cs.SE · 2026-09-19 · No. 118

Software Engineering, 2026-09-19.

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

01 — The papers

2 entries
  1. 01

    Quantifying Overclaiming Propensity in Frontier LLM Agents

    Nolan Smyth, Yorguin-Jose Mantilla-Ramos, Pascal Jr Tikeng Notsawo, Saskia Helbling, Alberto Tosato, Mohamed Amine...

    cs.SE · cs.AI · cs.LG

    Frontier coding agents are increasingly trusted to work autonomously for long periods, yet an agent's final response is often the only account of that work a user sees. We quantify the propensity of frontier agents to \emph{overclaim} task completion, a misrepresentation that can mislead the user. An agent overclaims when its final response contradicts information in its context. This definition requires no inference about intent and is...

    arxiv.org/abs/2609.20812 · PDF

  2. 02

    AdaRepair-Mem: Adaptive Experience Orchestration for Repository-Level Program Repair

    Z. C. Luo, J. C. Guo, W. J. He, S. Y. Wang, J. C. Yu, F. M. Zhao, Y. Chen, T. Cao, L. Q. Liu, N. Zheng, W. Xu, J....

    cs.SE · cs.AI

    Recent memory-augmented repository-level program repair methods reuse historical repair experiences to improve LLM-based issue resolution. However, our analysis reveals three limitations in existing repository-level memory retrieval. First, episodic memory is highly imbalanced across repositories, leaving low-resource repositories with little effective support. Second, more memory does not monotonically lead to higher repair success,...

    arxiv.org/abs/2609.20130 · 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.