Awesome Auto Research Hub Papers · Datasets · Projects
← Back to papers

SMCEvolve: Principled Scientific Discovery via Sequential Monte Carlo Evolution

arXiv 2026 68.2 method

TLDR

SMCEvolve uses Sequential Monte Carlo to guide LLM-driven program evolution for principled scientific discovery with convergence guarantees.

Reasoning

The paper introduces a novel SMC-based framework that provides theoretical guarantees and outperforms existing systems on diverse benchmarks. Its strength lies in principled design and finite-sample analysis, but the abstract lacks details on limitations or comparisons to non-LLM methods.

Read-first score

Read-first score 68.2, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 71.

Recency 8%
100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Reproducibility 25%
81

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=True; dataset=False; markers=code,github

Methodology quality 25%
60

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=analysis,benchmark

Topical relevance 42%
59.2

Uses existing LLM keyword relevance scores normalized to 0-100. AI scientist,automated scientific discovery,autonomous research agent,automated research,literature review agent,survey generation,automated experimentation,experiment design agent,AI for scientific research,paper writing agent,research automation,scientific discovery agent

Field roles

FrontierBridgeReproducibility anchor

Rank sensitivity

Stability: volatile; rank range: 38.

Keyword Scores

automated scientific discovery
10
AI for scientific research
9
scientific discovery agent
9
automated research
8
research automation
8
AI scientist
7
autonomous research agent
6
automated experimentation
6
experiment design agent
5
literature review agent
1
survey generation
1
paper writing agent
1

Deep Analysis

Innovations

  • Recasting program search as sampling from a reward-tilted target distribution using Sequential Monte Carlo
  • Adaptive parent resampling
  • Mixture of mutation with acceptance
  • Automatic convergence control
  • Finite-sample complexity analysis bounding LLM-call budget for target approximation error

Methodology

SMCEvolve frames program evolution as sampling from a reward-tilted distribution using a Sequential Monte Carlo sampler, incorporating adaptive parent resampling, a mixture of mutation with acceptance, and automatic convergence control. It includes a finite-sample complexity analysis bounding LLM-call budget for target approximation error, and is evaluated on math, algorithm efficiency, symbolic regression, and end-to-end ML research benchmarks.

Key Results

SMCEvolve surpasses state-of-the-art evolving systems across math, algorithm efficiency, symbolic regression, and end-to-end ML research benchmarks while using fewer LLM calls under self-determined termination.

Tags

AILGMA