Can Coding Agents Solve Repository-Level Issues with Rendered Code? An Exploratory Study of Visual Representations

• URL: http://arxiv.org/abs/2608.09268v1
• Date: Mon, 10 Aug 2026 08:24:19 GMT
• Title: Can Coding Agents Solve Repository-Level Issues with Rendered Code? An Exploratory Study of Visual Representations
• Abstract summary: We study whether rendering code as images can serve as operational context for agentic coding.<n> Rendered code consistently reduces prompt-token cost, but the savings do not increase linearly with the visual compression ratio.<n>It largely preserves end-to-end repair accuracy, but does not overcome the performance limits of the underlying model or agent architecture.
• Score: 30.48772161139388
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Visual modality has recently been explored as a way to compress textual tokens, including rendering code as images for static code understanding. We study whether this representation can serve as operational context for agentic coding, where an agent must navigate repositories, edit source files, and verify executable patches. Using SWE-bench Verified, we evaluate rendered code in repository-level repair workflows and introduce controlled agent settings to separate unguided repository exploration from more structured repair stages. Our results show a mixed picture. Rendered code consistently reduces prompt-token cost, but the savings do not increase linearly with the nominal visual compression ratio. It largely preserves end-to-end repair accuracy, but does not overcome the performance limits of the underlying model or agent architecture, and can become unstable under aggressive compression. Further analysis suggests that visual code is most useful when raw source reading is a major bottleneck; once repository localization is structured, much of the remaining cost comes from patch--test trial-and-error, where visual compression has limited leverage. Overall, our study positions rendered code as a viable but conditional compression mechanism for realistic coding agents.

Related papers

• RepoAtlas: Guiding Coding Agents via Evolving Multimodal Repository Views [14.618487825419328]
  We present textbfRepoAtlas, a training-free module that maintains evolving multimodal repository views.<n>RepoAtlas combines evidence from the issue with the agent's current exploration state to select a task-relevant region under a fixed budget.<n>We evaluate RepoAtlas on SWE-bench Verified, where it improves the resolve rate by 2.4 points while reducing input tokens and model calls by 5.8% and 7.8% on average.
  arXiv  Detail & Related papers  (2026-09-15T10:11:51Z)
• TRACE: Trajectory-robust Admission with Evidence Ordering for Efficient GUI Agents [54.88208747581851]
  Training-free visual token pruning can reduce this cost, but cache reuse introduces a fundamental constraint.<n>We propose textbfmethod, a training-free framework for emphtextbfTrajectory-textbfrobust textbfAdmission and textbfCoverage-aware textbfEvidence ordering.
  arXiv  Detail & Related papers  (2026-09-09T15:12:48Z)
• CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding [13.113776703707634]
  CodeShrink is an adaptive visual compression framework with three components.<n>Blank-Free Rendering replaces whitespace-dependent layouts with compact layouts and explicit structural markers, removing layout-induced tokens.<n> Dominant Token Selection jointly analyzes the instruction and code image to prune task-irrelevant visual tokens during inference.
  arXiv  Detail & Related papers  (2026-07-31T17:15:51Z)
• LLM Agents Can See Code Repositories [14.881212557304414]
  Coding agents powered by large language models have demonstrated strong performance on software engineering tasks.<n>Most agents consume repositories almost entirely as text.<n>Visual graphs of repository structure as a supplementary modality alongside standard text interfaces helps agents understand structure more efficiently.
  arXiv  Detail & Related papers  (2026-06-12T03:14:40Z)
• RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations [51.43574078961796]
  We introduce RepoMirage, a two-stage evaluation suite built on SWE-Bench Verified.<n>RepoMirage-Perturb applies three types of semantics-preserving repository-level perturbations, revealing a clear performance drop when correct solving requires broader context access.<n>We propose RepoAnchor, a structure-first prototype workflow that separates repository exploration from downstream problem solving.
  arXiv  Detail & Related papers  (2026-05-25T06:26:43Z)
• BUILD-AND-FIND: An Effort-Aware Protocol for Evaluating Agent-Managed Codebases [0.0]
  We introduce BUILD-AND-FIND, a protocol for evaluating whether downstream agents can recover intended choices from generated repositories.<n>For each task, a builder sees a hidden repository specification and creates a specification-traced multiple-choice question bank.<n>The protocol separates behavioral correctness from artifact-side recovery and reports recovery accuracy, repeatability, implementation coverage, and inspection effort.
  arXiv  Detail & Related papers  (2026-05-07T12:35:27Z)
• IMPACT-CYCLE: A Contract-Based Multi-Agent System for Claim-Level Supervisory Correction of Long-Video Semantic Memory [73.22944697933603]
  Existing pipelines produce opaque, end-to-end outputs that expose no intermediate state for inspection.<n>We present IMPACT-Cycle, a supervisory multi-agent system that reformulates long-video understanding as a multimodal iterative claim-level maintenance.
  arXiv  Detail & Related papers  (2026-04-22T03:03:33Z)
• Learning to Commit: Generating Organic Pull Requests via Online Repository Memory [11.042326503752756]
  Large language model (LLM)-based coding agents achieve impressive results on controlled benchmarks yet routinely produce pull requests that real maintainers reject.<n>We introduce Learning to Commit, a framework that closes this gap through Online Repository Memory.
  arXiv  Detail & Related papers  (2026-03-27T17:58:56Z)
• RECODE: Reasoning Through Code Generation for Visual Question Answering [68.86938437188964]
  We propose to leverage derendering -- the process of reverse-engineering visuals into executable code -- as a new modality for verifiable visual reasoning.<n>Our work demonstrates that grounding visual perception in executable code provides a new path toward more accurate and verifiable multimodal reasoning.
  arXiv  Detail & Related papers  (2025-10-15T17:05:37Z)
• Dense Retrievers Can Fail on Simple Queries: Revealing The Granularity Dilemma of Embeddings [65.31723739561151]
  This work stems from an observed limitation of text encoders: embeddings may not be able to recognize fine-grained entities or events within encoded semantics.<n>We introduce a new evaluation dataset, CapRetrieval, in which passages are image captions and queries are phrases targeting entity or event concepts in diverse forms.<n>We finetune encoders with our proposed data generation strategies, enabling a small 0.1B encoder to outperform the state-of-the-art 7B model.
  arXiv  Detail & Related papers  (2025-06-10T09:00:33Z)
• RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation [96.75695811963242]
  RepoCoder is a framework to streamline the repository-level code completion process. It incorporates a similarity-based retriever and a pre-trained code language model. It consistently outperforms the vanilla retrieval-augmented code completion approach.
  arXiv  Detail & Related papers  (2023-03-22T13:54:46Z)

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.