (LLMs), the balance between instruction data quality and quantity is a focal point. Recognizing this, we introduce a self-guided methodology for LLMs to autonomously discern and sele…

Instruction Following