cs.SE · 2026-09-02 · No. 103

Software Engineering, 2026-09-02.

7 new papers in cs.SE. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

7 entries
  1. 01

    Efficient SWE Agent Benchmarking via Trajectory-Aware Evaluation

    Kefeng Duan, Dewu Zheng, Yanlin Wang, Xiwen Wang, Ensheng Shi, Xilin Liu, Yuchi Ma, Jiachi Chen, Mingwei Liu, Zibin Zheng

    cs.SE · cs.AI · cs.CL

    Evaluating software engineering agents on realistic benchmarks is costly, since each task may require multi-step code exploration, modification, and test execution. Existing efficient evaluation methods select representative subsets to estimate full-benchmark performance, but are largely result-only: they fit historical pass/fail response matrices or static task semantics, discarding how agents solve problems. We propose PTA-IRT, a Privileged...

    arxiv.org/abs/2609.01603 · PDF

  2. 02

    Adaptive Critical Token-Aware Retrieval for Repository-Level Code Generation

    Kefeng Duan, Dewu Zheng, Yanlin Wang, Terry Yue Zhuo, Mingwei Liu, Jianxing Yu, Jiachi Chen, Ensheng Shi, Xilin Liu,...

    cs.SE · cs.AI · cs.CL

    The repository-level code generation task requires synthesizing code that satisfies task requirements while remaining consistent with the target repository context. Since real-world repositories often exceed the input length limits of LLMs, existing approaches commonly adopt retrieval-augmented generation (RAG) to provide repository-specific context. Despite improving repository-context retrieval, existing methods typically provide context as...

    arxiv.org/abs/2609.01601 · PDF

  3. 03

    Athena: Vulnerability-Affected Library Identification via Knowledge Graph Completion

    Phong Trinh Duy, Trang Dang Yen, Hung Nguyen-Huu, Bach Le, Quyet-Thang Huynh, Dieu Hoang Vu, David Lo, Thanh Le-Cong

    cs.SE · cs.AI · cs.CR

    A single vulnerability in a widely used library can cascade through millions of dependent applications, yet more than half of vulnerability database entries contain missing or incorrect affected-library information. Existing automated approaches neglect the relational structure of vulnerability databases, treating identification as an isolated text retrieval problem. In this paper, we propose Athena, the first graph-based approach for...

    arxiv.org/abs/2609.01187 · PDF

  4. 04

    Hints Help But Do They Teach? Evaluating Skills Transfer in Code Generation

    Will Badr

    cs.SE · cs.AI · cs.CL

    When a hint turns a failing generated program into a passing one, does it provide missing information or merely steer the model toward a solution it could already produce? We test these hypotheses on HumanEval+ and MBPP+ using executable evaluation. For Qwen2.5-3B-Instruct, adaptive relevant hints rescue 36 of 79 selected failures; an unrelated hint rescues 19, while eight unhinted samples solve 46 and recover 31 of the 36 relevant-hint...

    arxiv.org/abs/2609.01106 · PDF

  5. 05

    Does Fault Localization Beat a Fresh Attempt? A Placebo-Controlled Study of Test-Guided Code Repair

    Anik Jha

    cs.SE · cs.AI · cs.LG

    Fault localization can focus a code model's repair on the statements a failing test implicates, but a targeted edit may succeed merely because it is small, and a second model call may succeed without using the failure at all. We separate these explanations with three arms applied to the same failed candidate: blind whole-solution resampling, spectrum-based localization followed by suspect-span infilling, and same-length infilling at a...

    arxiv.org/abs/2609.00854 · PDF

  6. 06

    Probabilistic Model Checking of Autoregressive Neural Sequence Models

    Helge Spieker, Dennis Gross, Arnaud Gotlieb

    cs.SE · cs.AI

    Test-set accuracy is silent on two issues that matter when deploying autoregressive neural sequence models: how much probability mass the system under test (SUT) places on constraint-violating alternatives that are reachable under sampling and what fraction of the input population satisfies a domain requirement. We answer both with probabilistic model checking. The pipeline extracts a discrete-time Markov chain (DTMC) from the SUT's...

    arxiv.org/abs/2609.00838 · PDF

  7. 07

    Replacing Training with Memory: Listwise Selection for Text-to-SQL

    Yeonseok Jeong, Soyoung Yoon, Seongjun Lee, Seung-won Hwang

    cs.SE · cs.AI · cs.CL

    Modern Text-to-SQL systems often follow generate-execute-select pipelines, generating multiple candidate queries then selecting the best one. Listwise selection, by jointly comparing multiple candidates, has been widely adopted, but fine-tuning listwise selectors is costly. We thus propose a fine-tuning-free listwise selector. We replace two major fine-tuning objectives with inference-time strategies: (1) learning selection criteria as...

    arxiv.org/abs/2609.00834 · PDF

This edition is part of The Daily Abstract — cs.SE archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.