TOPIC

World Models

6 synthesis notes · 11 source papers

View as

What five design choices compose a world model?

World models are often presented as monolithic systems, but they actually involve five distinct design decisions—data preparation, representation, reasoning architecture, training objective, and decision integration—that can each fail independently. Understanding this decomposition helps diagnose why world model proposals fall short.

Can we extract causal belief networks from interview conversations?

Can natural language interviews be systematically parsed into causal graphs that capture how individuals reason about policy trade-offs? This matters for building auditable belief simulations that go beyond static opinion snapshots.

Can causal models alone capture how humans actually reason?

Explores whether causal belief networks provide a complete picture of human cognition or whether associative, analogical, and emotional reasoning modes fall outside their scope.

Can we measure reasoning quality beyond output plausibility?

How might we evaluate whether AI systems reason internally like humans do, rather than just producing human-like outputs? This matters because surface coherence can mask broken underlying reasoning.

Can language models simulate belief change in people?

Current LLM social simulators treat behavior as input-output mappings without modeling internal belief formation or revision. Can they be redesigned to actually track how people think and change their minds?

What should a world model actually be designed to do?

Current AI research treats world models as either video predictors or RL dynamics learners, but what if their real purpose is simulating actionable possibilities for decision-making rather than predicting next observations?

Source papers 11

The Arxiv papers behind this sub-topic. Links may take you off-site to arxiv.org.

AI Models Exceed Individual Human Accuracy in Predicting Everyday Social Norms
A fundamental question in cognitive science concerns how social norms are acquired and represented. While humans typically learn norms through embodied social experience, we investigated whether large…
Assessing adaptive world models in machines with novel games
Human intelligence exhibits a remarkable capacity for rapid adaptation and effective problem-solving in novel and unfamiliar contexts. We argue that this profound adaptability is fundamentally linked …
Can Language Models Serve as Text-Based World Simulators?
Broadly speaking, there are two ways to leverage LLMs in the context of world modeling and simulation. The first is neurosymbolic: a number of efforts use language models to generate code in a symboli…
Critiques of World Models
World Model, the supposed algorithmic surrogate of the real-world environment which biological agents experience with and act upon, has been an emerging topic in recent years because of the rising nee…
FinCoT: Grounding Chain-of-Thought in Expert Financial Reasoning
This paper presents FinCoT, a structured chain-of- thought (CoT) prompting approach that incorporates insights from domain-specific expert financial reasoning to guide the reasoning traces of large la…
Learning Human-Object Interaction as Groups
Human-Object Interaction Detection (HOI-DET) aims to localize human-object pairs and identify their interactive relationships. To aggregate contextual cues, existing methods typically propagate inform…
Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction
The evolution of Large Language Models (LLMs) from passive responders to autonomous agents necessitates a fundamental shift in learning paradigms—from static imitation to incentive-driven decision mak…
Scaling can lead to compositional generalization
Can neural networks systematically capture discrete, compositional task structure despite their continuous, distributed nature? The impressive capabilities of large scale neural networks suggest that …
Simulating Society Requires Simulating Thought
Simulating society with large language models (LLMs), we argue, requires more than generating plausible behavior; it demands cognitively grounded reasoning that is structured, revisable, and traceable…
TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks
To measure the progress of these LLM agents’ performance on performing real-world professional tasks, in this paper we introduce TheAgentCompany, an extensible benchmark for evaluating AI agents that …
What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models
Foundation models are premised on the idea that sequence prediction can uncover deeper domain understanding, much like how Kepler’s predictions of planetary motion later led to the discovery of Newton…