← back to paper

Review history

arxiv: 2607.07738 · 2 revisions

REFORGE: A Method for Benchmarking LLMs' Reverse Engineering Capabilities in Decompiled Binary Function Naming

1. 2026-08-02 ACCEPT HIGH v1.3.0-alltime-deepseek novelty 7.0
   78594 ms 9738 in 8880 out 2026-08-02T08:09:12.376814+00:00
2. 2026-07-10 CONDITIONAL HIGH v1.1.0-grok45 novelty 6.0
   29207 ms 14001 in 3372 out 2026-07-10T20:08:51.478328+00:00