← back to paper

Review history

arxiv: 2605.20251 · 2 revisions

ProcCtrlBench: Evaluating Process-Level Defects and Control Preservation in LLM Coding Agents

1. 2026-05-22 UNVERDICTED LOW v0.9.0 novelty 7.0
   29518 ms 5732 in 1342 out 2026-05-22T10:00:55.458193+00:00
2. 2026-05-21 UNVERDICTED LOW v0.9.0 novelty 6.0
   55163 ms 5734 in 1548 out 2026-05-21T08:28:09.318998+00:00