Instruction

Follow this topic Ask about this topic

Momentum

23 papers in the last four weeks, up 77% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 139

All topics

Self-Guided Plan Extraction for Instruction-Following Tasks with Goal-Conditional Reinforcement Learning
Apr 22, 2026Zoya Volovikova, Nikita Sorokin, Dmitriy Lukashevskiy +2Agentic Reinforcement Learning Large Language Model Planning
1AXXX · 2MIRAI
Automatic Slide Updating with User-Defined Dynamic Templates and Natural Language Instructions
Apr 20, 2026Kun Zhou, Jiakai He, Wenmian Yang +3Dynawm Instruction
School of Artificial Intelligence, Beijing Normal University, Beijing, PR China · Institute of Artificial Intelligence and Future Networks, Beijing Normal University, Zhuhai, PR China · Faculty of Arts and Sciences, Beijing Normal University, Zhuhai, PR China +1
SPREG: Structured Plan Repair with Entropy-Guided Test-Time Intervention for Large Language Model Reasoning
Apr 20, 2026Xuan Wang, Yu Ming, Xinhao Zhong +4LLM Reasoning Strategies Instruction
1Meituan
PRISM: Probing Reasoning, Instruction, and Source Memory in LLM Hallucinations
Apr 18, 2026Yuhe Wu, Guangyu Wang, Yuran Chen +6Large Language Model Hallucination Hallucination Detection
HKUST(GZ) · NYUSH · DUFE +2
Reasoning-targeted Jailbreak Attacks on Large Reasoning Models via Semantic Triggers and Psychological Framing
Apr 17, 2026Zehao Wang, Lanjun WangLarge Language Model Jailbreaks Jailbreak Attacks
College of Intelligence and Computing, Tianjin University, Tianjin 300350, China. · School of New Media and Communication, Tianjin University, Tianjin 300072, China. · Shanghai Key Laboratory of Data Science,[cs.LG] Shanghai 200438, China.
Schema-Key Wording as an Instruction Channel in Structured Generation under Constrained Decoding
Apr 16, 2026Yifan LeConstrained Decoding Data Generation
Independent Researcher
Language-Conditioned World Modeling for Visual Navigation
Mar 23, 2026Yifei Dong, Fengyi Wu, Yilong Dai +8Vision-Language Navigation Object Goal Navigation
University of Washington · National University of Singapore · Clemson University +2
Altered Thoughts, Altered Actions: Reasoning Chain as Control Surface for a Vision-Language-Action Policy
Mar 13, 2026Tuan Duong Trinh, Basim Azam, Mohammed Ishaq Ansari +2Generalizable Vision-Language-Action Policies Robot Policies
University of Melbourne Parkville, VIC, Australia
QAQ: Bidirectional Semantic Coherence for Selecting High-Quality Synthetic Code Instructions
Mar 12, 2026Jiayin Lei, Ming Ma, Yunxi Duan +2Synthetic Data Data Quality
Beijing University of Technology, Beijing, 100124, China · Institute of Neuroscience, State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology, Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Shanghai, 200031, China · University of Chinese Academy of Sciences, Beijing, 100049, China +1
PhotoAgent: Exploratory Visual Aesthetic Planning with Large Vision Models
Feb 26, 2026Mingde Yao, Zhiyuan You, King-Man Tam +2Image Editing Aesthetics
MMLab, CUHK · CPII under InnoHK · Institute of Science Tokyo +2
Patches of Nonlinearity: Instruction Vectors in Large Language Models
Feb 8, 2026Irina Bigoulaeva, Jonas Rohweder, Subhabrata Dutta +1Instruction-Tuned Models Mechanistic Interpretability
Ubiquitous Knowledge Processing Lab (UKP Lab) · Department of Computer Science, Technical University of Darmstadt · National Research Center for Applied Cybersecurity ATHENE, Germany
FineInstructions: Scaling Synthetic Instructions to Pre-Training Scale
Jan 29, 2026Ajay Patel, Colin Raffel, Chris Callison-BurchPretraining Instruction
University of Pennsylvania · University of Toronto · Vector Institute +1
From Instruction to Event: Sound-Triggered Mobile Manipulation
Jan 29, 2026Hao Ju, Shaofei Huang, Hongyu Li +4Real-World Manipulation Tasks Action Expert
University of Macau · Beihang University · Hefei University of Technology
GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI Grounding
Nov 2, 2025Shijie Zhou, Viet Dac Lai, Hao Tan +4Graphical User Interface Multimodal Large Language Models
University at Buffalo, USA · Adobe Research, USA
Instruction Retrieval at Inference Time for Small Language Models
Oct 15, 2025Kenan Alkiek, David Jurgens, Vinod VydiswaranInstruction-Tuned Models Instruction
School of Information University of Michigan Ann Arbor, MI 48109, USA
TIIF-Bench: How Does Your T2I Model Follow Your Instructions?
Jun 2, 2025Xinyu Wei, Jinrui Zhang, Zeqing Wang +4Modern Text-To-Image Models Text-To-Image
The Hong Kong Polytechnic University · OPPO Research Institute · Tsinghua University
RECAST: Expanding the Boundaries of LLMs' Complex Instruction Following with Multi-Constraint Data
May 25, 2025Zhengkang Guo, Wenhao Liu, Mingchen Xie +13Instruction Recast
College of Computer Science and Artificial Intelligence, Fudan University · Xiaohongshu Inc.
ETHER: Aligning Emergent Communication for Hindsight Experience Replay
Jul 28, 2023Kevin Yandoka Denamganaï, Daniel Hernandez, Ozan Vardal +2Goal-Conditioned Reinforcement Learning Hindsight
Department of Computer Science University of York York, UK
How LLMs Follow Instructions: Skillful Coordination, Not a Universal Mechanism
Date pendingElisabetta Rocchetti, Alfio FerraraInstruction Tuning Instruction-Tuned Models
Department of Computer Science, Università degli Studi di Milano

Apr 22, 2026, cs.AIJ/K move · Enter open · S save

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

Zoya Volovikova, Nikita Sorokin, Dmitriy Lukashevskiy, Aleksandr Panov+1

1AXXX · 2MIRAI

Agentic Reinforcement Learning Large Language Model Planning Instruction Goal-Conditioned Reinforcement Learning Iterative Co-Training Large Language Model Adaptation

Open paper AskPDF 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.

Momentum

Related topics

Latest papers 139