WhitzardNUWA Lab ↗
NUWANUWA INDEX

Search NUWA Index

Research · Benchmarks · Findings · Perspectives

中文
← Library

Institution

ELLIS Institute Tübingen

Roles and affiliations follow the cited source. A source check is not an independent replication.

More filters →

ELLIS Institute Tübingen ↗

Detecting Multi-Agent Collusion Through Multi-Agent Interpretability

QuestionCan activation-based group detectors generalize from known collusion to new scenarios?

Source summaryEvery model reached 1.00 in-distribution AUROC.

NUWA research note · independent review pending · Contains: question / method / findings / interpretation / limits

PostTrainBench: Can LLM Agents Automate LLM Post-Training?

QuestionCan coding agents autonomously improve a supplied base model through post-training?

Source summaryThe best reported agent average was 23.2%, against 7.5% base and 51.1% official instruction-tuned averages.

NUWA research note · independent review pending

AutonomyCapability