AGAR: a reinforcement learning substrate for LLM program evolution

arXiv:2610.09215 · cs.AI, cs.MA · Submitted 2026-10-06 · Read on arXiv

cs.AI, cs.MA

Submitted: 2026-10-06

Updated: 2026-10-06

Code: https://github.com/radixark/miles

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Reinforcement Learning — 1× in this paper · explained in 4 episodes

Sources

• Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning
• SMCEvolve: Principled Scientific Discovery via Sequential Monte Carlo Evolution
• ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution
• EvoX: Meta-Evolution for Automated Discovery
• Agent Lightning: Train ANY AI Agents with Reinforcement Learning
• AlphaEvolve: A coding agent for scientific and algorithmic discovery
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• TextGrad: Automatic "Differentiation" via Text

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems