Code Isn't Memory: A Structural Codebase Index Inside a Coding Agent

2026-06-21 · Ishaan Bhola, Adithyan Krishnan, Sravanth Kurmala, Mukunda NS arxiv

Coding agents now interleave LLMs with retrieval over the working repository, and retrieval implementations vary widely across deployed harnesses. Inside a fixed coding-agent harness on a fixed model, does adding a structural codebase index actually change cost or resolve? We ran three arms (the harness with the index, the same harness without it, and an agentic-grep comparator) on SWE-PolyBench Verified and SWE-bench Pro with Claude Opus 4.7 held fixed throughout, across three seeds, inside a leak-audited per-task sandbox. The within-harness ablation produces a large localization gain and a statistically separated resolve gain, with no cost penalty per cell and lower cost per solve. The cross-harness check shows that the index does not regress against an agentic-grep baseline on resolve or localization, again at no cost penalty. We release the per-cell exclusion ledger, the leak-audit script, the localization extractor, and the results database. The deployment question for a structural codebase index is thus not whether it is too expensive to run (across seeds, the index lands at a lower $/solved than agentic grep) but whether the workload includes multi-file changes where structural ranking pays off.

📄 PDF Abstract BibTeX arXiv:2606.22417

Code (0)

등록된 구현이 없습니다.

Codebase-Memory: Tree-Sitter-Based Knowledge Graphs for LLM Code Exploration via MCP

2026-03-28 · Martin Vogel, Falk Meyer-Eschenbach, Severin Kohler, Elias Grünewald 외 arxiv

Large Language Model (LLM) coding agents typically explore codebases through repeated file-reading and grep-searching, consuming thousands of tokens per query without structural understanding. We present Codebase-Memory,…

Knowledge Graphs

Retrieval-Conditioned Topology Selection with Provable Budget Conservation for Multi-Agent Code Generation

2026-05-07 · Abhijit Talluri, Pujith Anne, Bhagavan Choudary Pendiyala, Raghavendra Chilukuri arxiv

Multi-agent LLM systems for code generation face a fundamental routing problem: the optimal orchestration topology depends on the structural complexity of the code under modification, yet existing systems select topologi…

Code Generation

Gistify! Codebase-Level Understanding via Runtime Execution

2025-10-30 · Hyunji Lee, Minseon Kim, Chinmay Singh, Matheus Pereira 외 arxiv

As coding agents are increasingly deployed in large codebases, the need to automatically design challenging, codebase-level evaluation is central. We propose Gistify, a task where a coding LLM must create a single, minim…

CodeComp: Structural KV Cache Compression for Agentic Coding

2026-04-11 · Qiujiang Chen, Jing Xiong, Chenyang Zhao, Sidi Yang 외 arxiv

Agentic code tasks such as fault localization and patch generation require processing long codebases under tight memory constraints, where the Key-Value (KV) cache becomes the primary inference bottleneck. Existing compr…

Code Generation

CodeNav: Beyond tool-use to using real-world codebases with LLM agents

2024-06-18 · Tanmay Gupta, Luca Weihs, Aniruddha Kembhavi

We present CodeNav, an LLM agent that navigates and leverages previously unseen code repositories to solve user queries. In contrast to tool-use LLM agents that require ``registration'' of all relevant tools via manual d…