Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
131 tokens/sec
GPT-4o
10 tokens/sec
Gemini 2.5 Pro Pro
47 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Lyfe Agents: Generative agents for low-cost real-time social interactions (2310.02172v1)

Published 3 Oct 2023 in cs.HC, cs.AI, and cs.LG

Abstract: Highly autonomous generative agents powered by LLMs promise to simulate intricate social behaviors in virtual societies. However, achieving real-time interactions with humans at a low computational cost remains challenging. Here, we introduce Lyfe Agents. They combine low-cost with real-time responsiveness, all while remaining intelligent and goal-oriented. Key innovations include: (1) an option-action framework, reducing the cost of high-level decisions; (2) asynchronous self-monitoring for better self-consistency; and (3) a Summarize-and-Forget memory mechanism, prioritizing critical memory items at a low cost. We evaluate Lyfe Agents' self-motivation and sociability across several multi-agent scenarios in our custom LyfeGame 3D virtual environment platform. When equipped with our brain-inspired techniques, Lyfe Agents can exhibit human-like self-motivated social reasoning. For example, the agents can solve a crime (a murder mystery) through autonomous collaboration and information exchange. Meanwhile, our techniques enabled Lyfe Agents to operate at a computational cost 10-100 times lower than existing alternatives. Our findings underscore the transformative potential of autonomous generative agents to enrich human social experiences in virtual worlds.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (53)
  1. Jacob Andreas. Language models as agent models, 2022.
  2. Human memory: A proposed system and its control processes. In Psychology of learning and motivation, volume 2, pp.  89–195. Elsevier, 1968.
  3. The option-critic architecture. In Proceedings of the AAAI conference on artificial intelligence, volume 31, 2017.
  4. Alan D Baddeley and J Graham. Hitch. 1974. working memory. The psychology of learning and motivation, 8:47–89, 1974.
  5. Experience grounds language, 2020.
  6. Forgetting in memory models: Arguments against trace decay and consolidation failure. Forgetting, pp.  49–75, 2010.
  7. Sparks of artificial general intelligence: Early experiments with gpt-4. arXiv preprint arXiv:2303.12712, 2023.
  8. Two failures of self-consistency in the multi-step reasoning of llms, 2023a.
  9. Frugalgpt: How to use large language models while reducing cost and improving performance, 2023b.
  10. Interact: Exploring the potentials of chatgpt as a cooperative agent, 2023.
  11. Nelson Cowan. The magical number 4 in short-term memory: A reconsideration of mental storage capacity. Behavioral and brain sciences, 24(1):87–114, 2001.
  12. What is consciousness, and could machines have it? Robotics, AI, and Humanity: Science, Ethics, and Policy, pp.  43–56, 2021.
  13. S33{}^{3}start_FLOATSUPERSCRIPT 3 end_FLOATSUPERSCRIPT: Social-network simulation system with large language model-empowered agents, 2023.
  14. Retroactive interference model of forgetting. The Journal of Mathematical Neuroscience, 11(1):1–15, 2021.
  15. Two storage mechanisms in free recall. Journal of verbal learning and verbal behavior, 5(4):351–360, 1966.
  16. Significant Gravitas. Auto-GPT. https://github.com/Significant-Gravitas/Auto-GPT, 2023.
  17. Ann M Graybiel. The basal ganglia and chunking of action repertoires. Neurobiology of learning and memory, 70(1-2):119–136, 1998.
  18. New and improved embedding model, 2022.
  19. Thilo Hagendorff. Machine psychology: Investigating emergent capabilities and behavior in large language models using psychological methods, 2023.
  20. Product quantization for nearest neighbor search. IEEE transactions on pattern analysis and machine intelligence, 33(1):117–128, 2010.
  21. Unity: A general platform for intelligent agents. arXiv preprint arXiv:1809.02627, 2018.
  22. Michal Kosinski. Theory of mind may have spontaneously emerged in large language models, 2023.
  23. Langchain. Langchain: Ai solutions for natural language understanding. https://github.com/langchain-ai, 2022.
  24. Resource-rationality and dynamic coupling of brains and social environments. Behavioral and Brain Sciences, 43, 2019. URL https://api.semanticscholar.org/CorpusID:73441334.
  25. Swiftsage: A generative agent with fast and slow thinking for complex interactive tasks, 2023.
  26. Training socially aligned language models in simulated human society, 05 2023a.
  27. Agentbench: Evaluating llms as agents, 2023b.
  28. Dissociating language and thought in large language models: a cognitive perspective, 2023.
  29. Why there are complementary learning systems in the hippocampus and neocortex: insights from the successes and failures of connectionist models of learning and memory. Psychological review, 102(3):419, 1995.
  30. An integrative theory of prefrontal cortex function. Annual review of neuroscience, 24(1):167–202, 2001.
  31. George A Miller. The magical number seven, plus or minus two: Some limits on our capacity for processing information. Psychological review, 63(2):81, 1956.
  32. Yohei Nakajima. babyagi. https://github.com/yoheinakajima/babyagi, 2023.
  33. Social simulacra: Creating populated prototypes for social computing systems. In Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology, UIST ’22, New York, NY, USA, 2022. Association for Computing Machinery. ISBN 9781450393201. doi: 10.1145/3526113.3545616. URL https://doi.org/10.1145/3526113.3545616.
  34. Generative agents: Interactive simulacra of human behavior, 2023.
  35. Hierarchical reinforcement learning: A comprehensive survey. ACM Computing Surveys (CSUR), 54(5):1–35, 2021.
  36. Investigating emergent goal-like behaviour in large language models using experimental economics, 2023.
  37. Pinecone. Pinecone: A vector database for machine learning applications. https://github.com/pinecone-io, 2021.
  38. Communicative agents for software development, 2023.
  39. Facebook Research. Faiss: A library for efficient similarity search. https://github.com/facebookresearch/faiss, 2017.
  40. Clever hans or neural theory of mind? stress testing social reasoning in large language models, 2023.
  41. Reflexion: Language agents with verbal reinforcement learning, 2023.
  42. Cognitive architectures for language agents, 2023.
  43. Between mdps and semi-mdps: A framework for temporal abstraction in reinforcement learning. Artificial intelligence, 112(1-2):181–211, 1999.
  44. SeMI Technologies. Weaviate: An open-source, vector search engine powered by ml, vectors, graphs, and graphql. https://github.com/weaviate/weaviate, 2019.
  45. Pettingzoo: Gym for multi-agent reinforcement learning. Advances in Neural Information Processing Systems, 34:15032–15043, 2021.
  46. Voyager: An open-ended embodied agent with large language models, 2023a.
  47. When large language model based agent meets user behavior analysis: A novel user simulation paradigm, 2023b.
  48. Unleashing cognitive synergy in large language models: A task-solving agent through multi-persona self-collaboration, 2023c.
  49. Olagpt: Empowering llms with human-like problem-solving abilities, 2023.
  50. Proagent: Building proactive cooperative ai with large language models, 2023.
  51. Expel: Llm agents are experiential learners, 2023.
  52. Agents: An open-source framework for autonomous language agents, 2023.
  53. Ghost in the minecraft: Generally capable agents for open-world environments via large language models with text-based knowledge and memory, 2023.
Citations (22)

Summary

We haven't generated a summary for this paper yet.

X Twitter Logo Streamline Icon: https://streamlinehq.com