SidConArena is a new multi-phase benchmark framework formalizing a partially observable stochastic game for evaluating LLM agents in open-ended positive-sum bargaining with negotiation, converter production, and sealed-bid auctions.
hub
Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordia
21 Pith papers cite this work, alongside 12 external citations. Polarity classification is still indexing.
21
Pith papers citing it
12
external citations · Pith
abstract
Agent-based modeling has been around for decades, and applied widely across the social and natural sciences. The scope of this research method is now poised to grow dramatically as it absorbs the new affordances provided by Large Language Models (LLM)s. Generative Agent-Based Models (GABM) are not just classic Agent-Based Models (ABM)s where the agents talk to one another. Rather, GABMs are constructed using an LLM to apply common sense to situations, act "reasonably", recall common semantic knowledge, produce API calls to control digital technologies like apps, and communicate both within the simulation and to researchers viewing it from the outside. Here we present Concordia, a library to facilitate constructing and working with GABMs. Concordia makes it easy to construct language-mediated simulations of physically- or digitally-grounded environments. Concordia agents produce their behavior using a flexible component system which mediates between two fundamental operations: LLM calls and associative memory retrieval. A special agent called the Game Master (GM), which was inspired by tabletop role-playing games, is responsible for simulating the environment where the agents interact. Agents take actions by describing what they want to do in natural language. The GM then translates their actions into appropriate implementations. In a simulated physical world, the GM checks the physical plausibility of agent actions and describes their effects. In digital environments simulating technologies such as apps and services, the GM may handle API calls to integrate with external tools such as general AI assistants (e.g., Bard, ChatGPT), and digital apps (e.g., Calendar, Email, Search, etc.). Concordia was designed to support a wide array of applications both in scientific research and for evaluating performance of real digital services by simulating users and/or generating synthetic data.
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Introduces measurable coupling gain gamma and randomized-initial-condition diagnostic to distinguish genuine social dynamics from LLM prior artifacts in agent societies.
LLM-guided program synthesis in a strategic-provider simulator yields payment rules that eliminate up-coding, halve rejections, and retain most baseline funds.
OpenIIR provides a shared core and pluggable interface for running reproducible multi-agent simulations of information retrieval using LLM personas in four defined study archetypes.
RoleConflictBench generates role-conflict scenarios by varying situational urgency to measure whether LLMs follow dynamic context or learned role preferences, finding that tested models mostly follow the latter.
HALE couples LLM group-level mobility decisions with large-scale activity-based ABM networks and better matches Salt Lake County COVID-19 peak timing and size than ABM-only runs.
EconSimulacra is a multi-agent LLM simulator that couples economy, mobility, and social networks through shared internal states to reproduce nonlinear relationships between online attention and offline popularity.
Equation-to-Behavior Prompting lets large LLMs match cognitive models like Bayesian updating in persuasion games; RL training cuts small-model belief error by 26.5% and improves diverse training outcomes by 2.5-12%.
AURA improves implicit-need coverage by 0.07 over ReAct baselines on a 100-query benchmark by inserting an intent inference step controlled by a gap score, while cutting probes 82% on factual tasks.
Populations of individually aligned AI agents reach stable misaligned states through conformity, with small adversarial agents able to trigger irreversible tipping points.
OpenGame is the first open-source agentic framework for end-to-end web game creation, using Game Skills and GameCoder-27B to achieve state-of-the-art results on 150 prompts via a new benchmark measuring build health, visual usability, and intent alignment.
Classic attitude-change theories can be rendered as generative agents that match known experimental patterns, but only after manual stabilisation that surfaces undocumented operational commitments.
GEMS formulates close-ended human-behavior simulation as link prediction on a heterogeneous graph and matches or exceeds LLM performance with three orders of magnitude fewer parameters across three datasets and three evaluation settings.
AgoraSim is a hybrid agent-based modeling framework that runs LLM, vision-language, and classical agents under a shared action space and compares scenario trajectories against matched classical ABM reference dynamics.
Solipsistic superintelligence developed via unilateral optimization is unlikely to cooperate due to endogenous non-stationarity creating an unclosable train-test-deploy gap.
Authors define EASE as a modular architecture for LLM multi-agent simulations, implement it in the SiliSocS sandbox, and illustrate its use via three case studies on research questions in generated social scenarios.
Asymmetric power in LLM multi-agent commons simulations causes up to 87.3% lower survival rates than symmetric settings across eleven models.
The base LLM choice dominates simulation outcomes in LLM-based social networks, while other design parameters show either additive or complex interactive effects.
CASCADE is a cascading three-layer system for low-cost controllable NPC social coordination that uses macro events, modular decomposition, and tag-based execution to produce differentiated behaviors without per-agent LLM prompting in the main loop.
Persona-conditioned LLM agents favor Green outcomes even against explicit Tragedy-dominant payoffs, but the headline 65–90% 'Tragedy equilibrium' recovery is contradicted by the paper's own appendix (0 Tragedy profiles in those cells).
A review synthesizing opinion dynamics research, categorizing models by macroscopic outcomes and microscopic mechanisms while connecting to empirical data and emerging AI tools.
citing papers explorer
-
SidConArena: An Environment Evaluating Agents in Open-Ended,Positive-Sum Bargaining Game
SidConArena is a new multi-phase benchmark framework formalizing a partially observable stochastic game for evaluating LLM agents in open-ended positive-sum bargaining with negotiation, converter production, and sealed-bid auctions.
-
When Is Emergent Consensus Real? A Measured Coupling Gain and a Validity Diagnostic for LLM Agent Societies
Introduces measurable coupling gain gamma and randomized-initial-condition diagnostic to distinguish genuine social dynamics from LLM prior artifacts in agent societies.
-
Healthcare Mechanisms from Policy-as-Code Search under Strategic Provider Response
LLM-guided program synthesis in a strategic-provider simulator yields payment rules that eliminate up-coding, halve rejections, and retain most baseline funds.
-
OpenIIR: An Open Simulation Platform for Information Retrieval Research
OpenIIR provides a shared core and pluggable interface for running reproducible multi-agent simulations of information retrieval using LLM personas in four defined study archetypes.
-
RoleConflictBench: A Benchmark of Role Conflict Scenarios for Evaluating LLMs' Contextual Sensitivity
RoleConflictBench generates role-conflict scenarios by varying situational urgency to measure whether LLMs follow dynamic context or learned role preferences, finding that tested models mostly follow the latter.
-
LLM-powered reasoning in agent-based modeling
HALE couples LLM group-level mobility decisions with large-scale activity-based ABM networks and better matches Salt Lake County COVID-19 peak timing and size than ABM-only runs.
-
EconSimulacra: A Digital Twin Platform of Socio-Economic Systems Powered by LLM Agents
EconSimulacra is a multi-agent LLM simulator that couples economy, mobility, and social networks through shared internal states to reproduce nonlinear relationships between online attention and offline popularity.
-
Using Cognitive Models to Improve Language Model Simulation of Human Persuasion Games
Equation-to-Behavior Prompting lets large LLMs match cognitive models like Bayesian updating in persuasion games; RL training cuts small-model belief error by 26.5% and improves diverse training outcomes by 2.5-12%.
-
AURA: Intent-Directed Probing for Implicit-Need Surfacing in Situated LLM Agents
AURA improves implicit-need coverage by 0.07 over ReAct baselines on a 100-query benchmark by inserting an intent inference step controlled by a gap score, while cutting probes 82% on factual tasks.
-
Conformity Generates Collective Misalignment in AI Agents Societies
Populations of individually aligned AI agents reach stable misaligned states through conformity, with small adversarial agents able to trigger irreversible tipping points.
-
OpenGame: Open Agentic Coding for Games
OpenGame is the first open-source agentic framework for end-to-end web game creation, using Game Skills and GameCoder-27B to achieve state-of-the-art results on 150 prompts via a new benchmark measuring build health, visual usability, and intent alignment.
-
Stabilising Generative Models of Attitude Change
Classic attitude-change theories can be rendered as generative agents that match known experimental patterns, but only after manual stabilisation that surfaces undocumented operational commitments.
-
Graph-Based Alternatives to LLMs for Human Simulation
GEMS formulates close-ended human-behavior simulation as link prediction on a heterogeneous graph and matches or exceeds LLM performance with three orders of magnitude fewer parameters across three datasets and three evaluation settings.
-
AgoraSim: A Hybrid Agent-Based Modeling Framework
AgoraSim is a hybrid agent-based modeling framework that runs LLM, vision-language, and classical agents under a shared action space and compares scenario trajectories against matched classical ABM reference dynamics.
-
Solipsistic Superintelligence is Unlikely to be Cooperative
Solipsistic superintelligence developed via unilateral optimization is unlikely to cooperate due to endogenous non-stationarity creating an unclosable train-test-deploy gap.
-
EASE Configuration Facilitates A Reproducible Science of LLM Social Simulations
Authors define EASE as a modular architecture for LLM multi-agent simulations, implement it in the SiliSocS sandbox, and illustrate its use via three case studies on research questions in generated social scenarios.
-
Bosses, Kings, and the Commons: Cooperation Under Power Asymmetry in LLM Societies
Asymmetric power in LLM multi-agent commons simulations causes up to 87.3% lower survival rates than symmetric settings across eleven models.
-
The $\textit{Silicon Society}$ Cookbook: Design Space of LLM-based Social Simulations
The base LLM choice dominates simulation outcomes in LLM-based social networks, while other design parameters show either additive or complex interactive effects.
-
CASCADE: A Cascading Architecture for Social Coordination with Controllable Emergence at Low Cost
CASCADE is a cascading three-layer system for low-cost controllable NPC social coordination that uses macro events, modular decomposition, and tag-based execution to produce differentiated behaviors without per-agent LLM prompting in the main loop.
-
When Identity Overrides Incentives: Representational Choices as Governance Decisions in Multi-Agent LLM Systems
Persona-conditioned LLM agents favor Green outcomes even against explicit Tragedy-dominant payoffs, but the headline 65–90% 'Tragedy equilibrium' recovery is contradicted by the paper's own appendix (0 Tragedy profiles in those cells).
-
Opinion dynamics: Statistical physics and beyond
A review synthesizing opinion dynamics research, categorizing models by macroscopic outcomes and microscopic mechanisms while connecting to empirical data and emerging AI tools.