mlsanityData to 7 Oct 2026

Agents Thinking Fast and Slow: A Talker-Reasoner Architecture

arXiv 2410.08328 ↗First posted 10 Oct 2024cs.AI cs.CL cs.LGcited by 35

On the map: LLM reasoning → Reasoning for agents, planning and code

also in 1 more
Abstract (arXiv)

Large language models have enabled agents of all kinds to interact with users through natural conversation. Consequently, agents now have two jobs: conversing and planning/reasoning. Their conversational responses must be informed by all available information, and their actions must help to achieve goals. This dichotomy between conversing with the user and doing multi-step reasoning and planning can be seen as analogous to the human systems of "thinking fast and slow" as introduced by Kahneman. Our approach is comprised of a "Talker" agent (System 1) that is fast and intuitive, and tasked with synthesizing the conversational response; and a "Reasoner" agent (System 2) that is slower, more deliberative, and more logical, and is tasked with multi-step reasoning and planning, calling tools, performing actions in the world, and thereby producing the new agent state. We describe the new Talker-Reasoner architecture and discuss its advantages, including modularity and decreased latency. We ground the discussion in the context of a sleep coaching agent, in order to demonstrate real-world relevance.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 29 of its 40 references that are in the map. First posted on arXiv 10 Oct 2024.

Builds on

29 of 40 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Language Models, Agent Models, and World Models: The LAW for Machine Reasoning and Planning8 Dec
  2. 2023Reasoning with Language Model is Planning with World Model24 May

Other references · 27

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  5. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  6. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  7. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  8. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  9. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  10. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  11. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  12. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
15 more
  1. 2018World Modelscited by 1,444
  2. 2022LaMDA: Language Models for Dialog Applicationscited by 1,218
  3. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,173
  4. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,172
  5. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agentscited by 396
  6. 2023Auto-GPT for Online Decision Making: Benchmarks and Additional Opinionscited by 250
  7. 2024Reinforcement learningcited by 236
  8. 2024Self-Discover: Large Language Models Self-Compose Reasoning Structurescited by 108
  9. 2023Large Language Models as Generalizable Policies for Embodied Taskscited by 86
  10. 2023How FaR Are Large Language Models From Agents with Theory-of-Mind?cited by 75
  11. 2023LLM-Assist: Enhancing Closed-Loop Planning with Language-Based Reasoningcited by 59
  12. 2018Learning Actionable Representations with Goal-Conditioned Policiescited by 53
  13. 2022Large Language Models can Implement Policy Iterationcited by 31
  14. 2023Interactive Planning Using Large Language Models for Partially Observable Robotics Taskscited by 27
  15. 2024Empowering Large Language Model Agents through Action Learningcited by 20

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 21; 2026: 12.

35 papers.

Sort:

By area:

  1. 2025Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Modelscited by 89
  2. 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agentscited by 40
  3. 2024SOLAMI: Social Vision-Language-Action Modeling for Immersive Interaction with 3D Autonomous Characterscited by 18
  4. 2025A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Lawcited by 18
  5. 2026A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applicationscited by 17
  6. 2024Enhancing LLM Reasoning with Multi-Path Collaborative Reactive and Reflection agentscited by 15
  7. 2025Real-Time Reasoning Agents in Evolving Environmentscited by 13
  8. 2025UXAgent: A System for Simulating Usability Testing of Web Design with LLM Agentscited by 10
  9. 2025Dynamic Speculative Agent Planningcited by 10
  10. 2025Agentic Knowledgeable Self-awarenesscited by 8
  11. 2025Fast-Slow-Thinking: Complex Task Solving with Large Language Modelscited by 7
  12. 2025DSADF: Thinking Fast and Slow for Decision Makingcited by 6
23 more
  1. 2025Strategize Globally, Adapt Locally: A Multi-Turn Red Teaming Agent with Dual-Level Learningcited by 5
  2. 2025Sleepless Nights, Sugary Days: Creating Synthetic Users with Health Conditions for Realistic Coaching Agent Interactionscited by 4
  3. 2025UserCentrix: An Agentic Memory-augmented AI Framework for Smart Spacescited by 4
  4. 2025Interact, Instruct to Improve: A LLM-Driven Parallel Actor-Reasoner Framework for Enhancing Autonomous Vehicle Interactionscited by 3
  5. 2025BELLE: A Bi-Level Multi-Agent Reasoning Framework for Multi-Hop Question Answeringcited by 3
  6. 2025AgentCoMa: A Compositional Benchmark Mixing Commonsense and Mathematical Reasoning in Real-World Scenarioscited by 3
  7. 2026AIvilization v0: Toward Large-Scale Artificial Social Simulation with a Unified Agent Architecture and Adaptive Agent Profilescited by 3
  8. 2025Let's Get You Hired: A Job Seeker's Perspective on Multi-Agent Recruitment Systems for Explaining Hiring Decisionscited by 2
  9. 2025SimuPanel: A Novel Immersive Multi-Agent System to Simulate Interactive Expert Panel Discussioncited by 2
  10. 2025Thinking While Speaking: Inference-Time Knowledge Transfer for Responsive and Intelligent Conversational Voice Agentscited by 2
  11. 2025Run, Ruminate, and Regulate: A Dual-process Thinking System for Vision-and-Language Navigationcited by 2
  12. 2025iSHIFT: Lightweight Slow-Fast GUI Agent with Adaptive Perceptioncited by 2
  13. 2026DuCCAE: A Hybrid Engine for Immersive Conversation via Collaboration, Augmentation, and Evolutioncited by 1
  14. 2026VoiceMem: Streaming Dual-Brain Memory for Real-Time Interactioncited by 1
  15. 2025Polymorphic Combinatorial Frameworks (PCF): Guiding the Design of Mathematically-Grounded, Adaptive AI Agentscited by 0
  16. 2025Prepared mind, fast response: A temporal decoupling framework for adaptive knowledge orchestration in open-domain dialoguecited by 0
  17. 2026MeetBench-XL: Calibrated Multi-Dimensional Evaluation and Learned Dual-Policy Agents for Real-Time Meetingscited by 0
  18. 2026Enhancing Mathematical Problem Solving in LLMs through Execution-Driven Reasoning Augmentationcited by 0
  19. 2026KC-Agent: A Dual-Process Cognitive Architecture for Efficient ML Model Improvementcited by 0
  20. 2026STQA: A Benchmark for Stock-Focused Tabular Question Answering over Historical and Forecasted Datacited by 0
  21. 2026State-Grounded Conditioning: Wrapping User-Facing LLM Agents Where Direction Depends on Live Statecited by 0
  22. 2026OverForge: Reasoning Through Strategies and Tactics Helps Cooperative Lifelong Adaptationcited by 0
  23. 2026System Switch: When Should a Fast Decision Model Stop and Think?cited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023DUMA: a Dual-Mind Conversational Agent with Fast and Slow Thinking
  2. 2025A Desideratum for Conversational Agents: Capabilities, Challenges, and Future Directions
  3. 2026Never Stop Thinking: Continuous-Time Language Agents
  4. 2026MINDSET: Energy-based Schema Evolution for Long Conversational Agent Memory
  5. 2024Controllable and Reliable Knowledge-Intensive Task-Oriented Conversational Agents with Declarative Genie Worksheets
  6. 2025Overhearing LLM Agents: A Survey, Taxonomy, and Roadmap
  7. 2025AsyncVoice Agent: Real-Time Explanation for LLM Planning and Reasoning
  8. 2026Goal-Oriented Reasoning for RAG-based Memory in Conversational Agentic LLM Systems