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

Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks

arXiv 2026 41.8 method

TLDR

Introduces Evolution Fine-Tuning (EFT) to teach LLMs to evolve solutions across optimization tasks, achieving cross-task generalization.

Reasoning

The paper presents a novel mid-training paradigm that leverages evolutionary search trajectories to enable cross-task generalization in LLMs, supported by a large dataset and empirical improvements. However, the focus is on optimization tasks rather than broader scientific discovery or research automation, limiting direct relevance to some keywords.

Read-first score

Read-first score 41.8, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 33.

Recency 8%
100

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

Methodology quality 25%
50

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

Reproducibility 25%
38

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

Topical relevance 42%
27.5

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

Frontier

Rank sensitivity

Stability: volatile; rank range: 35.

Keyword Scores

automated scientific discovery
5
AI for scientific research
5
automated experimentation
4
research automation
4
scientific discovery agent
4
AI scientist
3
automated research
3
experiment design agent
3
autonomous research agent
2
literature review agent
0
survey generation
0
paper writing agent
0

Deep Analysis

Innovations

  • Evolution Fine-Tuning (EFT): a mid-training paradigm that teaches LLMs to evolve solutions across tasks by converting evolutionary search trajectories into supervision.
  • Finch Collection: a dataset of 156K evolutionary search trajectories spanning 10 domains and 371 optimization tasks.
  • Transferring the capability of iterative solution evolution from the search scaffold to the model itself, enabling cross-task generalization.
  • EFT as a 'practice phase' for general-purpose discovery agents that do not solve new problems from scratch.

Methodology

EFT fine-tunes open-source LLMs (2B to 9B parameters) on the Finch Collection dataset of evolutionary search trajectories. The models are evaluated on 22 held-out optimization tasks and further paired with test-time reinforcement learning.

Key Results

EFT models outperform base counterparts by 10.22% on average across 22 held-out tasks. With test-time RL, the model matches state-of-the-art on two circle-packing tasks and outperforms its base counterpart on the Erdős minimum-overlap problem.

Tags