A single deceptive evidence holder in an LLM multi-agent system sharply reduces collective fact recovery, and the false account propagates through honest agents.
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.MA 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
When Truth Is Distributed: Misinformation Derails Collective Fact Recovery in LLM-Based Multi-Agent Systems
A single deceptive evidence holder in an LLM multi-agent system sharply reduces collective fact recovery, and the false account propagates through honest agents.