How Should Agents See Code? Rethinking Code Representations for Agentic Software Engineering
cs.SE, cs.AI
Submitted: 2026-11-05
Updated: 2026-11-05
Code: https://github.com/MelikaSepidband/How-Should-Agents-See-Code
Project page: https://tree-sitter.github.io/tree-sitter/2https://github.com/davidhalter/jedi3https://github.com/mkdocstrings/griffe
Terminology
Sources
- GraphCoder: Enhancing Repository-Level Code Completion via Code Context Graph-based Retrieval and Language Model
- SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
- ARISE: A Repository-level Graph Representation and Toolset for Agentic Program Repair and Fault Localization
- RepoRepair: Leveraging Code Documentation for Repository-Level Automated Program Repair
- RepoQA: Evaluating Long Context Code Understanding
- 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