cs.AINov 10, 2026

AutoAssumption: Searching over Assumptions Discovers ML-Systems Algorithms

Authors: Igor Sadalski, Minghao Guo, Benjamin Jones, Wojciech Matusik

Organizations: MIT CSAIL, Cambridge, MA, USA.

Abstract

Many advances in ML systems came from breaking an assumption that earlier methods took for granted: speculative decoding dropped the assumption that a model needs one forward pass per token. Yet algorithms rarely state their assumptions, so experts and discovery harnesses search over programs, where one edit changes several design choices and gains are difficult to attribute. Searching over the assumptions themselves remains largely unexplored. Writing algorithms as proofs makes their assumptions explicit and turns algorithm design into a search over a small, structured space that an LLM can explore and a proof checker can audit. We formalize 89 algorithms from KV-cache eviction, weight pruning and speculative decoding as proof graphs with explicit assumptions, checked in Lean. Our harness, AutoAssumption, relaxes one assumption of a published method, re-derives and re-proves it, and generates its code. In KV-cache eviction and weight pruning, this search improved on every published algorithm we ran and produced state-of-the-art algorithms. The eviction algorithm has the highest RULER-4K score of the published methods we ran, and the pruning algorithm the lowest perplexity of thirteen on four LLaMA models. At equal budget, the harness scores within a point of OpenEvolve, an open-source implementation of AlphaEvolve, with a lower standard deviation across repeats. Future work will formalize more fields and combine them through the principal assumptions they share.

Figures & tables

Appendix figures & tables14 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. SeaEvo: Advancing Algorithm Discovery with Strategy Space Evolution

    Apr 27, 2026Sichun Luo, Yi Huang, Haochen Luo +7Automated Algorithm DiscoveryEvolutionary Optimization