Co-Saving cuts token usage by roughly half in multi-agent software development by injecting learned shortcut instructions that bypass intermediate reasoning steps, while slightly improving a composite code-quality score.
Chain-of-thought Prompting Elicits Reasoning in Large Language Models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Co-Saving: Resource Aware Multi-Agent Collaboration for Software Development
Co-Saving cuts token usage by roughly half in multi-agent software development by injecting learned shortcut instructions that bypass intermediate reasoning steps, while slightly improving a composite code-quality score.