World-Model Collapse as a Phase Transition
cs.AI
Submitted: 2026-06-30
Updated: 2026-11-12
Code: https://github.com/Hik289/world-model-collapse
Terminology
Sources
- Aeon: High-Performance Neuro-Symbolic Memory Management for Long-Horizon LLM Agents
- Graph of Thoughts: Solving Elaborate Problems with Large Language Models
- Genie: Generative Interactive Environments
- STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?
- WorldPrediction: A Benchmark for High-level World Modeling and Long-horizon Procedural Planning
- LLM-State: Open World State Representation for Long-horizon Task Planning with Large Language Model
- Evaluating Long-Context Reasoning in LLM-Based WebAgents
- WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation
- AgentLongBench: A Controllable Long Benchmark For Long-Contexts Agents via Environment Rollouts
- The Llama 3 Herd of Models
- StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models
- World Models
- Mastering Atari with Discrete World Models
- Mastering Diverse Domains through World Models
- WMIP: A Working-Memory-Inspired Programmable Probe of Cumulative State Tracking in Large Language Models
- SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
- LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks
- Scaling Laws for Neural Language Models
- Capable but Unreliable: Canonical Path Deviation as a Causal Mechanism of Agent Failure in Long-Horizon Tasks
- LLM+P: Empowering Large Language Models with Optimal Planning Proficiency
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents