cs.SE · 2026-08-28 · No. 98

Software Engineering, 2026-08-28.

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-Prime: Fewer Trajectories, Better Performance

    Dewu Zheng, Ruizhe Ye, Yanlin Wang, Yang Ye, Hongyu Zhang, Ensheng Shi, Xilin Liu, Yuchi Ma, Jianxing Yu, Zibin Zheng

    cs.SE · cs.AI · cs.CL

    To improve large language models' ability to resolve real-world software issues, prior work has focused on constructing large-scale agent trajectory datasets and performing supervised fine-tuning (SFT) on successful trajectories. However, task success does not guarantee high-quality supervision: successful trajectories may still contain ineffective, redundant, or risky steps. Directly using such trajectories for SFT can introduce noisy...

    arxiv.org/abs/2608.27449 · PDF

  2. 02

    From Static to Dynamic: Benchmarking Real-World Code Review with MCR-Bench

    Dewu Zheng, Yanlin Wang, Xiwen Wang, Kefeng Duan, Hongyu Zhang, Xilin Liu, Yuchi Ma, Zibin Zheng

    cs.SE · cs.AI · cs.CL

    In real-world software development, code review typically involves iterative interactions between developers and reviewers to improve software quality, making the process costly and time-consuming. Although recent work explores large language models (LLMs) for automated code review, most approaches oversimplify code review into a single-round, static decision task, which fails to capture the multi-round interactive nature and the complex...

    arxiv.org/abs/2608.27442 · PDF

  3. 03

    Persona-Execution Separation: An Architecture Pattern for Evolving LLM Agents under Execution Audit

    Yisen Xi

    cs.SE · cs.AI

    Large language model (LLM) agents in governed organizations must let the persona (instructions, tone, self-presentation) evolve freely, while keeping execution (stateful, audited work) traceable. A single trust domain does not satisfy both cheaply. We present Persona-Execution Separation (PES): persona and execution reside in different trust domains, connected by a governed contract bridge. The persona is singly-homed and may drift; execution...

    arxiv.org/abs/2608.27427 · PDF

  4. 04

    Beyond Execution: Auditing Experimental Fidelity in LLM-Driven Scientific Research

    Lezhi Yu, Xiaogang Xu, Yuhua Zhou, Shuibing He, Aimin Pan

    cs.SE · cs.AI

    LLM agents used for scientific experimentation must do more than generate executable code: they must implement the reference method faithfully, design experiments that test the paper's claims, and provide evidence supporting those claims. We show that agents often produce methodological hallucinations: silently reducing datasets or training budgets, replacing failed learning or generative components with lookup or oracle functions, or drawing...

    arxiv.org/abs/2608.26753 · PDF

  5. 05

    FaultLens: Learning Compact Behavioral Test Suites for Generated Operational Programs

    Zeming Liu, Hang Lyu, Jingtao Zhang

    cs.SE · cs.AI

    Generated operational programs are often validated with either a few hand-written examples or exhaustive regression suites. The former can miss sparse boundary and interaction faults, while the latter can be unnecessarily expensive. We introduce FaultLens, a method for learning compact behavioral test suites while preserving an auditable connection to executed evidence. It executes a rich probe domain once, stores the fault-probe kill...

    arxiv.org/abs/2608.26746 · 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.