Rewriting multi-agent LLM prompts as pseudocode with assertions, replanning, and comments yields moderate accuracy gains and large token savings in the tests reported here, though some headline numbers are overstated.
Virtualhome: Simulating household activities via programs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CodeAgents: A Token-Efficient Framework for Codified Multi-Agent Reasoning in LLMs
Rewriting multi-agent LLM prompts as pseudocode with assertions, replanning, and comments yields moderate accuracy gains and large token savings in the tests reported here, though some headline numbers are overstated.