Dual-Process Reasoning

Latest papers

9 papers2 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

MemDuet: Learning Dual-Process Memory for Long-Context Reasoning
Oct 14, 2026Jiangcheng Song, Haodong Jing, Yulin Mu +7Dual-Process Reasoning Memory-Augmented Language Model Agents
State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University · Faculty of Electronic and Information Engineering, Xi’an Jiaotong University · Imperial College London
JevGPT: Thinking Fast and Slow in Autonomous Research
Oct 13, 2026Yasheng Sun, Yanning Dai, Yimeng Chen +9Dual-Process Reasoning Autonomous Research Agents
King Abdullah University of Science and Technology (KAUST)
A Dual-Process Perspective on Nudge Susceptibility in LLM-Based GUI Agents
Sep 17, 2026Haya Halimeh, Sascha Kaltenpoth, Kevin Bösch +1Dual-Process Reasoning GUI Agents
Information Systems, Paderborn University, Paderborn, Germany.
Can Hallucinations Be Useful? Solving Multi-Hop Questions With SLMs By Chaining System-I/II Reasoning
May 26, 2026Saptarshi Sengupta, Suhang WangMulti-Hop QA LLM Hallucination Mitigation
The Pennsylvania State University
Reflecti-Mate: A Conversational Agent for Adaptive Decision-Making Support Through System 1 and System 2 Thinking
May 21, 2026Morita Tarvirdians, Senthil Chandrasegaran, Hayley Hung +2AI-Assisted Decision Making Dual-Process Reasoning
TU Delft Delft, The Netherlands · TU Delft/Leiden University Delft/Leiden, The Netherlands
Enhancing Self-Supervised Talking Head Forgery Detection via a Training-Free Dual-System Framework
May 5, 2026Ke Liu, Jiwei Wei, Shuchang Zhou +5Self-Supervised Learning Dual-Process Reasoning
University of Electronic Science and Technology of China Chengdu, China · Hainan University Haikou, China
The role of System 1 and System 2 semantic memory structure in human and LLM biases
Apr 14, 2026Katherine Abramski, Giulio Rossetti, Massimo StellaDual-Process Reasoning Cognitive Modeling
Department of Computer Science, University of Pisa, Italy · Institute of Information Science and Technologies - National Research Council, Italy · CogNosco Lab, Department of Psychology and Cognitive Science, University of Trento, Italy
A Theory of Appropriateness That Accounts for Norms of Rationality
Mar 14, 2026Joel Z. Leibo, Alexander Sasha Vezhnevets, Manfred Diaz +10Dual-Process Reasoning
Google DeepMind · Mila - Québec AI Institute · University of Toronto +4
Reasoning in machine vision by learning fast and slow thinking
Jun 27, 2025Shaheer U. Saeed, Yipei Wang, Veeru Kasivisvanathan +4Visual Reasoning Dual-Process Reasoning
Centre for Bioengineering, Queen Mary University of London, London, UK · Digital Environment Research Institute, Queen Mary University of London, London, UK · School of Engineering and Materials Science, Queen Mary University of London, London, UK +6

Oct 14, 2026J/K move · Enter open · S save

MemDuet: Learning Dual-Process Memory for Long-Context Reasoning

Jiangcheng Song, Haodong Jing, Yulin Mu, Lesong Tao+6

State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University · Faculty of Electronic and Information Engineering, Xi’an Jiaotong University · Imperial College London

Dual-Process Reasoning Memory-Augmented Language Model Agents Long-Context Inference LLM Inference Acceleration RL for Language Model Reasoning

Open paper AskPDF arXiv

Reasoning over infinitely long documents is becoming a reality with recurrent memory agents. However, increasing context length exacerbates the trade-off between reasoning performance and inference efficiency. Inspired by Kahneman's account of fast and slow thinking, we propose MemDuet, a dual-process memory framework that learns to coordinate a small language model for fast, parallel evidence selection from raw context chunks (System 1) with a large language model for memory-update verification and memory updates in document order (System 2). We train MemDuet in three stages: supervised fine-tuning of System 1 for evidence selection, Group Relative Policy Optimization (GRPO) of System 2 for verification and memory rewriting, and joint optimization of both policies to coordinate selection and updating for long-context reasoning. Experiments on diverse long-context reasoning benchmarks (RULER-HQA, LongBench v2, and 2WikiMultiHopQA) demonstrate a favorable accuracy-efficiency trade-off as context length grows. Averaged across evaluation settings on the three datasets, MemDuet achieves an end-to-end inference speedup of 9.74x and an output-token reduction of 73.91% relative to RL-MemAgent.