Real-world software engineering rarely consists of isolated changes. Features, migrations, and systematic fixes often unfold across multiple pull requests (PRs), requiring coordinated modifications across a repository. Yet most executable repository-level benchmarks retain a single issue or PR as the task unit, while e...
Wei-Hao Li, Zi-Hang Xu, Zhong-Qiu Wang et al.· 0 citations
Poison Valleys defines plausible but incorrect software mechanisms, place each in a model's hypothesis, implementation plan, or both, and evaluates the generated code with an Oracle and targeted diagnostic coordinates, creating a measured connection from upstream misconception to code mechanism and failure form.
Large language model (LLM) agents now fix software, operate computers and serve customers, but their harnesses, the programs that run them, call a large LLM at every step, which makes long tasks slow and costly. Most of these calls end in a multiple-choice decision, such as which tool to call next. Decision models such...
Kun-Lun Zhu, Tao Feng, Xue-Ning Han et al.· 0 citations
Agentic large language models have been documented to lose reasoning capability when placed inside a harness, the software that mediates their observations and actions. To reconcile these losses, we introduce AutoOnboarder, an autonomous system that adapts an agent to a task the way a trainer onboards a new employee. I...
Tanay Arora, Cong-Lin Liu· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Background: Left ventricular excessive trabeculation (LVET) ranges from preserved ejection fraction (EF) morphology to reduced EF Noncompaction cardiomyopathy. Emerging evidence indicates that EF reduction is more strongly associated with thinning of the Compact myocardial layer (CL) than with trabeculation alone, alth...
B. Mester, K. Grebur, K. Farkas-Suto et al.· Scientific Reports· 0 citations
What this is. The complete, unfiltered result of the Phygas search for the pulsar PSR J1312+1810C: for each of 3,887 young open clusters and moving groups (of 4,087 in the catalogue; the others were excluded by a distance prefilter) it records how close, how long ago and at what relative speed the pulsar and the cluste...
Alperen Yavuz· Zenodo (CERN European Organi...· 0 citations
What this is. The complete, unfiltered result of the Phygas search for the pulsar PSR J2354+6155: for each of 4,077 young open clusters and moving groups (of 4,087 in the catalogue; the others were excluded by a distance prefilter) it records how close, how long ago and at what relative speed the pulsar and the cluster...
Alperen Yavuz· Zenodo (CERN European Organi...· 0 citations
What this is. The complete, unfiltered result of the Phygas search for the pulsar PSR J0514-4002I: for each of 3,934 young open clusters and moving groups (of 4,087 in the catalogue; the others were excluded by a distance prefilter) it records how close, how long ago and at what relative speed the pulsar and the cluste...
Alperen Yavuz· Zenodo (CERN European Organi...· 0 citations
What this is. The complete, unfiltered result of the Phygas search for the pulsar PSR J1701-3006B: for each of 3,972 young open clusters and moving groups (of 4,087 in the catalogue; the others were excluded by a distance prefilter) it records how close, how long ago and at what relative speed the pulsar and the cluste...
Alperen Yavuz· Zenodo (CERN European Organi...· 0 citations
What this is. The complete, unfiltered result of the Phygas search for the pulsar PSR J1824-2452A: for each of 4,042 young open clusters and moving groups (of 4,087 in the catalogue; the others were excluded by a distance prefilter) it records how close, how long ago and at what relative speed the pulsar and the cluste...
Alperen Yavuz· Zenodo (CERN European Organi...· 0 citations
What this is. The complete, unfiltered result of the Phygas search for the pulsar PSR J1124-5916: for each of 4,086 young open clusters and moving groups (of 4,087 in the catalogue; the others were excluded by a distance prefilter) it records how close, how long ago and at what relative speed the pulsar and the cluster...
Alperen Yavuz· Zenodo (CERN European Organi...· 0 citations
What this is. The complete, unfiltered result of the Phygas search for the pulsar PSR J1751-4657: for each of 4,084 young open clusters and moving groups (of 4,087 in the catalogue; the others were excluded by a distance prefilter) it records how close, how long ago and at what relative speed the pulsar and the cluster...
Alperen Yavuz· Zenodo (CERN European Organi...· 0 citations
StudentSim is a research system for evaluating and improving AI tutoring tools before they are tested with learners. It models how individuals may engage with tutors, giving feedback to improve tutor performance across subjects like chess, writing, and mathematics. The post Simulating student learning for better AI tutoring appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduOct 6, 2026
Writing as a participant and researcher, PhD student JS Tan SM ’22 has co-authored a new book about the rise of tech worker protests and the employer backlash that followed.
MIT News · Artificial Intelligence· news.mit.eduOct 2, 2026
Writing as a participant and researcher, PhD student JS Tan SM ’22 has co-authored a new book about the rise of tech worker protests and the employer backlash that followed.
Requirements in large systems rarely exist in isolation. Their meaning depends on the wider project context - other requirements, policies, decisions, tests, and implementation details. That becomes especially important when AI is used for review, because spotting a possible conflict or gap is only the beginning. ReqSpace explores how AI, visualisation, and connected project context can help reviewers understand those findings, trace the relationships behind them, and focus on the questions that…
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
