ActBench, a 600-case trajectory-based benchmark, finds that behavioral safety of cowork agents depends more on the base language model than on the agent harness.
Advances in Neural Information Processing Systems , volume=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents
ActBench, a 600-case trajectory-based benchmark, finds that behavioral safety of cowork agents depends more on the base language model than on the agent harness.