Self-Improving Language Models with Bidirectional Evolutionary Search

arXiv:2605.28814 · cs.CL · Submitted 2026-05-27 · Read on arXiv

cs.CL

Submitted: 2026-05-27

Updated: 2026-10-13

Code: https://github.com/Embodied-Minds-Lab/BES

Terminology

• Bidirectional Evolutionary Search — 2× in this paper
• Agentic System — 1× in this paper · explained in 2 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Best-of-N Sampling — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
• FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI
• The Llama 3 Herd of Models
• ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution
• AlphaEvolve: A coding agent for scientific and algorithmic discovery
• Maximum Likelihood Reinforcement Learning
• Gemma 3 Technical Report
• ThetaEvolve: Test-time Learning on Open Problems
• DAPO: An Open-Source LLM Reinforcement Learning System at Scale
• Learning to Discover at Test Time

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering