ABF-Bench tests agents on verifiable blockchain fund tracing
A memory harness reached 75% edge recall, versus 47% for Codex and 10% for Claude Code.
Stories per day · 30 days
2 stories, newest first · one card per story
Stories tagged #blockchain-forensics
ABF-Bench makes blockchain fund tracing a verifiable LLM-agent task
Authors report 75% edge recall for their harness, versus 47% for Codex and 10% for Claude Code.