Skeleton Coding: Program Structure as Control for AI Agents
cs.SE, cs.AI, cs.LG
Submitted: 2026-10-28
Updated: 2026-11-14
Code: https://github.com/strands-labs/ai-functions
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks
- ProgramBench: Can Language Models Rebuild Programs From Scratch?
- RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation
- Interactive Code Generation via Test-Driven User-Intent Formalization
- Design Docs Are All You Need: An AI-native Machine-Learning Performance Tool
- SpecFirst: Behavioral Specification Elicitation as a First-Class Step in Agent-Based Program Synthesis from Scratch
- AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement
- A benchmark for vericoding: formally verified program synthesis
- Evaluating Large Language Models Trained on Code
Related papers
- ArkEval: Benchmarking and Evaluating Automated CodeRepair for ArkTS
- TestPrism: Rethinking Test Evaluation Beyond a Single Reference
- Mining Workflow Graphs for Black-Box Boundary Testing of Conversational LLM Agents
- Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
- GitSkills: A Dataset of Agent Skills on GitHub
- For Coding Agents, the Repository Matters