cs.SE · 2026-08-04 · No. 74

Software Engineering, 2026-08-04.

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

01 — The papers

5 entries
  1. 01

    SWE-Touch: Benchmarking Coding Agents When Users Touch the Code

    Yuqiao Tan, Jinxiang Meng, Fangyu Lei, Minzheng Wang, Shizhu He, Jun Zhao, Kang Liu

    cs.SE · cs.AI · cs.CL

    Real-world software development requires coding agents to operate in shared workspaces where users may inspect and modify code during an ongoing task, yet existing repository-level benchmarks typically evaluate agents working alone or restrict user participation to messages. This leads us to ask: how do coding agents understand and respond to code changes in a shared workspace? We introduce SWE-Touch, a framework that stress-tests this...

    arxiv.org/abs/2608.02499 · PDF

  2. 02

    Lossless Tensor Compression as Program Synthesis

    Jieke Shi, Junda He, Wenjia Jiang, Weifeng Sun, Shidong Pan, Zhensu Sun, Chengran Yang, Peixin Zhang, Yifan Jia,...

    cs.SE · cs.AI · cs.PL

    Model checkpoints are growing in both number and size, which makes archival, transfer, and deployment increasingly costly. General-purpose compressors can reduce storage requirements but ignore tensor structure, whereas existing tensor-specific compressors rely on fixed and format-specific pipelines. We present Brevis, which formulates lossless tensor compression as program synthesis. We design a typed domain-specific language (DSL) that...

    arxiv.org/abs/2608.02162 · PDF

  3. 03

    Pretraining on Call Graphs: When Binary Analysis Tasks Profit From Context

    Samuel Valenzuela, Johannes Kinder

    cs.SE · cs.CR · cs.LG

    Binary function embedding models are trained to encode the semantics of binary code in such a way that they can be generalized to a variety of reverse engineering tasks, such as binary code search, vulnerability detection, or malware classification. While many models only take the function in question as contextual input, there have been successful attempts to improve function embeddings by leveraging information from the call graph. In this...

    arxiv.org/abs/2608.02084 · PDF

  4. 04

    TELLER: Non-intrusive Cross-Layer Root-Cause Analysis for LLM Inference

    Ruilin Xu, Junyi Li, Pengfei Chen, Zongxuan Xie

    cs.SE · cs.CL · cs.LG · cs.PF

    Large language model (LLM) inference has evolved from an offline workload into a continuously operated software service, yet root-cause analysis remains difficult because a single request spans the inference engine, Python/C++ backend, host CUDA APIs, GPU kernels, and distributed communication. Existing profilers expose raw timelines, while log-based diagnosis often misses cross-layer execution semantics and request-level structure. We...

    arxiv.org/abs/2608.01975 · PDF

  5. 05

    Effective and Efficient Context Retrieval via Partial Dependency Graph for Repository-Level Code Generation

    Zhongxin Liu, Zhonghao Jiang, Zhifan Ye, Haoye Wang, Jiakun Liu, Xiaoxue Ren

    cs.SE · cs.AI

    LLM-based repository-level code generation aims to generate code using the context available in a software repository, requiring LLMs to reason over complex code dependencies. Due to limited context windows and insufficient repository-specific understanding, LLMs typically rely on retrieval-augmented generation (RAG) to incorporate relevant code. Early RAG approaches primarily employ similarity-based retrieval, which often fails to retrieve...

    arxiv.org/abs/2608.01927 · 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.