Research

Academic papers, cookbooks, and resources that inform iofold's approach to self-improving agents

Featured: GEPA - 35x More Efficient Than RL

iofold is built on GEPA (Genetic-Pareto Agent Evolution), which achieves state-of-the-art results with 400-1,200 rollouts instead of 24,000 required by traditional RL. The key: reflective mutation where LLMs analyze failures and propose improvements, combined with Pareto selection across training instances.

Read the paper

Genetic Evolution for Agents

Evolutionary algorithms that outperform RL for agent optimization

Reward Modeling

Techniques for scoring agent trajectories without extensive human labeling

LLM-as-Judge

Using language models to evaluate other language models

Prompt Optimization

Automatic optimization of prompts using feedback and gradients

Automatic Eval Generation

Automatically generating evaluations and benchmarks for LLMs

Code as Evals

Using executable code and programmatic methods for evaluation

Rollout Generation & Simulation

Generating agent trajectories efficiently without expensive real-world execution

User Behavior Simulation

Modeling realistic user interactions for multi-turn agent evaluation

Contribute Resources

Know of a paper, tool, or resource that should be on this page? We'd love to hear from you.