AnalysisOpinion / analysisLarge Language Models1 source · Sep 29, 2026

The Communication Bottleneck: A Round-Trip Study of Tree-Structured Expression Serialization in Language Models

The Communication Bottleneck: A Round-Trip Study of Tree-Structured Expression Serialization in Language Models

Key points

  • When language models reason in chain-of-thought or exchange free-text intermediates, they serialize structured information into natural language.
  • How much tree-structured compositional content survives this bottleneck?
  • We propose a round-trip protocol that answers this question empirically for tree-structured expressions.
  • Together these results identify tree-structured expression serialization as a primary limiting factor when models communicate hierarchical structure through natural language.

Sources (1)

Extractive summary: sentences quoted from the sources.

Before this

  1. Sep 28, 2026openai/openai-python v3.20.0
  2. Sep 24, 2026openai/openai-python v3.19.2
  3. Sep 2, 2026pytorch/pytorch v2.14.0: PyTorch 2.14.0 Release
  4. Jul 15, 2026huggingface/transformers v5.14.0: Release v5.14.0
  5. Jul 8, 2026pytorch/pytorch v2.13.0: PyTorch 2.13.0 Release
  6. Jun 10, 2026DiffusionGemma: 4x faster text generation

Related