mlsanityData to 7 Oct 2026

SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks

arXiv 2305.17390 ↗First posted 27 May 2023cs.CL cs.AI cs.LGcited by 166

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

also in 1 more
Abstract (arXiv)

We introduce SwiftSage, a novel agent framework inspired by the dual-process theory of human cognition, designed to excel in action planning for complex interactive reasoning tasks. SwiftSage integrates the strengths of behavior cloning and prompting large language models (LLMs) to enhance task completion performance. The framework comprises two primary modules: the Swift module, representing fast and intuitive thinking, and the Sage module, emulating deliberate thought processes. The Swift module is a small encoder-decoder LM fine-tuned on the oracle agent's action trajectories, while the Sage module employs LLMs such as GPT-4 for subgoal planning and grounding. We develop a heuristic method to harmoniously integrate the two modules, resulting in a more efficient and robust problem-solving process. In 30 tasks from the ScienceWorld benchmark, SwiftSage significantly outperforms other methods such as SayCan, ReAct, and Reflexion, demonstrating its effectiveness in solving complex interactive tasks.

Key facts. Cited by 166 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 37 of its 41 references that are in the map. First posted on arXiv 27 May 2023.

Builds on

37 of 41 references.

References · 37

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  6. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  7. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  8. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  9. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  10. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  11. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  12. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,528
25 more
  1. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,173
  2. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
  3. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,029
  4. 2017AI2-THOR: An Interactive 3D Environment for Visual AIcited by 850
  5. 2022A Generalist Agentcited by 802
  6. 2018Behavioral Cloning from Observationcited by 482
  7. 2022LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Modelscited by 459
  8. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agentscited by 396
  9. 2023Chameleon: Plug-and-Play Compositional Reasoning with Large Language Modelscited by 352
  10. 2018TextWorld: A Learning Environment for Text-based Gamescited by 304
  11. 2022ScienceWorld: Is your Agent Smarter than a 5th Grader?cited by 298
  12. 2017Thinking Fast and Slow with Deep Learning and Tree Searchcited by 245
  13. 2023OpenAGI: When LLM Meets Domain Expertscited by 196
  14. 2020Keep CALM and Explore: Language Models for Action Generation in Text-based Gamescited by 108
  15. 2021Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformerscited by 93
  16. 2015Deep Reinforcement Learning with a Natural Language Action Spacecited by 88
  17. 2023Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modellingcited by 88
  18. 2021Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoningcited by 85
  19. 2020Graph Constrained Reinforcement Learning for Natural Language Action Spacescited by 80
  20. 2020Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselinescited by 37
  21. 2020How to Motivate Your Dragon: Teaching Goal-Driven Agents to Speak and Act in Fantasy Worldscited by 35
  22. 2022On Grounded Planning for Embodied Tasks with Language Modelscited by 33
  23. 2023Interactive Natural Language Processingcited by 31
  24. 2019Deep Reasoning Networks: Thinking Fast and Slowcited by 12
  25. 2021Thinking Fast and Slow in AI: the Role of Metacognitioncited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 35; 2024: 64; 2025: 39; 2026: 28.

166 papers.

Sort:

By area:

  1. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  2. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  3. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  4. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 814
  5. 2023Cognitive Architectures for Language Agentscited by 422
  6. 2024Understanding the planning of LLM agents: A surveycited by 414
  7. 2025RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learningcited by 357
  8. 2024R-Judge: Benchmarking Safety Risk Awareness for LLM Agentscited by 268
  9. 2023FireAct: Toward Language Agent Fine-tuningcited by 247
  10. 2024Scaling Large Language Model-based Multi-Agent Collaborationcited by 235
  11. 2024Trial and Error: Exploration-Based Trajectory Optimization for LLM Agentscited by 194
  12. 2023ADaPT: As-Needed Decomposition and Planning with Language Modelscited by 172
38 more
  1. 2023Text2Reward: Reward Shaping with Language Models for Reinforcement Learningcited by 153
  2. 2023Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoningcited by 140
  3. 2023OpenAgents: An Open Platform for Language Agents in the Wildcited by 136
  4. 2024Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospectscited by 130
  5. 2024AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathwayscited by 122
  6. 2024The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinismcited by 113
  7. 2024EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithmscited by 109
  8. 2024A Survey on Large Language Model-Based Game Agentscited by 106
  9. 2025Establishing Best Practices for Building Rigorous Agentic Benchmarkscited by 94
  10. 2023T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Stepcited by 91
  11. 2023CLIN: A Continually Learning Language Agent for Rapid Task Adaptation and Generalizationcited by 88
  12. 2024I-Design: Personalized LLM Interior Designercited by 87
  13. 2025Lifelong Learning of Large Language Model based Agents: A Roadmapcited by 78
  14. 2024From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agentscited by 76
  15. 2023Agent Lumos: Unified and Modular Training for Open-Source Language Agentscited by 72
  16. 2023Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agentscited by 72
  17. 2023Lemur: Harmonizing Natural Language and Code for Language Agentscited by 71
  18. 2023Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4cited by 67
  19. 2023LASER: LLM Agent with State-Space Exploration for Web Navigationcited by 66
  20. 2023LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplaycited by 62
  21. 2023Integrating Large Language Model for Improved Causal Discoverycited by 54
  22. 2023Rehearsal: Simulating Conflict to Teach Conflict Resolutioncited by 54
  23. 2023Lyfe Agents: Generative agents for low-cost real-time social interactionscited by 49
  24. 2024MASAI: Modular Architecture for Software-engineering AI Agentscited by 49
  25. 2023Tree-Planner: Efficient Close-loop Task Planning with Large Language Modelscited by 48
  26. 2024Towards Efficient LLM Grounding for Embodied Multi-Agent Collaborationcited by 45
  27. 2025A Survey on the Optimization of Large Language Model-based Agentscited by 45
  28. 2024Emergence of Social Norms in Generative Agent Societies: Principles and Architecturecited by 41
  29. 2024EduAgent: Generative Student Agents in Learningcited by 41
  30. 2024Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Tracescited by 40
  31. 2023Teach AI How to Code: Using Large Language Models as Teachable Agents for Programming Educationcited by 38
  32. 2024Human-AI Collaborative Essay Scoring: A Dual-Process Framework with LLMscited by 38
  33. 2024Prompting Techniques for Reducing Social Bias in LLMs through System 1 and System 2 Cognitive Processescited by 38
  34. 2024Advancing Tool-Augmented Large Language Models: Integrating Insights from Errors in Inference Treescited by 38
  35. 2025Multi-agent Embodied AI: Advances and Future Directionscited by 36
  36. 2024System-1.x: Learning to Balance Fast and Slow Planning with Language Modelscited by 35
  37. 2024Generative AI Agents with Large Language Model for Satellite Networks via a Mixture of Experts Transmissioncited by 34
  38. 2024Agent-Oriented Planning in Multi-Agent Systemscited by 34

50 most cited of 166 All 166 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024PreAct: Prediction Enhances Agent's Planning Ability
  2. 2025Thinking by Doing: Building Efficient World Model Reasoning in LLMs via Multi-turn Interaction
  3. 2025Reflecting with Two Voices: A Co-Adaptive Dual-Strategy Framework for LLM-Based Agent Decision Making
  4. 2026Internalizing LLM Reasoning via Discovery and Replay of Latent Actions
  5. 2023Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration
  6. 2024IDEA: Enhancing the Rule Learning Ability of Large Language Model Agent through Induction, Deduction, and Abduction
  7. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models
  8. 2025DeepAgent: A General Reasoning Agent with Scalable Toolsets