PDES orchestration of small language models with non-AI verifier agents raises accuracy on four toy tasks from about 23 percent to 68 percent, with the verifiers supplying most of the correctness.
Title resolution pending
1 Pith paper cite this work, alongside 85 external citations. Polarity classification is still indexing.
1
Pith paper citing it
85
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Scalable, Symbiotic, AI and Non-AI Agent Based Parallel Discrete Event Simulations
PDES orchestration of small language models with non-AI verifier agents raises accuracy on four toy tasks from about 23 percent to 68 percent, with the verifiers supplying most of the correctness.