From Laboratory to Real-World Applications: Benchmarking Agentic Code Reasoning at the Repository Level

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Jia, Su, Yuxin, Lyu, Michael R.
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915974796541952
author Li, Jia
Su, Yuxin
Lyu, Michael R.
author_facet Li, Jia
Su, Yuxin
Lyu, Michael R.
contents As large language models (LLMs) evolve into autonomous agents, evaluating repository-level reasoning, the ability to maintain logical consistency across massive, real-world, interdependent file systems, has become critical. Current benchmarks typically fluctuate between isolated code snippets and black-box evaluations. We present RepoReason, a white-box diagnostic benchmark centered on abductive assertion verification. To eliminate memorization while preserving authentic logical depth, we implement an execution-driven mutation framework that utilizes the environment as a semantic oracle to regenerate ground-truth states. Furthermore, we establish a fine-grained diagnostic system using dynamic program slicing, quantifying reasoning via three orthogonal metrics: $ESV$ (reading load), $MCL$ (simulation depth), and $DFI$ (integration width). Comprehensive evaluations of frontier models (e.g., Claude-4.5-Sonnet, DeepSeek-v3.1-Terminus) reveal a prevalent aggregation deficit, where integration width serves as the primary cognitive bottleneck. Our findings provide granular white-box insights for optimizing the next generation of agentic software engineering.
format Preprint
id arxiv_https___arxiv_org_abs_2601_03731
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle From Laboratory to Real-World Applications: Benchmarking Agentic Code Reasoning at the Repository Level
Li, Jia
Su, Yuxin
Lyu, Michael R.
Software Engineering
Artificial Intelligence
As large language models (LLMs) evolve into autonomous agents, evaluating repository-level reasoning, the ability to maintain logical consistency across massive, real-world, interdependent file systems, has become critical. Current benchmarks typically fluctuate between isolated code snippets and black-box evaluations. We present RepoReason, a white-box diagnostic benchmark centered on abductive assertion verification. To eliminate memorization while preserving authentic logical depth, we implement an execution-driven mutation framework that utilizes the environment as a semantic oracle to regenerate ground-truth states. Furthermore, we establish a fine-grained diagnostic system using dynamic program slicing, quantifying reasoning via three orthogonal metrics: $ESV$ (reading load), $MCL$ (simulation depth), and $DFI$ (integration width). Comprehensive evaluations of frontier models (e.g., Claude-4.5-Sonnet, DeepSeek-v3.1-Terminus) reveal a prevalent aggregation deficit, where integration width serves as the primary cognitive bottleneck. Our findings provide granular white-box insights for optimizing the next generation of agentic software engineering.
title From Laboratory to Real-World Applications: Benchmarking Agentic Code Reasoning at the Repository Level
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2601.03731