Pith. sign in

REVIEW 11 cited by

Lyfe Agents: Generative agents for low-cost real-time social interactions

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2310.02172 v1 pith:64F7VDNS submitted 2023-10-03 cs.HC cs.AIcs.LG

classification cs.HCcs.AIcs.LG
keywords agentslyfecostsocialautonomousgenerativereal-timevirtual
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Highly autonomous generative agents powered by large language models 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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Eco3S: Complex Socio-Economic System Simulation via Agent-Based Models

    cs.AI 2026-07 conditional novelty 6.0 of 10

    Eco3S packages co-evolving environments, checkpoint counterfactuals, and auto-refinement into one LLM agent-based simulation platform, demonstrated on canal-rebellion, state-formation, and information-spread cases.

  2. MemoCue: Empowering LLM-Based Agents for Human Memory Recall via Strategy-Guided Querying

    cs.AI 2025-07 conditional novelty 6.0 of 10

    MemoCue uses a 5W scenario classifier and Monte Carlo Tree Search to generate cue-rich questions that help LLM agents guide humans through memory recall.

  3. Are Human Interactions Replicable by Generative Agents? A Case Study on Pronoun Usage in Hierarchical Interactions

    cs.CL 2025-01 conditional novelty 6.0 of 10

    In a leader/subordinate discussion simulation, most LLM agents do not reproduce the human pronoun pattern, and knowing the pattern does not help them show it.

  4. Creative Agents: Simulating the Systems Model of Creativity with Generative Agents

    cs.MA 2024-11 reject novelty 6.0 of 10

    Simulating Csikszentmihalyi's systems model with LLM agents does not provide clear evidence that social feedback improves AI creativity; the main statistical test was not significant.

  5. SimuPanel: A Novel Immersive Multi-Agent System to Simulate Interactive Expert Panel Discussion

    cs.HC 2025-06 conditional novelty 5.0 of 10

    A multi-agent LLM system called SimuPanel simulates expert panel discussions with personas grounded in public academic sources, and a small evaluation suggests the full reasoning pipeline produces higher LLM-judged di...

  6. SimSpark: Interactive Simulation of Social Media Behaviors

    cs.HC 2025-06 conditional novelty 5.0 of 10

    SimSpark combines LLM-powered agents with interactive visualizations to simulate believable, customizable social media behaviors such as posting, liking, following, and replying.

  7. Infected Smallville: How Disease Threat Shapes Sociality in LLM Agents

    physics.soc-ph 2025-06 reject novelty 5.0 of 10

    In three simulation runs, LLM agents primed with a swine flu article reduced social activity compared with controls, but the effect is confounded by prompt instructions and no inferential statistics are reported.

  8. The Truth Becomes Clearer Through Debate! Multi-Agent Systems with Large Language Models Unmask Fake News

    cs.SI 2025-05 conditional novelty 5.0 of 10

    TED uses structured pro/con debates between LLM agents plus a graph-based analysis model to detect fake news more accurately than prior methods on two benchmark datasets.

  9. SOTOPIA-S4: a user-friendly system for flexible, customizable, and large-scale social simulation

    cs.CY 2025-04 conditional novelty 4.0 of 10

    SOTOPIA-S4 packages a social simulation engine with a web interface, REST API, asynchronous multi-party turn-taking, and customizable LLM-based evaluation for non-programmers.

  10. From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents

    cs.CL 2024-12 conditional novelty 4.0 of 10

    A structured survey that categorizes LLM-based social simulation into individual, scenario, and society simulation, with associated methods, benchmarks, and observed trends.

  11. WiS Platform: Enhancing Evaluation of LLM-Based Multi-Agent Systems Through Game-Based Analysis

    cs.AI 2024-12 conditional novelty 4.0 of 10

    An open platform and benchmark for evaluating LLM-based multi-agent systems through the 'Who is Spy?' game, including a leaderboard and behavioral analysis of ten models.

Pith tools