activity
20242026
most citedEvaluating the Diversity and Quality of LLM Generated Content

1 citations · 1 across the 5 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

SWE-chat: Coding Agent Interactions From Real Users in the Wild

Joachim Baumann, Vishakh Padmakumar, Xiang Li +3

AI coding agents are being adopted at scale, yet we lack empirical evidence on how people actually use them and how much of their output is useful in practice. We present SWE-chat,…