Related papers: Configuration Smells in AGENTS.md Files: Common Mistakes in Configuring Coding Agents

Configuration Smells in AGENTS.md Files: Common Mistakes in Configuring Coding Agents

URL: http://arxiv.org/abs/2606.15828v4
Date: Fri, 19 Jun 2026 12:35:51 GMT
Title: Configuration Smells in AGENTS.md Files: Common Mistakes in Configuring Coding Agents
Abstract summary: We present the first catalog of smells for coding-agent configuration files.<n>To identify such smells, we first conducted a grey literature review and a repository mining analysis.<n>Our results show that configuration smells are widespread. Lint Leakage was the most common smell, affecting 62% of the files.
Score: 0.3298597939573778
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Coding agents are increasingly used to automate software engineering tasks. To guide their behavior, these agents commonly rely on configuration files, typically named AGENTS. md or CLAUDE. md, which provide instructions about architecture, workflows, coding conventions, and testing practices. Despite their growing importance, little is known about common problems affecting the definition and maintenance of these files. In this paper, we present the first catalog of smells for coding-agent configuration files. To identify such smells, we first conducted a grey literature review and a repository mining analysis. As a result, we identified six configuration smells and proposed automated heuristics to detect them. To evaluate the prevalence of the proposed smells, we analyzed 100 popular open-source repositories containing either an AGENTS. md or a CLAUDE. md file. Our results show that configuration smells are widespread. Lint Leakage was the most common smell, affecting 62% of the files, followed by Context Bloat (42%) and Skill Leakage (35%). We further show that several smells frequently co-occur, particularly Context Bloat, Skill Leakage, and Conflicting Instructions.

Related papers

Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction [57.138342889101345]
Tencent WorkBuddy Bench is a multi-domain evaluation suite for coding agents.<n>This report documents its construction methodology, scoring protocol, and a cross-model leaderboard.
arXiv Detail & Related papers (2026-07-23T04:34:06Z)
SmellBench: Towards Fine-Grained Evaluation of Code Agents on Refactoring Tasks [34.43588103259487]
SmellBench proactively injects code smells into clean code from real-world repositories.<n>It contains 294 cases spanning 7 popular smell types, 3 difficulty levels, 2 instruction settings across 7 real-world repositories.<n>Experiments show that the best combination - Qwenwen Code + Sonnet 4.5 - achieved only a 50.34 score of smell elimination.
arXiv Detail & Related papers (2026-06-04T01:49:07Z)
An Event-Driven Tool for Context-Aware Code Smell Detection Using SmellDSL [0.5424799109837065]
Code smells signal violations of design principles that degrade the internal quality of evolving software systems.<n>SmellHunter is a context-aware tool that interprets scripts written in the Smell domain-specific language to detect and code smells.<n>SmellHunter is integrated into the development environment via a dedicated plugin and provides aggregated insights via a mobile application.
arXiv Detail & Related papers (2026-05-20T03:43:32Z)
How to Interpret Agent Behavior [56.59836196946289]
We introduce ACT*ONOMY, a taxonomy for describing and analyzing agent behavior at runtime.<n>By providing a shared vocabulary, ACT*ONOMY helps researchers, agent designers, and end users interpret agent behavior more consistently.
arXiv Detail & Related papers (2026-05-13T14:52:40Z)
LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues [80.29362825271768]
LongMemEval-V2 is a benchmark for evaluating whether memory systems can help agents acquire the experience needed to become knowledgeable colleagues in customized environments.<n>LME-V2 contains 451 manually curated questions covering five core memory abilities for web agents.<n>We propose a suite of two memory methods: AgentRunbook-R, an efficient RAG-based memory with knowledge pools for raw state observations, events, and strategy notes, and AgentRunbook-C, which stores trajectories as files and invokes a coding agent to gather evidence in an augmented sandbox.
arXiv Detail & Related papers (2026-05-12T17:59:34Z)
SmellBench: Evaluating LLM Agents on Architectural Code Smell Repair [1.6922906233636834]
Architectural code smells erode software maintainability and are costly to repair manually.<n>We present the first empirical evaluation of large language model agents on architectural code smell repair.<n>We contribute SmellBench, a task orchestration framework that incorporates smell-type-specific optimized prompts.
arXiv Detail & Related papers (2026-05-07T22:33:32Z)
FS-Researcher: Test-Time Scaling for Long-Horizon Research Tasks with File-System-Based Agents [53.03492387564392]
We introduce FS-Researcher, a file-system-based framework that scales deep research beyond the context window via a persistent workspace.<n>A Context Builder agent browses the internet, writes structured notes, and archives raw sources into a hierarchical knowledge base that can grow far beyond context length.<n>A Report Writer agent then composes the final report section by section, treating the knowledge base as the source of facts.
arXiv Detail & Related papers (2026-02-02T03:00:19Z)
A Causal Perspective on Measuring, Explaining and Mitigating Smells in LLM-Generated Code [49.09545217453401]
Propensity Smelly Score (PSC) is a metric that estimates the likelihood of generating particular smell types.<n>We identify how generation strategy, model size, model architecture and prompt formulation shape the structural properties of generated code.<n> PSC helps developers interpret model behavior and assess code quality, providing evidence that smell propensity signals can support human judgement.
arXiv Detail & Related papers (2025-11-19T19:18:28Z)
Your Build Scripts Stink: The State of Code Smells in Build Scripts [7.543600033457145]
Insecure URLs were the most prevalent code smell in Maven build scripts.<n>HardcodedPaths/URLs were commonly observed in both Gradle and CMake scripts.<n>Wildcard Usage emerged as the most frequent smell in Makefiles.
arXiv Detail & Related papers (2025-06-22T09:01:42Z)
An Empirical Study of Dotfiles Repositories Containing User-Specific Configuration Files [1.7556600627464058]
Hundreds of thousands choose to publicly host their repositories on GitHub.<n>We collected and analyzed publicly-hosted dotfiles repositories on GitHub.<n>We found that 25.8% of the top 500 most-starred GitHub users maintain some form of publicly accessible dotfiles repository.
arXiv Detail & Related papers (2025-01-30T18:32:46Z)
FoC: Figure out the Cryptographic Functions in Stripped Binaries with LLMs [51.898805184427545]
We propose a novel framework called FoC to Figure out the Cryptographic functions in stripped binaries.<n>We first build a binary large language model (FoC-BinLLM) to summarize the semantics of cryptographic functions in natural language.<n>We then build a binary code similarity model (FoC-Sim) upon the FoC-BinLLM to create change-sensitive representations and use it to retrieve similar implementations of unknown cryptographic functions in a database.
arXiv Detail & Related papers (2024-03-27T09:45:33Z)
Task-Aware Specialization for Efficient and Robust Dense Retrieval for Open-Domain Question Answering [85.08146789409354]
We propose a new architecture, Task-awaredomain for dense Retrieval (TASER) TASER enables parameter sharing by interleaving shared and specialized blocks in a single encoder. Our experiments show that TASER can achieve superior accuracy, surpassing BM25, while using about 60% of the parameters as bi-encoder dense retrievers.
arXiv Detail & Related papers (2022-10-11T05:33:25Z)

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