cs.SE · 2026-05-30 · No. 12

Software Engineering, 2026-05-30.

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

    Automating Low-Risk Code Review at Meta: RADAR, Risk Calibration, and Review Efficiency

    Chris Adams, Arjun Singh Banga, Parveen Bansal, Souvik Bhattacharya, Rujin Cao, Pedro Canahuati, Nate Cook, Brian...

    cs.SE · cs.AI

    AI-assisted coding tools have altered software production. At Meta, significant lines of code per human-landed diff grew by 105.9% year over year and per-developer diff volume rose 51%, with agentic AI responsible for over 80% of that growth. Meanwhile, the share of diffs receiving timely review has declined, exposing a widening gap between code supply and reviewer bandwidth. We ask three questions that progress from feasibility through...

    arxiv.org/abs/2605.30208 · PDF

  2. 02

    Projectional Decoding: Towards Semantic-Aware LLM Generation

    Boqi Chen, José Antonio Hernández López, Aren A. Babikian

    cs.SE · cs.AI

    Large language models (LLMs) are increasingly used to generate software artifacts across many software engineering (SE) tasks, yet ensuring the semantic validity of these artifacts remains a fundamental challenge. Existing constrained decoding techniques can enforce syntactic correctness and, in some cases, specific semantic rules, but lack a general representation that bridges LLM-generated text with the reasoning required for semantic...

    arxiv.org/abs/2605.30054 · PDF

  3. 03

    REPOT: Recoverable Program-of-Thought via Checkpoint Repair

    Parsa Mazaheri

    cs.SE · cs.AI · cs.CL

    One-shot Program-of-Thought (PoT) emits a Python program that prints a primitive-action plan; a single invalid action silently invalidates the trajectory. We introduce RePoT (Recoverable PoT): a deterministic verified replay that walks the plan through the environment to its first invalid transition, then one LLM call that resumes from the verified prefix. RePoT costs at most one extra LLM call on the ~14% of problems where PoT fails. RePoT...

    arxiv.org/abs/2605.30052 · PDF

  4. 04

    Agora: Toward Autonomous Bug Detection in Production-Level Consensus Protocols with LLM Agents

    Xiang Liu, Sa Song, Zhaowei Zhang, Huiying Lan, Jason Zeng, Ming Wu, Michael Heinrich, Yong Sun, Ceyao Zhang

    cs.SE · cs.AI

    Consensus protocols form the backbone of distributed systems and blockchains, where implementation bugs can cause data corruption and financial losses. While LLM-based approaches show promise in code analysis, they struggle with deep protocol-level logic bugs involving complex state-dependent behaviors across multiple execution stages. We present Agora, a domain-aware multi-agent framework that integrates hypothesis-driven testing with LLM...

    arxiv.org/abs/2605.29910 · PDF

  5. 05

    Inferring Code Correctness from Specification

    Tambon Florian, Papadakis Mike

    cs.SE · cs.AI

    Large language models (LLMs) have become integral to modern software development, enabling automated code generation at scale. However, validating the correctness of LLM-generated code remains a critical and largely unsolved challenge. Existing approaches either rely on dynamic consensus across multiple code candidates - making them costly and difficult to scale - or on static reasoning that is susceptible to dynamic bugs and order bias. In...

    arxiv.org/abs/2605.29822 · 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.