Proof-Carrying Evolution: Black-Box Search, White-Box Flight
cs.RO, cs.NE, cs.SY, eess.SY
Submitted: 2026-10-30
Updated: 2026-10-30
Code: https://github.com/karpathy/autoresearch
License: http://creativecommons.org/licenses/by/4.0/
The gist: We study whether a language model can help design controllers whose behavior can be formally checked.
Terminology
Abstract
We study whether a language model can help design controllers whose behavior can be formally checked. In proof-carrying evolution (PCE), a search proposes controllers together with their certificates. Their mathematical forms are fixed; a proposer chooses their numerical parameters together. Certificate checks guide selection, and only a certified candidate can be returned. The deployed artifact is a control law and its certificate; the language model is used only during design. We compare four language models with classical search and synthesis on docking under a speed limit, pursuit of a maneuvering target, and attitude control on SO(3), using paired runs and shared proposal allowances. Certificates are checked in exact rational arithmetic during search on the linear problems. On SO(3), the search uses floating-point checks, followed by exact re-verification of every reported champion. The best run of each method also receives Lean 4 proofs of its stated control properties. On the linear problems, the strongest models beat the standard classical baselines on every run, but a classical optimizer that chooses certificates for the same objective closes most of that lead. Among the cited pursuit champions, the ranking does not survive a change from Euler to zero-order-hold dynamics. On SO(3), no model detectably outperforms CMA-ES when mixed with classical mutation. When models write every proposal, one tested model improves on CMA-ES and the other performs worse than its mixed variant. All search medians remain below the hand-tuned law. In a docking control with the objective and mutation operator held fixed, retaining certified candidates yields new certified designs in every run; removing this rule yields none.
Sources
- Visual Language Models as Operator Agents in the Space Domain
- Simple Baselines are Competitive with Code Evolution
- Agentic AutoResearch forSpace Autonomy: An Auditable, LLM-Driven Research Agent for Aerospace Control Problems
- Multi-Phase Spacecraft Trajectory Optimization via Transformer-Based Reinforcement Learning
- AIDE: AI-Driven Exploration in the Space of Code
- Meta-Harness: End-to-End Optimization of Model Harnesses
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition
- Language Models are Spacecraft Operators
- Fine-Tuned Language Models as Space Systems Controllers
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation