Software Engineering Papers of the Week

As such, they can handle not only independent requests but whole chains of them, each request built on the last. Agents are known to report wrong work as done, yet benchmarks still test them one request at a time, on human-written code, checked once.

This paper presents the Structured Agentic Software Engineering (SASE) vision, outlining several of the foundational pillars for the future of SE.

We propose failure-boundary profiles, an evaluation in which each scenario family varies one measured factor, such as corridor width or the time gap in oncoming traffic, and each variant is certified from measurement as one where the agent should proceed or one where it should stop.

Whether an agent harness can continuously evolve across multiple tasks without suffering from catastrophic forgetting remains an important open question. In this paper, we investigate this open question through a comprehensive empirical study of continual harness self-evolution.

It is commonly evaluated by asking whether two programs are semantically equivalent, but a yes/no answer does not reveal whether a model knows which code change caused a semantic difference, or which sequence of code changes produced the modified program. We study two tasks that ask these questions directly, diagnosing semantic change and reconstructing sequences of code changes, alongside detecting semantic equivalence.

Repairing these bugs requires coordinated edits across multiple, disjoint code regions, posing substantially greater challenges. We present the first systematic study of LLM-driven coding agents ( Claude Code, Codex, Gemini-cli , and Qwen Code ) on this task.

This work devises a novel differential testing approach for QSSes, named QDIFF with three major innovations: (1) We generate input programs to be tested via semantics-preserving, source to source transformation to explore program variants.

On public SWE-bench Verified trajectories, where each model attempts each issue once, two run-independent factors dominate predictor performance.

Conclusion This study demonstrates the potential of LLMs to assist in architectural refactoring tasks and provides insights into optimizing their use through tailored prompting and retrieval techniques.

In this paper, we propose a retrieval approach for LLM-powered log level prediction that prioritizes context relevance over random selection and basic similarity.

To this end, we propose SE2, a self-exploring and self-evolving paradigm for adaptive edge AI development.

We introduce $\textbf{Foresight-SWE}$, a benchmark for measuring whether coding agents can anticipate and address unstated problems during software engineering tasks.

This paper investigates map-based code-representation workflows as a design variable in agentic software engineering, examining how different repository views change agents' retrieval behavior, task success, token use, and latency. In this paper, we study five code-representation workflows: abstract syntax trees, call graphs, module dependencies, documentation-enriched search, and a hybrid workflow that combines them.

In this paper, we conduct a large-scale empirical study to investigate the prevalence and impact of mislabeled issues in IRBL benchmarks.

In this work, we aim to complement prior work by analyzing the construct validity of agentic coding benchmarks.

Abstract Large Language Models (LLMs) are widely used in software engineering (SE) research and practice, yet their non-determinism, opaque training data, and rapidly evolving models threaten the reproducibility and replicability of empirical studies.

Specifically, we aim to investigate whether and how incubation of FOSS projects or bypassing incubation correlates with software quality outcomes.

We introduce SWE-Trail, a trajectory collector that uses earlier trajectories to guide subsequent collection while keeping that history outside the coding agent's context.

Rather than further increasing complexity within individual repositories, we introduce CrossSWE, a benchmark for cross-repository joint development comprising 171 real-world instances spanning 165 repositories, 20 technical domains, and 13 programming languages.