Agentic Repository Mining: A Multi-Task Evaluation

• URL: http://arxiv.org/abs/2605.04845v1
• Date: Wed, 06 May 2026 12:43:46 GMT
• Title: Agentic Repository Mining: A Multi-Task Evaluation
• Abstract summary: Mining software repositories often requires classifying artifacts like commits, reviews, code lines, or entire repositories into categories.<n>We investigate whether LLM agents that dynamically explore repositories through standard bash commands can match the classification quality of simple LLMs that receive pre-engineered context.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Mining software repositories often requires classifying artifacts like commits, reviews, code lines, or entire repositories into categories. Human labeling is expensive and error-prone; limited context frequently leads to misclassifications or uncertainty in labels. We investigate whether LLM agents that dynamically explore repositories through standard bash commands can match the classification quality of simple LLMs that receive pre-engineered context. Across four tasks, eight approach configurations, and 4943 classifications, agents achieve competitive accuracy despite retrieving their own context. The primary advantage is robustness: agents avoid context-window overflows and scale independently of artifact size. A manual diagnosis of 100 cases where approaches disagree with the ground truth reveals specification ambiguities and labels produced under limited context, suggesting that accuracy against such ground truth may underestimate approaches with broader context access.

Related papers

• Adaptive Critical Token-Aware Retrieval for Repository-Level Code Generation [53.85136813868056]
  ACToR is an adaptive critical token-aware retrieval framework for repository-level code generation.<n>We show that ACToR consistently outperforms state-of-the-art methods on repository-level benchmarks.
  arXiv  Detail & Related papers  (2026-09-01T17:59:39Z)
• When Benchmarks Lie: Evaluating Malicious Prompt Classifiers Under True Distribution Shift [0.0]
  We present a comprehensive analysis using a benchmark of 18 datasets spanning harmful requests, jailbreaks, indirect prompt injections, and extraction attacks.<n>We propose Leave-One-Dataset-Out (LODO) evaluation to measure true out-of-distribution generalization.
  arXiv  Detail & Related papers  (2026-02-15T14:21:43Z)
• Favia: Forensic Agent for Vulnerability-fix Identification and Analysis [5.43098755190303]
  We propose Favia, a forensic, agent-based framework for vulnerability-fix identification.<n>Favia combines scalable candidate ranking with deep and iterative semantic reasoning.<n>We evaluate Favia on CVEVC, a large-scale dataset we made that comprises over 8 million commits from 3,708 real-world repositories.
  arXiv  Detail & Related papers  (2026-02-13T00:51:22Z)
• Exploring Semantic Labeling Strategies for Third-Party Cybersecurity Risk Assessment Questionnaires [0.3568466510804538]
  Third-Party Risk Assessment (TPRA) is a core cybersecurity practice for evaluating suppliers against standards such as ISO/IEC and NIST.<n>This paper explores strategies for organizing and retrieving TPRA cybersecurity questions using semantic labels.
  arXiv  Detail & Related papers  (2026-02-09T18:36:50Z)
• Instruction Boundary: Quantifying Biases in LLM Reasoning under Various Coverage [34.247904738521136]
  We investigate how different instruction formats can either facilitate or mislead LLM reasoning ability.<n>We introduce the concept of Instruction Boundary, which systematically analyzes how different levels of prompt coverage can lead to reasoning biases.<n>We propose BiasDetector, a unified framework that quantifies LLMs' ability to identify sparse labels under different kinds of Instruction Boundary conditions.
  arXiv  Detail & Related papers  (2025-09-24T16:15:26Z)
• CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward [50.97588334916863]
  We develop CompassVerifier, an accurate and robust lightweight verifier model for evaluation and outcome reward.<n>It demonstrates multi-domain competency spanning math, knowledge, and diverse reasoning tasks, with the capability to process various answer types.<n>We introduce VerifierBench benchmark comprising model outputs collected from multiple data sources, augmented through manual analysis of metaerror patterns to enhance CompassVerifier.
  arXiv  Detail & Related papers  (2025-08-05T17:55:24Z)
• Self-Regularization with Sparse Autoencoders for Controllable LLM-based Classification [29.74457390987092]
  We propose a novel framework to identify and regularize unintended features in large language models (LLMs) latent spaces.<n>We evaluate the proposed framework on three real-world tasks, including toxic chat detection, reward modeling, and disease diagnosis.
  arXiv  Detail & Related papers  (2025-02-19T22:27:59Z)
• SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal [64.9938658716425]
  SORRY-Bench is a proposed benchmark for evaluating large language models' (LLMs) ability to recognize and reject unsafe user requests.<n>First, existing methods often use coarse-grained taxonomy of unsafe topics, and are over-representing some fine-grained topics.<n>Second, linguistic characteristics and formatting of prompts are often overlooked, like different languages, dialects, and more -- which are only implicitly considered in many evaluations.
  arXiv  Detail & Related papers  (2024-06-20T17:56:07Z)
• Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection [98.66771688028426]
  We propose a Ambiguity-Resistant Semi-supervised Learning (ARSL) for one-stage detectors. Joint-Confidence Estimation (JCE) is proposed to quantifies the classification and localization quality of pseudo labels. ARSL effectively mitigates the ambiguities and achieves state-of-the-art SSOD performance on MS COCO and PASCAL VOC.
  arXiv  Detail & Related papers  (2023-03-27T07:46:58Z)
• Dynamic Semantic Matching and Aggregation Network for Few-shot Intent Detection [69.2370349274216]
  Few-shot Intent Detection is challenging due to the scarcity of available annotated utterances. Semantic components are distilled from utterances via multi-head self-attention. Our method provides a comprehensive matching measure to enhance representations of both labeled and unlabeled instances.
  arXiv  Detail & Related papers  (2020-10-06T05:16:38Z)
• Weakly-supervised Salient Instance Detection [65.0408760733005]
  We present the first weakly-supervised approach to the salient instance detection problem. We propose a novel weakly-supervised network with three branches: a Saliency Detection Branch leveraging class consistency information to locate candidate objects; a Boundary Detection Branch exploiting class discrepancy information to delineate object boundaries; and a Centroid Detection Branch using subitizing information to detect salient instance centroids.
  arXiv  Detail & Related papers  (2020-09-29T09:47:23Z)

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.