GAMBIT provides a three-mode benchmark and dataset for evaluating imposter detectors against co-evolved adaptive adversaries in multi-agent LLM systems on chess tasks.
Proceedings of the AAAI Conference on Artificial Intelligence , year =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
GAMBIT: A Three-Mode Benchmark for Adversarial Robustness in Multi-Agent LLM Collectives
GAMBIT provides a three-mode benchmark and dataset for evaluating imposter detectors against co-evolved adaptive adversaries in multi-agent LLM systems on chess tasks.