Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-12T15:45:46.302732Z
Paper Citation Record · LEDGER
Incentives to Build Houses, Trade Houses, or Trade House Building Skills in Simulated Worlds under Various Governing Systems or Institutions: Comparing Multi-agent Reinforcement Learning to Generative Agent-based Model
As of 13 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 0 inbound Pith citation observations for arXiv:2411.17724.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
36 of 36 outbound references displayed
- verified exact0
- verified fuzzy27
- unresolved9
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation e9e28719-4b7b-42f3-b148-23355eac07aa · outbound
This paper cites In particular, the AI-Economist uses structured curriculum learning to stabilize the challenging two-level, co-adaptive learning problem.
Incentives to Build Houses, Trade Houses, or Trade House Building Skills in Simulated Worlds under Various Governing Systems or Institutions: Comparing Multi-agent Reinforcement Learning to Generative Agent-based Model In particular, the AI-Economist uses structured curriculum learning to stabilize the challenging two-level, co-adaptive learning problem
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T15:45:46.624227Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 11f5e375-1a28-4628-87b3-216545d71cfe · outbound
This paper cites To overcome, the training procedure in the AI-Economist has two important features - curriculum learning and entropy-based regularization.
Incentives to Build Houses, Trade Houses, or Trade House Building Skills in Simulated Worlds under Various Governing Systems or Institutions: Comparing Multi-agent Reinforcement Learning to Generative Agent-based Model To overcome, the training procedure in the AI-Economist has two important features - curriculum learning and entropy-based regularization
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T15:45:46.615918Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation fff69b1f-f05c-4085-ba54-cbe9ac71af78 · outbound
This paper cites Each agent has a varied house build-skill which sets how much income an agent receives from building a house.
Incentives to Build Houses, Trade Houses, or Trade House Building Skills in Simulated Worlds under Various Governing Systems or Institutions: Comparing Multi-agent Reinforcement Learning to Generative Agent-based Model Each agent has a varied house build-skill which sets how much income an agent receives from building a house
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T15:45:46.607793Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation b0dc2b08-d552-45e5-a2c3-bcffc3f11c68 · outbound
This paper cites Quadrants contain different combi- nations of resources: both stone and wood, only stone, only wood, or nothing.
Incentives to Build Houses, Trade Houses, or Trade House Building Skills in Simulated Worlds under Various Governing Systems or Institutions: Comparing Multi-agent Reinforcement Learning to Generative Agent-based Model Quadrants contain different combi- nations of resources: both stone and wood, only stone, only wood, or nothing
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T15:45:46.598513Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation b7bad65b-a672-4b23-9bf5-150ea74d4a31 · outbound
This paper cites The action space of the agents includes four movement actions: up, down, left, and right.
Incentives to Build Houses, Trade Houses, or Trade House Building Skills in Simulated Worlds under Various Governing Systems or Institutions: Comparing Multi-agent Reinforcement Learning to Generative Agent-based Model The action space of the agents includes four movement actions: up, down, left, and right
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T15:45:46.590282Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 636dc216-c7e8-4d51-b33e-0ece4e632c2f · outbound
This paper cites an unresolved cited work.
Reference 6
- Resolution
- unresolved
- raw_fallback, observed 2026-08-12T15:45:46.581836Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation fd2a8cb3-1ebe-4e5c-8985-f519535b3203 · outbound
This paper cites Agents can submit asks (the number of coins they are willing to accept) or bids (how much they are willing to pay) in exchange for one unit of wood or stone.
Incentives to Build Houses, Trade Houses, or Trade House Building Skills in Simulated Worlds under Various Governing Systems or Institutions: Comparing Multi-agent Reinforcement Learning to Generative Agent-based Model Agents can submit asks (the number of coins they are willing to accept) or bids (how much they are willing to pay) in exchange for one unit of wood or stone
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T15:45:46.573818Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 4fa7329f-634b-4171-80c6-75e968197220 · outbound
This paper cites Agents are restricted from building on source cells as well as locations where a house already exists.
Incentives to Build Houses, Trade Houses, or Trade House Building Skills in Simulated Worlds under Various Governing Systems or Institutions: Comparing Multi-agent Reinforcement Learning to Generative Agent-based Model Agents are restricted from building on source cells as well as locations where a house already exists
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T15:45:46.565717Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation b19f523e-2ae1-4615-b7bf-7f2090da6c61 · outbound
This paper cites Taxation is implemented using income brackets and bracket tax rates.
Incentives to Build Houses, Trade Houses, or Trade House Building Skills in Simulated Worlds under Various Governing Systems or Institutions: Comparing Multi-agent Reinforcement Learning to Generative Agent-based Model Taxation is implemented using income brackets and bracket tax rates
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T15:45:46.557371Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 66b90b08-6379-45e0-95c4-2a2eb7eef846 · outbound
This paper cites an unresolved cited work.
Reference 10
- Resolution
- unresolved
- raw_fallback, observed 2026-08-12T15:45:46.548985Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation fb00cdc9-8817-479e-8594-43a5156c742f · outbound
This paper cites Accordingly, taxes are collected at the end of each tax year by subtracting T (zi) from Ci.
Incentives to Build Houses, Trade Houses, or Trade House Building Skills in Simulated Worlds under Various Governing Systems or Institutions: Comparing Multi-agent Reinforcement Learning to Generative Agent-based Model Accordingly, taxes are collected at the end of each tax year by subtracting T (zi) from Ci
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T15:45:46.541089Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 68d91f10-b4a7-4cde-88ee-8e00a8f5cb3f · outbound
This paper cites It is found that build-skill is a substantial determinant of behavior; agents’ gather-skill empirically does not affect optimal behaviors in our settings.
Incentives to Build Houses, Trade Houses, or Trade House Building Skills in Simulated Worlds under Various Governing Systems or Institutions: Comparing Multi-agent Reinforcement Learning to Generative Agent-based Model It is found that build-skill is a substantial determinant of behavior; agents’ gather-skill empirically does not affect optimal behaviors in our settings
Reference 12
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T15:45:46.533039Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation a0300a8d-593c-42ef-8809-b2afda678b31 · outbound
This paper cites RL is instantiated at two levels, that is, for two types of actors: training agent behavioral policy models and a taxation policy model for the social planner.
Incentives to Build Houses, Trade Houses, or Trade House Building Skills in Simulated Worlds under Various Governing Systems or Institutions: Comparing Multi-agent Reinforcement Learning to Generative Agent-based Model RL is instantiated at two levels, that is, for two types of actors: training agent behavioral policy models and a taxation policy model for the social planner
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T15:45:46.524790Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 7ad695b9-7279-41ed-a130-400503686def · outbound
This paper cites To improve learning efficiency, a single-agent policy networkπ(ai,t|oi,t; θ) is trained whose weights are shared by all agents, that is, θi = θ.
Incentives to Build Houses, Trade Houses, or Trade House Building Skills in Simulated Worlds under Various Governing Systems or Institutions: Comparing Multi-agent Reinforcement Learning to Generative Agent-based Model To improve learning efficiency, a single-agent policy networkπ(ai,t|oi,t; θ) is trained whose weights are shared by all agents, that is, θi = θ
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T15:45:46.516671Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 8e8a2d22-cb0c-44fd-853e-c9fea74f1c59 · outbound
This paper cites an unresolved cited work.
Reference 15
- Resolution
- unresolved
- raw_fallback, observed 2026-08-12T15:45:46.508131Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 4049aac8-4632-4939-8126-5bbfd1e1b818 · outbound
This paper cites an unresolved cited work.
Reference 16
- Resolution
- unresolved
- raw_fallback, observed 2026-08-12T15:45:46.500230Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation cffa148d-fd94-4fca-9daa-e56fe16b47fa · outbound
This paper cites an unresolved cited work.
Reference 17
- Resolution
- unresolved
- raw_fallback, observed 2026-08-12T15:45:46.491995Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation b16c9ec2-2008-4246-81fe-51468f4cd0f3 · outbound
This paper cites Hence, the sum of pretax and post-tax incomes is the same.
Incentives to Build Houses, Trade Houses, or Trade House Building Skills in Simulated Worlds under Various Governing Systems or Institutions: Comparing Multi-agent Reinforcement Learning to Generative Agent-based Model Hence, the sum of pretax and post-tax incomes is the same
Reference 18
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T15:45:46.483884Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation f403f7b7-41fb-4de3-b69a-54544ab75bef · outbound
This paper cites an unresolved cited work.
Reference 19
- Resolution
- unresolved
- raw_fallback, observed 2026-08-12T15:45:46.476035Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 4723926e-fa1d-47c1-96aa-635775027248 · outbound
This paper cites In Concordia both are generative.
Incentives to Build Houses, Trade Houses, or Trade House Building Skills in Simulated Worlds under Various Governing Systems or Institutions: Comparing Multi-agent Reinforcement Learning to Generative Agent-based Model In Concordia both are generative
Reference 20
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T15:45:46.467592Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation b56539fb-c0d1-4cfe-9c4b-66048497b203 · outbound
This paper cites The game master receives the agent actions and produces event statements, which define the course of events in the simulation as a result of the agent’s generated action.
Incentives to Build Houses, Trade Houses, or Trade House Building Skills in Simulated Worlds under Various Governing Systems or Institutions: Comparing Multi-agent Reinforcement Learning to Generative Agent-based Model The game master receives the agent actions and produces event statements, which define the course of events in the simulation as a result of the agent’s generated action
Reference 21
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T15:45:46.458358Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 9930ca9c-a474-44d5-89b7-2a8f133f7a32 · outbound
This paper cites The game master absorbs their intended actions, decides on the outcome of their attempts, and generates event statements.
Incentives to Build Houses, Trade Houses, or Trade House Building Skills in Simulated Worlds under Various Governing Systems or Institutions: Comparing Multi-agent Reinforcement Learning to Generative Agent-based Model The game master absorbs their intended actions, decides on the outcome of their attempts, and generates event statements
Reference 22
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T15:45:46.449859Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 6168d2a7-2b69-4e3f-8506-66fe05892215 · outbound
This paper cites The game master determines the effect of the agents’ actions on these variables, records them, and checks that they are valid.
Incentives to Build Houses, Trade Houses, or Trade House Building Skills in Simulated Worlds under Various Governing Systems or Institutions: Comparing Multi-agent Reinforcement Learning to Generative Agent-based Model The game master determines the effect of the agents’ actions on these variables, records them, and checks that they are valid
Reference 23
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T15:45:46.440979Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 1085ea1c-4a84-4815-bb47-33c9055af432 · outbound
This paper cites an unresolved cited work.
Reference 24
- Resolution
- unresolved
- raw_fallback, observed 2026-08-12T15:45:46.432804Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 040939c7-c977-4db4-98e8-b3f55c981812 · outbound
This paper cites an unresolved cited work.
Reference 25
- Resolution
- unresolved
- raw_fallback, observed 2026-08-12T15:45:46.425136Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 2d09fb11-ddce-4788-8bce-463d04551a17 · outbound
This paper cites The idea is that, if the outputs of LLMs conditioned to model specific human populations, they reflect the beliefs and attitudes of those populations.
Incentives to Build Houses, Trade Houses, or Trade House Building Skills in Simulated Worlds under Various Governing Systems or Institutions: Comparing Multi-agent Reinforcement Learning to Generative Agent-based Model The idea is that, if the outputs of LLMs conditioned to model specific human populations, they reflect the beliefs and attitudes of those populations
Reference 26
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T15:45:46.417116Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 6294bf66-b630-487f-8d7f-30bb771502e4 · outbound
This paper cites Concordia makes this possible by using an associative memory in a modular and flexible fashion to keep the record of agents experience.
Incentives to Build Houses, Trade Houses, or Trade House Building Skills in Simulated Worlds under Various Governing Systems or Institutions: Comparing Multi-agent Reinforcement Learning to Generative Agent-based Model Concordia makes this possible by using an associative memory in a modular and flexible fashion to keep the record of agents experience
Reference 27
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T15:45:46.408719Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 85e6e948-644b-45a7-bb3b-f5e8a5421084 · outbound
This paper cites The working memory is zi i composed of the states of individual components.
Incentives to Build Houses, Trade Houses, or Trade House Building Skills in Simulated Worlds under Various Governing Systems or Institutions: Comparing Multi-agent Reinforcement Learning to Generative Agent-based Model The working memory is zi i composed of the states of individual components
Reference 28
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T15:45:46.399849Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 28331074-e257-43d0-9374-92b53f122ea7 · outbound
This paper cites When creating a generative agent in Concordia, the user creates the components that are relevant for their simulations.
Incentives to Build Houses, Trade Houses, or Trade House Building Skills in Simulated Worlds under Various Governing Systems or Institutions: Comparing Multi-agent Reinforcement Learning to Generative Agent-based Model When creating a generative agent in Concordia, the user creates the components that are relevant for their simulations
Reference 29
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T15:45:46.390859Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 3eb43132-a0f8-4cd5-99bd-3377bbb7e5e4 · outbound
This paper cites The most simple form of fa is a concatenation operator over zt = zi t i.
Incentives to Build Houses, Trade Houses, or Trade House Building Skills in Simulated Worlds under Various Governing Systems or Institutions: Comparing Multi-agent Reinforcement Learning to Generative Agent-based Model The most simple form of fa is a concatenation operator over zt = zi t i
Reference 30
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T15:45:46.382480Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation d3849948-4e1a-408d-b955-3994c842432f · outbound
This paper cites In Concordia, conditioning is explicitely done on the memory stream m, since a component may make specific queries into the agent’s memory to update its state.
Incentives to Build Houses, Trade Houses, or Trade House Building Skills in Simulated Worlds under Various Governing Systems or Institutions: Comparing Multi-agent Reinforcement Learning to Generative Agent-based Model In Concordia, conditioning is explicitely done on the memory stream m, since a component may make specific queries into the agent’s memory to update its state
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T15:45:46.373200Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 85a4c039-b9c1-464d-92fd-ce46000d0fc0 · outbound
This paper cites The game master mediates between the state of the world and agents’ actions.
Incentives to Build Houses, Trade Houses, or Trade House Building Skills in Simulated Worlds under Various Governing Systems or Institutions: Comparing Multi-agent Reinforcement Learning to Generative Agent-based Model The game master mediates between the state of the world and agents’ actions
Reference 32
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T15:45:46.364054Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 48a13e9e-acbd-4059-b971-658528aff673 · outbound
This paper cites Like agents, the game master has an associative memory implemented using various components.
Incentives to Build Houses, Trade Houses, or Trade House Building Skills in Simulated Worlds under Various Governing Systems or Institutions: Comparing Multi-agent Reinforcement Learning to Generative Agent-based Model Like agents, the game master has an associative memory implemented using various components
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T15:45:46.355439Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation e5f82d7d-5e01-4445-af49-9b50758b48aa · outbound
This paper cites | f e(zt, at)) (14).
Reference 34
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T15:45:46.346162Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 03a38d47-e556-4f44-afb8-7fe65f69f3b3 · outbound
This paper cites After adding the event statement et to its memory the game master can update its components using the same Eq.
Incentives to Build Houses, Trade Houses, or Trade House Building Skills in Simulated Worlds under Various Governing Systems or Institutions: Comparing Multi-agent Reinforcement Learning to Generative Agent-based Model After adding the event statement et to its memory the game master can update its components using the same Eq
Reference 35
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-12T15:45:46.336974Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation cd31d661-df2a-432e-ab14-4f4da9c63e5a · outbound
This paper cites an unresolved cited work.
Reference 36
- Resolution
- unresolved
- raw_fallback, observed 2026-08-12T15:45:46.326533Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Pith citing papers
No inbound Pith citation observations are available.