ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: QiHong Chen, Aaron Imani, Iftekhar Ahmed
• Venue: arXiv: cs.SE
• Published: 2026-07-09
• Collected: 2026-07-10
• URL: http://arxiv.org/abs/2607.08691v1
• PDF: https://arxiv.org/pdf/2607.08691v1
• DOI: UNKNOWN

Plain-Language Brief

The paper proposes ProjAgent, a new system for generating code at the repository level by introducing 'procedural similarity' as a retrieval signal. This method decomposes the target function into steps and retrieves relevant functions from the repository that exhibit similar procedural behavior. It also uses static analysis feedback to repair generated code. Evaluated on REPOCOD, ProjAgent outperformed existing baselines with 41.14% Pass@1.

What the Document Says

• The paper introduces ProjAgent, a system for generating code at the repository level.
• ProjAgent uses procedural similarity as an explicit retrieval signal.
• ProjAgent decomposes the target function into intermediate reasoning steps.
• ProjAgent retrieves repository functions that exhibit similar procedural behavior at each step.
• The retrieved procedural context is integrated with conventional semantic retrieval for a richer repository context.
• ProjAgent incorporates a conservative static-analysis feedback loop to repair generated code.
• The evaluation of ProjAgent on REPOCOD resulted in 41.14% Pass@1.
• ProjAgent outperformed existing retrieval-based baselines.

Key Concepts Mentioned

• repository-level code generation
• procedural similarity
• intermediate reasoning steps
• retrieved procedural context
• static analysis feedback

Claims Made by the Document

• ProjAgent is an effective system for generating code at the repository level.
• Procedural similarity is a previously unexplored retrieval dimension.

Evidence Used

• Achieved 41.14% Pass@1 in evaluation on REPOCOD.
• Outperformed existing retrieval-based baselines.

Methods / Approach

• Decomposition of the target function into intermediate reasoning steps.
• Agentic workflow to retrieve repository functions.
• Static-analysis feedback loop for code repair.

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

The paper does not mention any limitations in the provided text.

Open Questions

• What is the specific algorithm used for procedural similarity analysis?
• How efficient is ProjAgent compared to other code generation systems?

Notes for Future Q&A

May include interpretation. Labeled where it does.

The paper focuses on presenting the concept and evaluation of ProjAgent, but it does not provide detailed information about its implementation or comparison with other similar systems.

Raw Abstract / Excerpt

Repository-level code generation requires implementing target functions while accounting for complex cross-file dependencies and project-specific conventions. Existing retrieval methods predominantly rely on lexical, structural, or semantic similarity, often overlooking repository functions that implement similar procedural logic despite differing in identifiers or application domains. We propose ProjAgent, a repository-level code generation system that introduces procedural similarity as an explicit retrieval signal. ProjAgent decomposes the target function into intermediate reasoning steps and employs an agentic workflow to retrieve repository functions that exhibit similar procedural behavior at each step. The retrieved procedural context is integrated with conventional semantic retrieval to construct a richer repository context for code generation. ProjAgent further incorporates a conservative static-analysis feedback loop that iteratively repairs generated code using compiler and static-analysis feedback. Evaluated on REPOCOD, ProjAgent achieves 41.14% Pass@1, outperforming existing retrieval-based baselines. These results demonstrate that procedural similarity is an effective and previously unexplored retrieval dimension for repository-level code generation.