index
:
dissertation.git
logs
main
Undergraduate dissertation — Deceptive Alignment in Autonomous LLM Agents (UEL, 2026). Sandboxed agentic-LLM deception study: 960 runs, three-tier judging (regex + blackbox + glassbox).
summary
refs
log
tree
commit
diff
log msg
author
committer
range
path:
root
/
papers
/
2511.09030v1.pdf
Age
Commit message (
Expand
)
Author
2025-11-23
new paper
CaptainJack2491