Introduces PACT protocol that projects agent outputs into action-state records, yielding comparable or better task performance with substantially fewer tokens in multi-agent LLM systems and production harnesses.
arXiv preprint arXiv:2405.14394 , year =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
What Should Agents Say? Action-state Communication for Efficient Multi-Agent Systems
Introduces PACT protocol that projects agent outputs into action-state records, yielding comparable or better task performance with substantially fewer tokens in multi-agent LLM systems and production harnesses.