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

• URL: http://arxiv.org/abs/2606.22417v1
• Date: Sun, 21 Jun 2026 10:10:51 GMT
• Title: Code Isn't Memory: A Structural Codebase Index Inside a Coding Agent
• Abstract summary: We run three arms (the harness with the index, the same harness without it, and an agentic- comparator) on SWE-PolyBench and SWE-bench Pro with Opus 4.7 held fixed throughout.<n>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.<n>The deployment question for a structural index is thus not whether it is too expensive to run (across seeds, the index lands at a lower $/solved than agentic) but whether the workload includes multi-file changes where structural ranking pays off
• Score: 0.13999481573773073
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Codebook Agent: Amortized Topology Design for LLM Multi-Agent Systems [67.04448659688579]
  We develop a query-independent 16-entry codebook that ranks the top decoded candidates in a single batched forward pass.<n>With no iterative search and no message passing at test time, Codebook Agent is the most accurate method on all six benchmarks.
  arXiv  Detail & Related papers  (2026-09-02T08:10:22Z)
• When Does Restricting a Coding Agent to execute_code Help? A Regime $\ imes$ Agent-Design Ablation [20.672156968511587]
  We run a comparison of three-arm ablation (baseline / bash_only / code_only) on synthetic computation tasks and SWE-bench Mini modification tasks.<n>Across the four resulting (regime, agent) cells, restricting the agent to a single execute_code MCP tool is cheaper than -- or statistically tied with -- its cheapest tool-rich rival.<n>The lone exception is SWE-bench/Claude, where code_only is directionally costlier.
  arXiv  Detail & Related papers  (2026-07-12T04:52:08Z)
• SHERLOC: Structured Diagnostic Localization for Code Repair Agents [33.35079971033214]
  We introduce SHERLOC, a training-free framework pairing a reasoning LLM with compact repository tools and self-recovery.<n>SHERLOC reaches state-of-the-art localization across model scales: 84.33% accuracy@1 on SWE-Bench Lite and 81.27% recall@1 on SWE-Bench Verified.
  arXiv  Detail & Related papers  (2026-06-23T17:05:50Z)
• Probe-and-Refine Tuning of Repository Guidance for Coding Agents [0.0]
  LLM-based coding agents need higher-level operational knowledge about a repository.<n>Recent studies disagree on whether LLM-generated guidance improves or harms agent performance.<n>In this paper we show that how the guidance is produced is the decisive variable.
  arXiv  Detail & Related papers  (2026-06-18T17:30:15Z)
• SCDBench: A Benchmark for LLM-Based Smart Contract Decompilers [55.39407031861402]
  We introduce SCDBench, a dataset and benchmark methodology for smart contract decompilation.<n>The dataset contains 600 real-world Solidity contracts with paired bytecode inputs, ground-truth source code, and replayable semantic checkpoints.<n>We evaluate Claude Opus 4.7, GPT-5.3-Codex, and GLM-5 in a zero-shot decompilation setting, including GLM-5 variants with and without extended reasoning.
  arXiv  Detail & Related papers  (2026-05-27T20:08:47Z)
• BLAgent: Agentic RAG for File-Level Bug Localization [2.2917707112773593]
  BLAgent is a novel agentic RAG framework for file-level bug localization.<n> BLAgent attains over 78% Top-1 accuracy with open-source models.<n> BLAgent improves end-to-end repair success by over 20%.
  arXiv  Detail & Related papers  (2026-05-18T07:20:13Z)
• MEME: Multi-entity & Evolving Memory Evaluation [76.57263966646404]
  MEME defines six tasks spanning the full space defined by the multi-entity and evolving axes.<n> evaluating six memory systems spanning three memory paradigms on 100 controlled episodes.<n>We find that all systems collapse on dependency reasoning under the default configuration.
  arXiv  Detail & Related papers  (2026-05-12T17:55:10Z)
• Mitigating Implicit Inconsistencies in Patch Porting [13.153399281876451]
  Implicit inconsistencies pose challenges for developers to resolve due to their non-local nature.<n>We propose MIP, which enables collaboration among an LLM, a compiler, and code analysis utilities.<n> Experiments on two representative scenarios, cross-fork and cross-branch patch porting, show that MIP successfully resolves more than twice as many patches as the best-performing baseline in both settings.
  arXiv  Detail & Related papers  (2026-04-02T06:33:31Z)
• Pull Requests as a Training Signal for Repo-Level Code Editing [49.82435173554125]
  Clean Pull Request (Clean-PR) is a mid-training paradigm that leverages real-world GitHub pull requests as a training signal for repository-level editing.<n>We introduce a scalable pipeline that converts noisy pull request diffs into Search/Replace edit blocks through reconstruction and validation.<n>On SWE-bench, our model significantly outperforms the instruction-tuned baseline, achieving absolute improvements of 13.6% on SWE-bench Lite and 12.3% on SWE-bench Verified.
  arXiv  Detail & Related papers  (2026-02-07T09:22:25Z)
• Co-Designing Quantum Codes with Transversal Diagonal Gates via Multi-Agent Systems [1.5948632947109136]
  We present a multi-agent, human-in-the-loop workflow that co-designs quantum codes with prescribed diagonal gates.<n>The workflow is powered by GPT-5 and implemented within RA (https://texra.ai)-a multi-agent research assistant platform.
  arXiv  Detail & Related papers  (2025-10-23T16:45:39Z)
• Where LLM Agents Fail and How They can Learn From Failures [62.196870049524364]
  Large Language Model (LLM) agents have shown promise in solving complex, multi-step tasks.<n>They amplify vulnerability to cascading failures, where a single root-cause error propagates through subsequent decisions.<n>Current systems lack a framework that can comprehensively understand agent error in a modular and systemic way.<n>We introduce the AgentErrorTaxonomy, a modular classification of failure modes spanning memory, reflection, planning, action, and system-level operations.
  arXiv  Detail & Related papers  (2025-09-29T18:20:27Z)
• MapCoder-Lite: Squeezing Multi-Agent Coding into a Single Small LLM [9.44363104217319]
  MapCoder-Lite upgrades a single 7B model into four role-specialised agents-retriever, planner, coder, and debugger-using only rank-32.<n>MapCoder-Lite more than doubles xCodeEval accuracy (from $13.2%$ to $28.3%$), eliminates all format failures, and closes to within six points of a 32B baseline.
  arXiv  Detail & Related papers  (2025-09-22T08:19:11Z)
• Don't Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration Pitfalls [83.89771461061903]
  Recent advancements in tree search algorithms guided by verifiers have significantly enhanced the reasoning capabilities of large language models (LLMs)<n>Recent advancements in tree search algorithms guided by verifiers have significantly enhanced the reasoning capabilities of large language models (LLMs)<n>We identify two key challenges contributing to this inefficiency: $textitover-exploration$ due to redundant states with semantically equivalent content, and $textitunder-exploration$ caused by high variance in verifier scoring.<n>We propose FETCH, a flexible, plug-and-play system compatible with various tree search algorithms.
  arXiv  Detail & Related papers  (2025-02-16T16:12:01Z)
• On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents [58.79302663733703]
  Large language model-based multi-agent systems have shown great abilities across various tasks due to the collaboration of expert agents.<n>The impact of clumsy or even malicious agents--those who frequently make errors in their tasks--on the overall performance of the system remains underexplored.<n>This paper investigates what is the resilience of various system structures under faulty agents on different downstream tasks.
  arXiv  Detail & Related papers  (2024-08-02T03:25:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.