minimum-description-length

Tag

Cards List
#minimum-description-length

Minimum Description Length Unsupervisedly Separates Law-Grade from Statistical-Grade Knowledge in a Self-Improving Science Agent - and Reveals 86% of Its Own Discoveries Are Statistical

arXiv cs.AI ↗ · 2026-10-26

This paper shows that a deployed self-improving science agent already computes an MDL compression ratio that can unsupervisedly separate law-grade from statistical-grade scientific knowledge, recovering canonical laws with high significance while revealing 86% of its own admitted discoveries compress nothing — the first measured instance of a discovery agent auditing its own ledger and finding itself over-claiming.

0 favorites 0 likes
#minimum-description-length

Stochastic complexity of vectors containing cluster structure

arXiv cs.LG ↗ · 2026-09-02 Cached

This paper introduces a recursion formula for efficiently computing the stochastic complexity of vectors with cluster structure using the Normalized Maximum Likelihood model, reducing time complexity from polynomial to linear.

0 favorites 0 likes
#minimum-description-length

Where Induction Runs Out: Description-Length Difficulty and the Memorisation Gap in Integer-Sequence Benchmarks

arXiv cs.LG ↗ · 2026-09-01 Cached

This paper analyzes integer-sequence benchmarks for language models using minimum description length, revealing that these benchmarks often measure memorisation rather than inductive reasoning, and introduces a new difficulty measure.

0 favorites 0 likes
#minimum-description-length

SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure

Hugging Face Daily Papers ↗ · 2026-08-11 Cached

SkillZip is a new method for compressing the accumulated skills of self-evolving agents without evaluation rollouts, by finding a minimal faithful structural explanation that reuses repeated rules and procedures while preserving rare exceptions.

0 favorites 0 likes
← Back to home

Submit Feedback