# AlgoPilot: Fully Autonomous Program Synthesis Without Human-Written Programs

arXiv: https://arxiv.org/abs/2501.06423 · HTML: https://mlsanity.com/paper/2501.06423/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 14 references that are in the map.
- First posted on arXiv 11 Jan 2025.

## Builds on (most cited first, 8 of 8)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Neural Turing Machines](https://mlsanity.com/paper/1410.5401/) (2014)
- [DeepCoder: Learning to Write Programs](https://mlsanity.com/paper/1611.01989/) (2016)
- [RobustFill: Neural Program Learning under Noisy I/O](https://mlsanity.com/paper/1703.07469/) (2017)
- [Neural Programmer-Interpreters](https://mlsanity.com/paper/1511.06279/) (2015)
- [A Generalist Neural Algorithmic Learner](https://mlsanity.com/paper/2209.11142/) (2022)
- [Neural Algorithmic Reasoning with Causal Regularisation](https://mlsanity.com/paper/2302.10258/) (2023)
- [Neural Program Synthesis with Priority Queue Training](https://mlsanity.com/paper/1801.03526/) (2018)

## Abstract (arXiv)

Program synthesis has traditionally relied on human-provided specifications, examples, or prior knowledge to generate functional algorithms. Existing methods either emulate human-written algorithms or solve specific tasks without generating reusable programmatic logic, limiting their ability to create novel algorithms. We introduce AlgoPilot, a groundbreaking approach for fully automated program synthesis without human-written programs or trajectories. AlgoPilot leverages reinforcement learning (RL) guided by a Trajectory Language Model (TLM) to synthesize algorithms from scratch. The TLM, trained on trajectories generated by random Python functions, serves as a soft constraint during the RL process, aligning generated sequences with patterns likely to represent valid algorithms. Using sorting as a test case, AlgoPilot demonstrates its ability to generate trajectories that are interpretable as classical algorithms, such as Bubble Sort, while operating without prior algorithmic knowledge. This work establishes a new paradigm for algorithm discovery and lays the groundwork for future advancements in autonomous program synthesis.