DeltaEvolve: Accelerating Scientific Discovery through Momentum-Driven Evolution

TL;DR

DeltaEvolve introduces a momentum-driven evolutionary framework that uses semantic deltas instead of full-code histories, enabling more efficient and effective scientific discovery with less token consumption.

Contribution

It proposes a novel semantic delta approach within an EM framework, improving over full-code histories for guiding evolution in scientific discovery tasks.

Findings

Achieves better solutions with less token consumption.

Outperforms full-code-based evolutionary agents across diverse tasks.

Demonstrates efficiency and effectiveness in scientific discovery.

Abstract

LLM-driven evolutionary systems have shown promise for automated science discovery, yet existing approaches such as AlphaEvolve rely on full-code histories that are context-inefficient and potentially provide weak evolutionary guidance. In this work, we first formalize the evolutionary agents as a general Expectation-Maximization framework, where the language model samples candidate programs (E-step) and the system updates the control context based on evaluation feedback (M-step). Under this view, constructing context via full-code snapshots constitutes a suboptimal M-step, as redundant implement details dilutes core algorithmic ideas, making it difficult to provide clear inspirations for evolution. To address this, we propose DeltaEvolve, a momentum-driven evolutionary framework that replaces full-code history with structured semantic delta capturing how and why modifications between successive nodes affect performance. As programs are often decomposable, semantic delta usually contains many effective components which are transferable and more informative to drive improvement. By organizing semantic delta through multi-level database and progressive disclosure mechanism, input tokens are further reduced. Empirical evaluations on tasks across diverse scientific domains show that our framework can discover better solution with less token consumption over full-code-based evolutionary agents.