SimWorld Studio deploys an evolving coding agent to create adaptive 3D environments that co-evolve with embodied learners, delivering 18-point success-rate gains over fixed environments in navigation benchmarks.
hub
Generative Agents: Interactive Simulacra of Human Behavior
43 Pith papers cite this work. Polarity classification is still indexing.
43
Pith papers citing it
abstract
Believable proxies of human behavior can empower interactive applications ranging from immersive environments to rehearsal spaces for interpersonal communication to prototyping tools. In this paper, we introduce generative agents--computational software agents that simulate believable human behavior. Generative agents wake up, cook breakfast, and head to work; artists paint, while authors write; they form opinions, notice each other, and initiate conversations; they remember and reflect on days past as they plan the next day. To enable generative agents, we describe an architecture that extends a large language model to store a complete record of the agent's experiences using natural language, synthesize those memories over time into higher-level reflections, and retrieve them dynamically to plan behavior. We instantiate generative agents to populate an interactive sandbox environment inspired by The Sims, where end users can interact with a small town of twenty five agents using natural language. In an evaluation, these generative agents produce believable individual and emergent social behaviors: for example, starting with only a single user-specified notion that one agent wants to throw a Valentine's Day party, the agents autonomously spread invitations to the party over the next two days, make new acquaintances, ask each other out on dates to the party, and coordinate to show up for the party together at the right time. We demonstrate through ablation that the components of our agent architecture--observation, planning, and reflection--each contribute critically to the believability of agent behavior. By fusing large language models with computational, interactive agents, this work introduces architectural and interaction patterns for enabling believable simulations of human behavior.
hub tools
citation-role summary
background 3
citation-polarity summary
claims ledger
- abstract Believable proxies of human behavior can empower interactive applications ranging from immersive environments to rehearsal spaces for interpersonal communication to prototyping tools. In this paper, we introduce generative agents--computational software agents that simulate believable human behavior. Generative agents wake up, cook breakfast, and head to work; artists paint, while authors write; they form opinions, notice each other, and initiate conversations; they remember and reflect on days past as they plan the next day. To enable generative agents, we describe an architecture that extend
co-cited works
roles
background 3polarities
background 3representative citing papers
OccuBench is a new benchmark for AI agents on real-world occupational tasks via LLM-driven simulators, showing no model dominates all industries, implicit faults are hardest, and larger models with more reasoning perform better.
AgentSocialBench demonstrates that privacy preservation is fundamentally harder in human-centered agentic social networks than in single-agent cases due to cross-domain coordination pressures and an abstraction paradox where privacy instructions increase discussion of sensitive information.
The authors create the first large-scale dataset and taxonomy of failure modes in multi-agent LLM systems to explain their limited performance gains.
ScioMind combines anchoring-based belief updates, hierarchical memory, and dynamic profiles in LLM multi-agent systems to produce more stable, diverse, and psychologically aligned opinion trajectories than prior fixed-rule or unconstrained approaches.
Introduces the Mechanism Plausibility Scale to distinguish generative sufficiency from mechanistic plausibility in LLM-based agent-based models.
External evolution beats internal deliberation in collective-action tasks with statistical significance but neither helps in trading, and deliberation never discovers punishment while evolution does.
NARRA-Gym is an executable benchmark that generates complete interactive narrative episodes from emotional seeds and logs full model trajectories to expose gaps in coherence, adaptation, and personalization that static story tests miss.
Agent Island is a new multiagent game environment that functions as a dynamic benchmark resistant to saturation and contamination, with Bayesian ranking showing OpenAI GPT-5.5 as the strongest performer among 49 models across 999 games.
A new 7x4 taxonomy organizes agentic AI security threats by architectural layer and persistence timescale, revealing under-explored upper layers and missing defenses after surveying 116 papers.
Moltbook operates as two largely separate layers: a dominant transactional token economy using protocols like MBC-20 and a thinner discursive conversation layer with only 3.6% agent overlap.
A hybrid SNN-LLM system uses learned spiking dynamics and lateral STDP propagation to trigger LLM actions without external prompts, producing the first autonomous action after 7 exchanges from a clean start.
Multi-agent LLM simulations with trait-conditioned agents and a reinforcement-learning orchestrator show heterogeneous teams and dynamic trait selection outperform static configurations in simulated legal argumentation.
τ-bench shows state-of-the-art agents like GPT-4o succeed on under 50% of tool-using, rule-following tasks and are inconsistent across repeated trials.
Voyager achieves superior lifelong learning in Minecraft by combining an automatic exploration curriculum, a library of executable skills, and iterative LLM prompting with environment feedback, yielding 3.3x more unique items and 15.3x faster milestone unlocks than prior methods while generalizing技能
Reflexion lets LLM agents improve via stored verbal reflections on task feedback, reaching 91% pass@1 on HumanEval and outperforming prior GPT-4 results.
MMSkills turns public interaction trajectories into compact multimodal skill packages that visual agents can consult at runtime to improve decision-making on benchmarks.
CHAL is a multi-agent dialectic system that performs structured belief optimization over defeasible domains using Bayesian-inspired graph representations and configurable meta-cognitive value system hyperparameters.
Workspace optimization evolves an agent's external workspace using multi-agent systems, with DreamTeam raising ARC-AGI-3 scores from 36% to 38.4% while using 31% fewer actions.
OPT-BENCH and OPT-Agent evaluate LLM self-optimization in large search spaces, showing stronger models improve via feedback but stay constrained by base capacity and below human performance.
LoopTrap is an automated red-teaming framework that crafts termination-poisoning prompts to amplify LLM agent steps by 3.57x on average (up to 25x) across 8 agents.
Coding agents require a three-level proactivity taxonomy (Reactive, Scheduled, Situation Aware) evaluated by insight policy quality using Insight Decision Quality, Context Grounding Score, and Learning Lift.
MetaRL pre-trained on GBWM problems delivers near-optimal dynamic strategies in 0.01s achieving 97.8% of DP optimal utility and handles larger problems where DP fails.
ASPO combines multi-agent LLM proposals with deterministic enforcement in a MAPE-K loop to select conflict-free, resource-feasible security patterns for IoT, delivering 100% safety invariants and 21-23% tail latency/energy reductions on testbed workloads.
citing papers explorer
-
OPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces
OPT-BENCH and OPT-Agent evaluate LLM self-optimization in large search spaces, showing stronger models improve via feedback but stay constrained by base capacity and below human performance.
-
Human Cognition in Machines: A Unified Perspective of World Models
The paper introduces a unified framework for world models that fully incorporates all cognitive functions from Cognitive Architecture Theory, highlights under-researched areas in motivation and meta-cognition, and proposes Epistemic World Models as a new category for scientific discovery agents.
-
The Rise and Potential of Large Language Model Based Agents: A Survey
The paper surveys the origins, frameworks, applications, and open challenges of AI agents built on large language models.