paper-with-me

홈 › Papers

World-Model Collapse as a Phase Transition

2026-06-30 · Xinyuan Song, Zekun Cai arxiv

Water looks unchanged as it warms, then at a critical point it boils. We ask whether long-horizon language agents show an analogous transition in their implicit world models. In some parameter settings, changing state load by a small amount, or adding a single step of horizon, leaves behavior nearly unchanged; near a critical boundary, the same small change causes a sudden world collapse. We study this effect in a deterministic task family with exact per-step gold state. A large grid search over state cardinality, dependency density, horizon, branching, observation mode, and mutation rate reveals a phase diagram: a solved plateau, a narrow transition band, and a collapse floor. Per-step traces show the mechanism: world-state fidelity fails before action validity, so the agent is not merely choosing a bad action; it is acting from a corrupted world. Stronger models translate the critical boundary but do not remove the qualitative transition. These results make world-model collapse a measurable bottleneck for long-horizon agents.

📄 PDF Abstract BibTeX arXiv:2606.31399

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Posterior Collapse as a Phase Transition in Variational Autoencoders

2025-10-02 · Zhen Li, Fan Zhang, Zheng Zhang, Yu Chen arxiv

We investigate the phenomenon of posterior collapse in variational autoencoders (VAEs) from the perspective of statistical physics, and reveal that it constitutes a phase transition governed jointly by data structure and…

Understanding Performance Collapse in Layer-Pruned Large Language Models via Decision Representation Transitions

2026-05-08 · Boyu Shi, Chang Liu, ChuanBao Gao, Xu Yang 외 arxiv

Layer pruning efficiently reduces Large Language Model (LLM) computational costs but often triggers sudden performance collapse. Existing representation-based analyses struggle to explain this mechanism. We propose study…

Logical Phase Transitions: Understanding Collapse in LLM Logical Reasoning

2026-01-06 · Xinglang Zhang, Yunyao Zhang, ZeLiang Chen, Junqing Yu 외 arxiv

Symbolic logical reasoning is a critical yet underexplored capability of large language models (LLMs), providing reliable and verifiable decision-making in high-stakes domains such as mathematical reasoning and legal jud…

Mathematical ReasoningLogical Reasoning

Folding of Protein L with implications for collapse in the denatured state ensemble

2016-02-29

A fundamental question in protein folding is whether the coil to globule collapse transition occurs during the initial stages of folding (burst-phase) or simultaneously with the protein folding transition. Single molecul…

Protein Folding

Exact Phase Transitions in Deep Learning

2022-05-25 · Liu Ziyin, Masahito Ueda

This work reports deep-learning-unique first-order and second-order phase transitions, whose phenomenology closely follows that in statistical physics. In particular, we prove that the competition between prediction erro…

Deep Learning